International Journal of

Geo-Information

Article
Mapping Cropland Extent in Pakistan Using Machine Learning
Algorithms on Google Earth Engine Cloud
Computing Framework
Rana Muhammad Amir Latif 1 , Jinliao He 1, * and Muhammad Umer 2

1 The Center for Modern Chinese City Studies, Institute of Urban Development, East China Normal University,
Shanghai 200062, China
2 Department of Computer Science, COMSATS University Islamabad, Islamabad 22060, Pakistan
* Correspondence: [email protected]

Abstract: An actual cropland extent product with a high spatial resolution with a precision of up to
60 m is believed to be particularly significant in tackling numerous water security concerns and world
food challenges. To advance the development of niche, advanced cropland goods such as crop variety
techniques, crop intensities, crop water production, and crop irrigation, it is necessary to examine how
cropland products typically span narrow or expansive farmlands. Some of the existing challenges are
processing by constructing precision-high resolution cropland-wide items of training and testing data
on diverse geographical locations and safe frontiers, computing capacity, and managing vast volumes
of geographical data. This analysis includes eight separate Sentinel-2 multi-spectral instruments data
from 2018 to 2019 (Short-wave Infrared Imagery (SWIR 2), SWIR 1, Cirrus, the near infrared, red,
green, blue, and aerosols) have been used. Pixel-based classification algorithms have been employed,
and their precision is measured and scrutinized in this study. The computations and analyses have
been conducted on the cloud-based Google Earth Engine computing network. Training and testing
data were obtained from the Google Earth Engine map console at a high spatial 10 m resolution
for this analysis. The basis of research information for testing the computer algorithms consists of
Citation: Latif, R.M.A.; He, J.; Umer, 855 training samples, culminating in a manufacturing field of 200 individual validation samples
M. Mapping Cropland Extent in
measuring product accuracy. The Pakistan cropland extent map produced in this study using four
Pakistan Using Machine Learning
state-of-the-art machine learning (ML) approaches, Random Forest, SVM, Naïve Bayes & CART
Algorithms on Google Earth Engine
shows an overall validation accuracy of 82%, 89% manufacturer accuracy, and 77% customer accuracy.
Cloud Computing Framework.
Among these four machine learning algorithms, the CART algorithm overperformed the other three,
ISPRS Int. J. Geo-Inf. 2023, 12, 81.
https://doi.org/10.3390/
with an impressive classification accuracy of 93%. Pakistan’s average cropland areas were calculated
ijgi12020081 to be 370,200 m2 , and the cropland’s scale of goods indicated that sub-national croplands could be
measured. The research offers a conceptual change in the development of cropland maps utilizing a
Academic Editors: Giuseppe Modica,
remote sensing multi-date.
Maurizio Pollino and
Wolfgang Kainz
Keywords: geospatial analysis; Sentinel-2 MSI; machine learning; Google Earth Engine; cloud
Received: 12 December 2022 computing; cropland mapping
Revised: 10 February 2023
Accepted: 16 February 2023
Published: 20 February 2023

1. Introduction
Precise agricultural croplands are of considerable value in assessing and tracking the
Copyright: © 2023 by the authors.
world’s food and water health in broad regions that chart small to large fields. The presence
Licensee MDPI, Basel, Switzerland. of humans has already been a significant part of the research on the Earth’s atmosphere [1].
This article is an open access article However, stronger relations the with economic and social sciences are required to study the
distributed under the terms and projected population development, migration trends, allocation of food resources, and earth
conditions of the Creative Commons management practice to adapt to current global biodiversity challenges [2]. These methods
Attribution (CC BY) license (https:// are also very relevant to assess the worldwide cultivation of water, the productivity of crops
creativecommons.org/licenses/by/ (productivity per unit of soil), the productivity of water (crop per drop or productivity per
4.0/). unit of water), and studies regarding food security [3–6]. The efficient monitoring of crop

ISPRS Int. J. Geo-Inf. 2023, 12, 81. https://doi.org/10.3390/ijgi12020081 https://www.mdpi.com/journal/ijgi

ISPRS Int. J. Geo-Inf. 2023, 12, 81 2 of 24

conditions requires the regional, timely, precise, and cost-effective mapping of croplands. In
this case, spatially dispersed remote monitoring maps with high spatial resolution provide
a powerful means for the monitoring of croplands [7].
The recent decades have seen a proliferation of global and national cropland devices
that make use of the medium to coarse (250 m to 1 km) distant sensing data, such as the
(AVHRR) Advanced Very High-Resolution Radio, and the (MODIS) Moderate Resolution
Image Spectroradiometer [8–13]. Their geographical distribution patterns and features,
such as the strength of crops and crop superiority, are highly beneficial to offer an initial
evaluation of agricultural croplands. However, the poor resolution of such materials
hinders the applicability of these materials in appraising small farms [14]. In addition,
the Land Use Land Cover (LULC) products generated using various remote sensing data
containing croplands that are agricultural in one or more categories are subject to worldwide
regional land utilization. Topics include the MCD12Q1 [15], Global Land Cover Fine
Resolution [16], and Globeland30 [17]. However, the LULC-focused goods did not focus
on mapping croplands in depth. Cropland accuracy is also affected [18]. Many of these
products are often coarse.
Cropland concepts often vary from product to product, with specific cropland out-
comes and features for each product. In general, the current cropland scale items are of
gross resolution, lack field specifics, or are mapped in certain LULC categories with no
emphasis on different cropland classes [19]. Consequently, very high risks and failures
exist at cropland locations. In the past, there have been incidences of agricultural cropland
monitoring using sophisticated remote-sensing technologies. Such studies were based on
numerous sensor data for various irrigated and rain-fed cultures with spectral, radiometric,
and spatial-temporal resolutions [8,9,13,20–27]. This approach consists of object-based
or pixel-based techniques or a combination of unsupervised and supervised techniques.
Pixel-based approaches include: (a) employing a time-weighted dynamic temporal warp-
ing analysis based on pixels and objects [20], (b) the Knowledge-Based Temporal Features
method [7], (c) the RF Algorithm [22,28], (d) SVM Support Vector Machines [29], (e) the
probabilistic method [30], (f) Decision Tree [31,32], (g) Spectral Matching techniques [33,34],
and (h) phenomenological approaches [35,36].
A current attempt was made to map the cropland scale to semi-automatics preparation
and multi-classification method approaches [37,38]. Nevertheless, such approaches have
primarily been applied to: (a) high-resolution (Landsat 30-m) areas, (b) limited areas,
and (c) multi-temporal intermediate (250-m or higher) remotely sensed data. Obtaining
high-quality, cloud-accessible imagery and using multi-temporal, high-resolution data
has previously been challenging for farmland mapping over broad expanses. However,
these problems have been eliminated due to a shift in underlying data collection regarding
remote sensing, administration, and analysis paradigms. Sentinel-2 routinely collects
the high-resolution visual imagery of land and ocean environments (10 m to 60 m) [39].
The Sentinel-2 multi-spectral satellite captures details in 13 invisible, short-wave, short-
spectrum frequencies. Sentinel-2 protects the coast and the Mediterranean Sea from 56◦ S
to 84◦ N. The Sentinel-2 satellite revisits and captures land area imagery of the exact land
area coordinates or the same area of land at five day intervals. However, the viewing
angles vary. Sentinel-2 captures scenes with room resolutions of 10 m, 20 m, and 60 m [40].
Managing vast amounts of Landsat data for study across broad areas is a primary challenge
in modern remote sensing strategies utilizing commercial imagery processing tools on
PC-based workstations [41].
Whatever the strength of the devices, the entire data analysis operation, including pre-
processing, is complicated, slower, and repetitive in vast areas, including 1000 sentinel-2
images. Large-scale sensing without these limitations is now possible thanks to the advent
of the internet and the widespread adoption of high-powered ML algorithms in cloud
computing platforms such as the Google Earth Engine [42,43]. Ref. [43] demonstrated
that a GEE database that incorporates earth observers and airborne sensors, such as the
United States Department of Agriculture (USDA), Moderate Resolution Imaging Spectrora-
ISPRS Int. J. Geo-Inf. 2023, 12, 81 3 of 24

diometer (MODIS), National Agriculture Statistical Service (NASS), National Aeronautics

and Space Administration (NASA), Cropland Data Layer(CDL), and the United States
Geological Survey (USGS) Landsat, and weather/climate databases, as well as automated
elevator templates, can be integrated to include multi-petabyte repositories of georefer-
enced databases.
This framework’s robust data management has made it applicable to various geospatial
processing tasks. GEE allows batch processing using Python or JavaScript on application
program interfaces and supports essential machine learning algorithms (MLAs) that are
commonly beneficial for image enhancement and picture classification application pro-
gramming interfaces (APIs). It does away with the need for many pre-processing steps
in traditional remote sensing systems. Some research [44] has recently utilized the GEE
platform for global and continental-scale mapping projects. Thus, this analysis’s primary
objective was to map all croplands comprehensively using high-resolution (up to 60 m),
multi-year (2018–2020) (five-days), and multi-spectral instrument (sentinel-2) level-1C
data for all of Pakistan. Pakistan has vast fields of cropland with different crop systems.
It is a primary producer of agricultural produce and an exporter of large commercial
agricultural fields [44].
Significant crops in agriculture, including rice, wheat, cotton, sugarcane, and maize,
have recorded 25.6 percent value-added in agriculture and 5.3% of the gross domestic
product in Pakistan. Wheat is a major crop in this region’s agricultural industry, accounting
for 10% of the value-added agriculture and 2.1% of the gross domestic product [45]. There
has been a downturn in the field of wheat growing and development. The area of wheat-
growing regions decreased from 9,199,000 to 9,180,000 hectares from 2013 to 2015. The
wheat output decreased from 25,979,000 tons in 2013–2014 to 25,478,000 tons in 2014–2015,
which accounted for 0.7% of the GDP, and a 3.2% additional value of cultivation compen-
sated for rice crops [46]. There has been an increase and development in the regions planted
with rice. From 2014 to 2015, the production of rise rose from 6,798,000 to 7,005,000 tons
and the area grew from 2,789,000 to 2,892,000 hectares. Maize is a significant crop of grain,
contributing 0.4% of the gross domestic product and 2.1% value-added for agriculture.
The region and yield planted with maize has decreased. The field area decreased from
1,168,000 hectares to 1,130,000 (4,695,000 tons) hectares [47].
The Sentinel-2A satellite includes a large, swath-high resolution multi-spectral imager
consisting of 13 spectral bands. It is undertaking field-based surveys in favor of forest
surveillance, analysis of improvements in the region of ground cover, and the control of
natural disasters [48]. Sentinel-2B was deployed on 7 March 2017 as a European satellite
for optical imagery. The second Sentinel-2 satellite deployed under the European Space
Agency Copernicus System would be 180◦ relative to Sentinel-2A. The Sentinel-2A satellite
has a wide bandwidth of 13 spectral bands and high-resolution multi-spectral images. The
satellite provides details including predicted crop yields, agriculture, and forestry [49].
The province of Punjab is Pakistan’s largest wheat-producing district and comprises
roughly 76% of Pakistan’s total area under wheat [50]. Pakistan has an average field
area of 2.1 ha [51] in a small-form land tenure system. Approximately 10% of fields less
than 1 ha are in the Punjab province. The wheat of sugar cane, clover, vegetables, and
fruit groves may sometimes be cultivated in mixed cropping systems. In countries with
small-scale farms and heterogeneous agricultural regimes, remote detection strategies are
often considered unsuitable [52]. Therefore, satellite data’s adequate characterization of
Pakistan’s wheat region poses many challenges. Medium-resolution sensors, such as the
MODIS, are highly insufficient at monitoring smaller or scattered crop fields at 250 m
(1 pixel is approximately 6.25 ha). Sentinel-2 Multi-spectral instrument (MSI-Level-1C)
photos can display tiny and scattered farms in addition to broad farms at a high resolution
of up to 60 m (1 pixel roughly 0.09 ha). Furthermore, the farmlands in Pakistan, as well as
its valleys, river banks, and vast plains, are quite complex.
We are using the GEE cloud-computing infrastructure with Sentinel-2 MSI data from
many classifiers; the project aimed to create a 60-m-deep picture of Pakistan’s cropland.
ISPRS Int. J. Geo-Inf. 2023, 12, 81 4 of 24

While the United States Department of Agriculture (USDA) has a farmland layer called
the 30 m Cropland Data Layer (CDL) derived from Landsat imagery, Pakistan does not
have anything comparable [53]. Therefore, the research aimed to generate a precise 30-m
cropland extent map of Pakistan using 16-day Landsat-8 Operational Land Imager (OLI)
data for the notional year 2018–2019 using a range of machine learning classifiers through
the GEE cloud computing platform. Since MLAs have effectively categorized large datasets
at high spatial and temporal resolutions for wide-area land cover mapping, we employ
pixel-based machine learning approaches for this investigation [54]. Second, this research
used a large quantity of reference training and validation data, such as data from reputable
secondary sources and data ranging from sub-meter to 5-m extremely high-resolution
photography. The machine learning classifier’s accuracy and degree of uncertainty were
determined by its training on these reference datasets. Third, the 30-m farmland product’s
calculated cropland area was compared to national and subnational agricultural areas
based on statistical analysis.
For these reasons, creating accurate maps of farmland in these two nations is crucial.
Since MLAs were extremely useful for categorizing big datasets at high spatial and temporal
resolutions for mapping vast expanses of land, we opted for a pixel-dependent MLA
approach for this study [55]. Second, this research trained and compared its models using
a diverse set of high-resolution sub-meter to 10-m picture samples. Machine learning
classifiers benefited from being trained on such comparison datasets, which also helped to
measure classification accuracy and generate uncertainty.

Sentinel-2 Data Literature Study

A brief literature study on Sentinel-2 data with its social implications is presented
below. For the literature study, research articles in the context of geospatial data analysis on
Sentinel-2 data & Sentinel-2 data analysis with ML algorithms were gathered and selected,
as shown in Table 1.

Table 1. The literature study of Sentinel-2 data analysis with Machine Learning algorithms.

Authors Social Implications/Article Summary

This paper assesses how the Sentinel-2 approach for time-weighted
dynamic time-setting (TWDTW) works in three fields of research (In
Romania, Italy, and the US) for pixel- and object-based categorization of
(Belgiu&Csillik, 2018)
various crop varieties. The classification outputs for pixel-and
[20]
object-based image processing systems are contrasted with Random
Forest (RF). Both approaches have been tested for their response to the
testing samples.
(Xiong, J., Thenkabail, P.S., Tilton, J.C., Gumma, M.K.,
This work reveals that we use Sentinel-2 (10 m to 20 m) for 10 days, and
Teluguntla, P., Oliphant, A., Congalton, R.G., Yadav, K.
Google Earth Engine Landsat-8 Data for a mapping approach to cropland
and Gorelick, N., Xiong, J., 2017)
in broad spatial resolution (30 m or better).
[56]
This article presents the findings of a study on cropland mapping using
artifacts as spatial analysis units from the Sentinel-2 time series
information. A multi-resolution segmentation algorithm was
automatically divided into the Sentinel-2 data series, and the resulting
(Csillik&Belgiu, 2017)
image artifacts were categorized using the Time-Weighted Time Warping
[57]
(TWDTW) technique. We used this method in the agricultural region of
southeast Romania to chart wheat, corn, rice, sunflower, and trees. The
applied cropland mapping system has obtained a cumulative precision of
93.43% and a kappa index of 92%.
ISPRS Int. J. Geo-Inf. 2023, 12, 81 5 of 24

Table 1. Cont.

Authors Social Implications/Article Summary

To construct land utilization charts from a smallholder agricultural zone
(Lebourgeois, V., Dupuy, S., Vintrou, É., Ameline, M., in Madagascar at five different nomenclature rates, we analyzed and
Butler, S. and Bégué, A., 2017) enhanced the performance of a hybrid Random Forest classifier/object
[58] technique. Step one was to improve the RF classifier by increasing the
number of input variables.
(Castaldi, F., Hueni, A., Chabrillat, S., Ward, K., This research aims to use signal-to-noise ratio (SNR) to evaluate the
Buttafuoco, G., Bomans, B., Vreys, K., Brell, M. and van efficacy and importance of spectral and spatial resolution. The
Wesemael, 2019) capabilities of multi-spectral S2 and hyperspectral airborne remote
[59] sensing data are compared in this study.
This paper establishes a method of analyzing crop performance at
farm-to-community rates with Sentinel-2 high-resolution series and soil
(Lambert, Traoré, Blaes, Baret, & Defourny, 2018)
data in the Koningué municipality of Mali. The study is based on the
[60]
supervised, pixel-dependent classification of crop forms in the current
cultivable mask.
This study examines whether a Sentinel-2 data time series can be used to
examine mowing rates in the Swiss Canton of Aargau. Two Cloud
(Kolecka, Ginzler, Pazur, Price, & Verburg, 2018)
Casting techniques and three SPM devices were evaluated for their
[61]
capacity to detect and track grassland management tasks (pixels,
pavement polygons & shrunken pail polygons).
This crop map of Belgium was made using optical data from the
(Van Tricht, Gobin, Gilliams, & Piccard, 2018) Sentinel-1 and Sentinel-2 satellites. The excellent accuracy of 82% and a
[62] Kappa value of 0.77 were achieved while estimating eight crop forms
using an automated random forest classifier.
This method combined the sensors’ data into a unified yearly composite.
The south’s water, forests, urban and built-up water, croplands, rubber,
(Poortinga, A., Tenneson, K., Shapiro, A., Nquyen, Q., palm oil, and mangrove were used as benchmarks against which to
San Aung, K., Chishtie, F. and Saah, D., 2019) analyze and assess several factors. Through this training data, we were
[63] able to generate many levels of biophysical probability for each class. In
decision-tree logic and Monte Carlo simulations, these fundamental
building blocks were used for the base and probability charts.
In this study, we examined the applicability of the Breaks for Additive
Season and Trend (BFAST) method for characterizing land-use anomalies
in land-use research, and we provided an overview of a time-series
(Kanjir, Ðurić, & Veljanovski, 2018)
approach utilizing Sentinel-2 images. This study examines the
[64]
relationship between time-defined greenness and the improper use of
permanent widows and agricultural fields throughout one growing
season (vegetative vigor).
The research provides one of the wealthiest wetland-sized provinces in
(Mahdianpari, Salehi, Mohammadimanesh,
Canada with a first comprehensive inventory chart of wetlands. Five
Homayouni, & Gill, 2019)
wetland groups and three non-wetland groups were set up around the
[65]
island of Newfoundland. Together, they cover about 106,000 km2 .
The research addresses the benefits and limitations of classification
(Shelestov, Lavreniuk, Kussul, Novikov, &
compared to the consistency obtained for various categories for the
Skakun, 2017)
Ukrainian environment and uses a neural network method to equate it to
[66]
the classifier.

2. Literature Review
The literature uses various classification techniques and algorithms for picture seg-
mentation and classification, including SVM, Deep Learning, Random Forest, and others.
The Random Forest framework has been built with the help of particle swarm optimization
and the learned representation of filter [67] photos of a road scene and an Indore scene in
order to do semantic segmentation. Random Forest was used for landcover classification as
an object-based image classification method [68]. The Mudrock picture segmentation model
ISPRS Int. J. Geo-Inf. 2023, 12, 81 6 of 24

was built using deep learning and pixel values. A comparison was made between this
model and the Random Forest algorithm to determine its efficacy [69]. Semantic ground
cover segmentation in Worldview-2 pictures was performed using a CNN model. SVM and
Random Forest were used to evaluate the outcomes [70]. Using the Semantic Texton Forest
framework, we have successfully applied class-specific picture semantic segmentation
based on textual and color characteristics to the publicly available datasets CamVid and
MSRC-v2 [71]. Support Vector Machine (SVM) [72] has been implemented [73] to use land-
cover data to develop a unified method that can account for variations in both spectral and
spatial dimensions. We examined the performance of four machine learning algorithms,
Random Forest, Support Vector Machine, Naive Bayes, and k-Nearest Neighbor on satellite
data for object-based analysis and semantic land cover segmentation [74]. Using optical
remote sensing images, semantic segmentation, and a Deep Convolutional Network, we
were able to forecast potential landslide danger zones [75]. To create a land cover map, we
utilized the SVM algorithm on images from the CORONA collection [76]. A method of
categorization was presented for use in object-based picture analysis via a comparison of
random forest and support vector machine (SVM) for wetland area categorization utilizing
Deep Convolutional Neural Networks (DCNN) and Fully Convolutional Networks (FCN).
The difference results from the additional time and effort spent on the computer and on
additional training data [77]. To classify the land cover dataset, a Multi-Level Feature
Aggregation Network was introduced to combine feature extraction with up-sampling [78].
One way to segment the Kalideos database remote sensing images into distinct study areas
was to use object and pixel processing. Using a Multilayer Feed-Forward Neural Net-
work (MLFFNN), we compared its performance to that of SVM and Maximum Likelihood
Classification when segmenting images for semantic meaning (MLC) [79]. Wetlands were
modelled using four classifiers (k-Nearest Neighbor, Random Forest, and Decision Tree).
Classification accuracy was calculated by comparing these models to a hybrid model in-
cluding ANN [80]. The semantic segmentation of roadways, shoulders, guardrails, ditches,
fences, and boundaries was performed using PointNet and ANN [81]. Using CNN’s fea-
tures together with various filters and multi-resolution segmentation, a technique was
proposed for semantic segmentation of LiDAR data and high-resolution optical images [82].
These methods use pixel-wise semantic segmentation to label the area of interest.
Satellite photos are complicated and challenging to segment because of the similarities
in the texture of different regions. These algorithms extract the texture, patterns, and
orientation of images to identify distinct areas. The literature does not reveal any studies
focusing on mapping agricultural acreage and increasing agricultural output to the same
extent. Our group mapped agricultural farmland using semantic segmentation results to
identify cultivated and uncultivated areas. The weak regions might be used in agriculture
and horticulture to distribute food better. Additionally, it helps pinpoint the yearly decline
of farmland, which is a crucial indicator for environmental sustainability. Compared with
deep learning algorithms, machine learning methods such as Random Forest, Support
Vector Machine (SVM), Naive Bayes, and CART are more efficient regarding data amounts,
computational complexity, and memory utilization.

3. Study Area
Pakistan, located in Southern Asia, has a total land area of over 790,000 km2 and has
a moderate climate. Some regions of the United States have dry or semi-arid climates,
whereas others do not. Most of Pakistan’s arable land is located in the country’s southern
and eastern regions rather than its northern and western ones. The appearance of the same
crop growing in several locations might vary considerably [83]. Mountains (such as the
Himalayas and Karakoram), plateaus, bare-rock regions, and deserts are a part of the varied
landscape. Most northern and southwestern farmland fields are small because mountains,
bare rocks, and deserts are poor locations to raise crops. There are extensive plains in the
southeast, with densely populated agricultural areas running beside the Indus River [84].
ISPRS Int. J. Geo-Inf. 2023, 12, 81 7 of 24

Our field of research included Pakistan, the world’s largest cropland region. Four
developed agro-ecological zones, which help to define areas with everyday cultivation
activities, and forms with soil and environment trends, are stratified among Pakistan’s
regions, as shown in Figure 1.

Figure 1. The division of the agro-ecological study into specialized subfields (RAEZs). The distribu-
tion of comparative training data in machine learning algorithms is also shown in the illustration.
Based on the pixel classification, the analyzed supervised areas match.

Pakistan’s long history of extensive and cautious farming has resulted in sophisticated
agricultural practices, a diverse selection of crops, and a variety of croplands that can adjust
to a broad range of environmental and topographical factors [85]. When these factors come
into play, it becomes more challenging to acquire farmland. Cropland on the southeastern
plains is uniform in shape, closely spaced, and widely dispersed. The southwest plateaus
are dotted with towns and farmland. Terraces and fields strung out along valleys and
rivers may also be seen in the northern mountain areas. Pakistan, as a “paradigmatic
example of Asian agriculture, is characterized by a wealth of crop varieties, significant
spatial differences in crops, intra-class variations of the same crop in different regions, and
complex small-scale farming techniques, including crop rotation on the same plot during
different seasons and intercropping”.
There is a great deal of work in farmland mapping utilizing earth observation data sets
despite the limited availability of operational charts, for various reasons. Identifying plant
types necessitates using fine-scale time-lapse images to establish the minute differences
between crop phenology. Second, crops are unique landscape units that require an adequate
spatial resolution to be resolved unambiguously [86], which is the standard technological
compromise between time and geographical resolution for Earth observation satellites. For
data sets with poor spatial resolution, duplicated imagery at a given location does not yield
a high return quality. Moderate-resolution imaging spectrometer (MODIS) sensors with a
worse spatial resolution, such as 250 m per 250 m, have wider swaths and greater repeat
imaging frequencies, but are restricted to producing accurate surface estimates for small
farm sizes [87].
Since its introduction in 2015, Sentinel-2 has been available in two unique versions:
Sentinel-2A and Sentinel-2B. Three hundred and fifty photographs from the Sentinel-2
satellite were selected using the Google Earth Engine (GEE); they were collected between
January 2018 and December 2019. High-resolution Google Earth remotely sensed images
were utilized to provide visual interpretations of land cover categories, and the Google
Earth Engine platform was used to generate 857 training sample points and 200 test sample
points at random. Vegetable gardens were retrieved together with planted croplands, since
their distinction could not be made while processing remotely sensed images. Furthermore,
in this case, we are talking about adjustments to the Food and Agricultural Organization’s
ISPRS Int. J. Geo-Inf. 2023, 12, 81 8 of 24

(FAO) Global Agro-Ecological Zones (GAEZs), with a spatial resolution of 10 km, with an
eye on the increasing importance of days, soil, and land [88]. As many of these locations
contain a negligible proportion of cropland relative to the rest of the nation, the GAEZs
include various zones to partition croplands. Consequently, we refined GAEZ into Refined
Agro-Ecological Zones (RAEZs) with the ASTER Global Digital Model 2 (GDEM V2)
30 m data slope generated from 30 m GDEM and cropland percentage data in one region,
utilizing advanced space-based thermal emission and reflection radiometers (ASTER).
Various RAEZs, based on the area’s significance for croplands, are merged into vast regions.

4. Dataset
Data was used for the analysis of Sentinel-2 MSI (Level-1C). First, the satellite sensor
data will be identified and discussed, followed by comparison validation and training
in Pakistan.

4.1. Sentinel-2 MSI Satellite Imagery Data

Data from the Sentinel-2 MSI satellite’s multi-spectral sensor were stored in Pakistan’s
GEE cloud for two years (2018–2019) to study grain dynamics at different times of the year.
Recent advances in multi-spectral sensors, such as the Sentinel-2 Multi-Spectral Imager
(MSI), have improved signal-to-noise ratios and narrowed spectral bands, promising fruitful
rangeland management [89]. According to research comparing S-2 to Landsat-8 and earlier
Landsat sensors, the geographical and spectral ability of Sentinel-2 to differentiate between
range and land management has been improved [90]. Information from Sentinel-2 between
10 m and 60 m in resolution is updated every 5 days. Due to cloud limitations, we cannot
get continuous 5-day server-free time series results for wall-to-wall coverage over the whole
region. Bimonthly composites were created to overcome this barrier and guarantee clear
or almost perfect wall sight everywhere (taking into account the cloudiness of different
countries and locations). As seen in Figure 2, mega-file data cubes (MFDCs) ranging in
size from 10 m to 60 m were constructed. These MFDCs were used to generate a 48-band
MFDC for six-time intervals (temporal composites).

Figure 2. 10m to 60m Sentinel-2 MSI data were composed for six time-frames. Eight bands were
formed for every time frame (e.g., time 1: Julian days 1–60), taking the median value of one pixel for
each cycle (SWIR 1, SWIR 2, Red, NIR, Black, Cirrus, Aerosol, and B.
ISPRS Int. J. Geo-Inf. 2023, 12, 81 9 of 24

Regarding the research region, we used the multi-year (2018–2019) five-day Sentinel-2
for (1) maintaining the wall-to-wall data coverage; and (2) maintaining the effect of the
cloud coverage. Based on seasonal variations in the region and the quality of cloud-free
Sentinel-2 data, the nominal years 2018 and 2019 were further subdivided into various
cycles or phases. MFDC cloud-free wall-to-wall collections from Pakistan were developed
in bi-monthly or tri-monthly intervals. The product of a total of six cycles (period 6:
301–365, period 5: 240–300, period 4: 181–240, period 3: 131–240, period 2: 61–120, and
term 1: Julian 1–60 covering 12 months may be produced in cloud-free or nearly cloud-free
pictures for bi-monthly intervals. Notably, Sentinel-2 multi-year (2018–2019) details are
used to optimize the chances of cloud-free pixel purity over Pakistan over each period
(e.g., 1–60 days). As a result, all Sentinel-2 five-day photographs were gathered covering
Pakistan. Cirrus (1376.9 nm), Aerosol (442.3 nm), SWIR 2 (2185.7 nm), SWIR (1610.4 nm),
NIR (833 nm), red (665 nm), green (559 nm), and blue (492.1 nm) were used with each
duration. These images contributed to a 48-band MFDC with eight median-meaning bands
consisting of six cycles. The band stack and periods lead to MFDC. Both compositions were
carried out on the GEE cloud-based geospatial data research tool [43]. The restricted supply
of temporal pictures and Sentinel-2 TOA items were used instead of Surface Reflectiveness
(SR), as shown in Figure 2 and Table 2.

Table 2. Sentinel 2: MSI 10 m to 60 m data used in the study characteristics multi-temporal multimedia.

The Mega-File
The Time-Composite Name
Name of the Data Cube The Series of
of Julian Days over Data Years of the Data
Data Provider with Total # of Sentinel-2
Data Provider
Bands
C1: 1–60
C2: 61–120
European Multi-Spectral European
C3: 121–180
Pakistan Union/ESA/ 48 2018, 2019 Instrument, Union/ESA/
Copernicus C4: 181–240 Level-1C Copernicus
C5: 241–300
C6: 301–365

4.2. Training and Validation Sample Croplands

In the following stage, Pakistan’s training and assessment data were compiled. Train-
ing and testing data points or samples have been collected to train our machine learning
algorithms in this phase. A machine learning algorithm used training samples to learn the
underlying knowledge and then used these samples as a reference for classifying the land
surface as cropland or non-cropland areas. Furthermore, testing samples were used to test
how well our machine learning algorithm learned from the training phase. Samples have
been obtained for a wide range of cropland and non-cropland groups with stable distribu-
tion in Pakistan. Validation data have been used for precision, mistake, and uncertainty.
Croplands have been described as farmlands with an annual crop standing + croplands
fallows + permanent crops [21]. The comparison training and evaluation data were then
correctly labeled. In Pakistan, other observations were made using very high spatial resolu-
tion imaging (VHRI) sub-meter to 10-m and several years of Google Earth Engine photos.
Of these, 857 measurements and 200 study samples were obtained, as shown in Figure 3.
ISPRS Int. J. Geo-Inf. 2023, 12, 81 10 of 24

Figure 3. Sub-meter to 10 m image details with a relatively good resolution for Pakistan. Illustration
of Pakistan’s comparison training data obtained using high-resolution imagery sub-meter to 10 m.

Table 3 describes the distribution of the comparison training and validation results.

Table 3. Education and confirmation details on sources. A collection of comparison samples

used by machine-learning algorithms and the number of testing samples required to determine
autonomous accuracy.

Class Training Samples Validation Samples

Cropland 416 100
Pakistan
Non-Cropland 441 100

5. Methodology
The objective of the analysis was for Pakistan to develop the correct cropland scale
commodity Sentinel-2 at 10 m to 60 m. Figure 3 illustrates the procedure to generate
croplands for Pakistan utilizing five days’ time-series data for the 2018–2019 time frame.
We have implemented a pixel-based supervised classification technique using the many
machine learning classifiers in the GEE cloud computing architecture. A description of the
method has been provided in Figure 4.
ISPRS Int. J. Geo-Inf. 2023, 12, 81 11 of 24

Figure 4. A review of cropland planning techniques. The research used classification algorithms
for pixel-based supervised machine learning. The study was carried out on the cloud infrastructure
framework of Google Earth Cloud.

5.1. Machine Learning Algorithms

We have selected four different algorithms: Rides, Support Vector Machine (SVM),
Random Tree, and Naïve Bayes Pixel-based supervised. In addition, the algorithm accura-
cies listed were compared. They are often robust to detect noise and overfitting and are
particularly effective for categorizing remote sensing devices. In remote sensing systems,
SVM receives the most attention. SVMs are subjected to highly effective classifiers and pos-
sible remote sensing data inquiry methods. SVMs have a technique for categorization, not a
statistical norm but a geometrical norm based on the margins. To achieve the categorization
function, SVMs do not require inferences of statistical distribution in the groups, but by
manipulating the edge maximization model, they describe the categorizing model [91]. An
array of binary decision trees constructs a random forest classifier by selecting a portion
of the sample bootstrap from the input data and selecting an informative subset for each
partition [92]. The RF concept is superior to that of a single decision tree. The bootstrap
combines (bag) a collection of decision trees by scanning random subspaces from the data
(features) and breaking up the nodes at most, eliminating the association between the trees.
In random forest, graders often quantitatively calculate the contribution of each variable
to the classification performance, which is helpful in determining the significance of each
variable. They have a test of internal precision for an ‘off-bag’ technique (OOB), in which
roughly one third of the knowledge is retained as a test data collection to determine the
classification accuracy. The RF classification can be cross-validated using separate data
sets. The GEE ran specific forest classifiers using five inputs: (1) classification tree numbers,
(2) leaf maxes, (3) decision tree input percentage, (4) out-of-bag mode of the random seed
variable, and (5) the decision tree development random seed variable. The random forest
classification variable in GEE requires six input parameters. With growing numbers of
plants, the average classification accuracy improves non-excessively [93].
The Naive Bayes Method is a Bayesian classification methodology that predicts a class
mark for a data instance by the distribution of attribute values, and is a statistical and linear
ISPRS Int. J. Geo-Inf. 2023, 12, 81 12 of 24

classification method. It is a parametric classification in which the assignment element

remains consistent. The distribution of the nucleus, multivariate or multi-nominal, can be
the usual (Gaussian). Bayesian classifiers use the theorem of Bayes to determine subsequent
probabilities for all class input results. The data instance [94] is allocated to class labels
with optimum conditional probability. These distribution assumptions would influence the
creation of the NBC model and model parameters. If an attribute defined to an entity is
identified by F = {f1 , . . . , fd }, and the distribution of each attribute (function) is natural,
then the probability (process), recognized as a class jth (Cj), is as the following equation:

d d
P(F|Cj ) = ∏ P(Fk |Cj ) = ∏ N(fk ; µ̂jk ; σ̂jk ) (1)
k =1 k =1

where µ̂jk and σ̂jk are estimated results of µ and σ for the kth feature and jth class. Then, by
using the conditional probability rule, the following equation is obtained.

d
P(Cj |F) = P(Cj )P(F|Cj ) = P(Cj ) ∏ N(fk ; µ̂jk ; σ̂jk ) (2)
k =1

The description outcomes of the artifacts may be calculated based on their attributes
(functions) with the maximum probability value of P (Cj |F)

d
ĉ = argcj maxP(Cj ) ∏ N(fk ; µ̂jk ; σ̂jk ) (3)
k =1

where Cj is the description of the outcome/output.

The CART is a supervised computer analysis algorithm that constitutes a binary
decision tree, similar to the Decision Tree algorithm. It necessitates defining and developing
the tree using samples for which the optimal classification cannot be determined. The
Decision Tree concludes with a root node for each element in the function space, minimizing
the uncleanness of all nodes. The decision tree then progresses through incremental splits,
so impurity does not decrease dramatically as more separation is introduced [95]. Therefore,
the decision tree expands. The tree of judgment consists of multi-level and multi-leaf nodes,
and after it has been built, the judgment tree is broken. The designed trees are sometimes
unnecessarily suited because there is always a disproportionate number of knots and
branches. The tree may be sliced by manipulating the younger branches’ parameters
or thresholds.
The following procedures were used to train machine-learning algorithms to construct
an iterative sample selection process to achieve an appropriate sample size, as shown in
Figure 5. The step-by-step approach is listed below:
• Produce a computer description of current examples in instruction.
• Classify MFDC from 10 m to 60 m based on the existing classification with the GEE
cloud on Support Vector Machine, Random Forest, and Naïve Bayes algorithms, as
shown in Figure 2.
• Visually examine the categorization tests using current reference maps and sub-meter
to 10-m VHRI.
• Connect field samples to designated zones with comparison submeter to 10 m VHRI
from Google Earth Imagery.
• Repeat measures 1–4 of the expanded training data collection to optimize classification
and obtain high precision.
ISPRS Int. J. Geo-Inf. 2023, 12, 81 13 of 24

Figure 5. Land Classifications map of Pakistan.

The number of iterations available for the sample collection of the testing depends
on the area’s difficulty. To conduct the classification shown in Figure 3, Pakistan has
been divided into many agro-ecological regions (see Figure 1), with the iterative sorting
frequently replicated ∼2–3 fold, enhancing the initial categorized performance. We began
with a limited number of samples (250 to begin with) and then gradually increased the
measurement size to a high degree of precision. Following each repetition, we visually
contrasted the classification outcome at 100 s of locations with submeters of VHRI of 10 m.
When the assessment outcomes were insufficient, we passed the tests sufficiently. Using the
independent validation results, the accuracy evaluation team conducted accuracy analysis,
as shown in Table 3.

5.2. Google Earth Platforms Cloud Computing

For the pixel description of croplands, we have used Google Earth Engine (GEE) cloud
computing for machine learning algorithms. GEE’s accessible Sentinel-2 MSI archives are
already optimized for atmospheric and topographical impacts, saving us much time in
accessing the information. Throughout the GEE application editor, we used the JavaScript
API. Google Fusion tables were utilized to import all testing samples and zonal boundaries
into GEE (Appendix A).
ISPRS Int. J. Geo-Inf. 2023, 12, 81 14 of 24

Remote Sensing Analysis Accuracy on the GEE Platform

GEE generally performed exceptionally in simplifying access to remote sensing prod-
ucts through the cloud platform and executing sophisticated processes for satellite data
processing. Numerous processed-ready satellite scenes or composites are immediately
available to the user. Even though our research did not focus on massive volumes of data,
we demonstrated that the GEE cloud platform might be used to construct massive-scale
applications that access and analyze satellite data. Because of what GEE can do, the meth-
ods discussed in the paper can be used globally. The study also looked at the validity or
accuracy of crop mapping with GEE using existing commodities and processing chains.
However, we think that there are a few things that need to be changed before GEE can
be used to map crops on a large scale, especially in an operational context:
• It would help if it was possible to find solutions to the problem of data loss caused by
weather conditions (such as clouds and shadows) that were easily accessible.
• Improve existing classifiers, especially the SVM, by incorporating neural network
classifiers (through a library such as TensorFlow’s deep learning capabilities).

6. Results and Discussion

This portion consists of three distinct components, beginning with a demonstration of
the ML-based mapping technique for Pakistan using up to 60 m of Sentinel-2 MSI, followed
by an evaluation of farmland distribution precision, errors, and uncertainties. Finally,
croplands are described and addressed at a regional level.
Having accurate, detailed, and high-resolution farmland maps at the national scale
is crucial for ensuring long-term agricultural productivity and food security [96]. This
research looked at the feasibility of using a machine-learning-based method to precisely
map and label GEE’s agricultural districts. Other authors have indicated that the GEE cloud
platform provides a legitimate tool and processing environment for generating a precise
and accurate cropland extent product in a matter of minutes [97] thanks to its computing
capacity and well-integrated large-scale analytic approaches.
As a result of its unusual revisit frequency of 5 days (for twin satellites S2A and S2B)
and 10m per pixel spatial resolution, Sentinel-2 was chosen as the significant resource
satellite to identify and map agricultural distribution at the field size. Since fields and farms
in Pakistan and similar locations are, on average, 0.9 hectares in size and only data with
such high spatial resolution can give sufficient information for efficient and detailed crop
monitoring and classification, Sentinel-2 is better suited to the diversity of agroecosystems,
terrain patterns, and agricultural methods present there.
Our approach is premised on extracting phenological variables (metrics) for farmland-
type mapping, since these characteristics have previously shown their usefulness in moni-
toring and identifying unique vegetation cover at different spatial scales [98].
Moreover, the findings confirmed the efficacy of the machine learning techniques used
in GEE to create granular estimates of agricultural expansion over large regions. Classifiers
from the field of machine learning (Support Vector Machine, CART, Naive Bayes, and
Random Forest) were chosen because they produce probabilities for each label, are com-
putationally efficient when dealing with large amounts of data, have outperformed other
state-of-the-art methods, and have few parameters that need tuning [54]. Since complex
classification will involve more uncertainty when numerous classes concurrently occupy
the same pixel [99], this final benefit gives a soft category (probability estimate), which is
especially relevant in Pakistan’s fragmented and diversified landscapes. The probability
maps we generate are well correlated with the corresponding high-resolution images. Each
pixel was classified as cropland or non-cropland based on the probability maps, and the
threshold used was 60%. These findings represent a significant improvement above the
state-of-the-art, as seen in Figure 5. The standard picture stacking approach, which may
miss critical phenological events and make it impossible to identify the farmland or crop
type, has been replaced by our suggested framework, which incorporates phenological
data to map cropland and how it varies. Furthermore, current products prioritize LULC
ISPRS Int. J. Geo-Inf. 2023, 12, 81 15 of 24

even when the primary objective is not to create a comprehensive map of agricultural areas.
Moreover, they are exclusively accessible for specific years and are seldom updated [100].
Some additional difficulties arise when using GEE to locate reference samples in areas
with insufficient ground data. When operating in Asia, obtaining a representative sample
at the Sentinel scale and choosing a uniform pixel is challenging. The only way to solve this
issue is to improve the quality of the input samples, include more data layers whenever
feasible, and do away with the outliner altogether. Using Google Earth Engine to locate
reference samples raises eyebrows, since the resulting interpretations are not as reliable as
data gathered in the field. Previous studies, however, corroborate the usefulness of rapid
and easy methods of mapping land cover. Crowdsourced Google Earth data regarding
the geographical distribution of farmland in Pakistan was found to be more accurate
than global land cover datasets. People tend to understate the extent to which humans
affect things when analyzing crowdsourced data, and there was little difference between
specialists and non-experts in terms of identifying human impact.

6.1. 10 m to 60 m Cropland Extent Product for Pakistan

In the nominal years 2018–2019, the trial generated 10 m to 60 m of croplands extracted
from Sentinel-2 MSI 5-day time series data for Pakistan. The machine learning algorithms
listed in Section 4 were used to distinguish croplands from non-croplands in the GEE cloud
computing setting. The method was iterated, and the samples were modified and input
to the algorithms several times before optimum cultivable cropland outcomes relative to
non-cropland were obtained (see Figure 5).

6.2. Accuracy Assessment

The cropland map for Pakistan was evaluated for accuracy with an error matrix that
did not apply to the manufacturer of this dataset [101]. The accuracy error matrix has been
developed for the entire world. The precision of the ultimate cropland map of Pakistan
was calculated using a minimum of 200 stratified, randomly spaced testing samples. An
error matrix, as shown in Table 4 for complete accuracy (Pakistan as a whole), Naïve Bayes,
Ride, Random Tree, and SVM algorithms was developed, and its accuracy on a 10 m
to 60 m Sentinel-2 MSI dataset and validation data collection is provided below. In the
validation dataset, the average precision of the CART algorithm was 82%, with an accuracy
of 89% for the producer and 73.0% for the customer for the cropland class. The validation
data collection had a complete accuracy of 75% for the Random Forest method, a vendor
accuracy of 77% for the cropland class, and an implementation accuracy of 71.0%. The
validation data collection was 76% for the Naïve Bays method, 81% for the manufacture,
and 54.0% for the cropland class for consumer accuracy. Similarly, SVM’s total validity
data accuracy was 74%, the producer’s accuracy was 76%, and cropland accuracy was
68%. Table 4 demonstrates the performance of the algorithm CART with the best average
validity performance relative to the other three algorithms. Classification accuracy defines
the performance of the machine learning algorithm on the provided training data, while
validation accuracy defines the implementation of the machine learning algorithm on
detailed testing data supplied to the algorithm externally.
Classification accuracies can be further increased, particularly the accuracies of the
consumer and supplier (see Table 4), by separating the regions (see Figure 1). Google
Earth Engine (GEE) is a powerful tool for capturing, storing and classifying photographs
via a cloud storage network. While GEE allows the handling of extensive data and easy
calculations, it is restricted to how GEE handles comprehensive data using MLAs. There
are still several obstacles to overcome, such as the lack of data on comparative training from
agricultural fields of greater variety. By illustration, for a specific classifier, the study of the
entire broad data population contributes to inconsistencies in the classification performance
and a decrease in accuracy instead of classifying data for each pixel. Many directions
to boost precision and raise uncertainty are better than spatial mappings, such as the
convergence of global forest maps [102] and global water masks [103]. Since 10 m to 60 m of
ISPRS Int. J. Geo-Inf. 2023, 12, 81 16 of 24

Sentinel-2 images include thousands of pixels in such broad fields, this is not a substantial
study, but is perhaps the best one to obtain, considering the difficulty of general areas and
capital. Larger samples for training and testing are possible, particularly in numerous
croplands, including highland to lowland deltas that consider specific subspecies within
permanent cultivations, cropland falls, and permanent plants. Similar approaches have
often been implemented in many nations of the world in addition to those employed here.
In a recent report on Africa [56], for instance, 94% of the development lands had an average
weighted precision (85% or 14.1% omission error) and 68.5% (31.5% commission error),
with a producers’ accuracy of 85%, and an Africa overall consumer accuracy of 31.5%
(commission error).

Table 4. The computer analysis performance error matrix algorithms. The 10 m to 60 m cropland
expanded commodity for Pakistan’s precision error matrix.

CART Algorithm Accuracy on Training and Validation Datasets

Cropland Non-Cropland Total User Accuracy
Cropland 73 27 100 73%
Classification Accuracy: 93%
Non-Cropland 9 91 100 91%
Validation Accuracy: 82%
Total 82 118 200
Producer Accuracy 89% 77%
Random Forest Algorithm Accuracy on Training and Validation Datasets
Cropland Non-Cropland Total User Accuracy
Cropland 71 29 100 71%
Classification Accuracy: 91%
Non-Cropland 21 79 100 79%
Validation Accuracy: 75%
Total 92 108 200
Producer Accuracy 77% 73%
Naïve Bayes Algorithm Accuracy on Training and Validation Datasets
Cropland Non-Cropland Total User Accuracy
Cropland 54 46 100 54%
Classification Accuracy: 83%
Non-Cropland 13 87 100 87%
Validation Accuracy: 76%
Total 67 133 200
Producer Accuracy 81% 65%
Support Vector Machine Algorithm Accuracy on Training and Validation Datasets
Cropland Non-Cropland Total User Accuracy
Cropland 68 32 100 68%
Classification Accuracy: 83%
Non-Cropland 21 79 100 79%
Validation Accuracy: 74%
Total 89 111 200
Producer Accuracy 76% 71%

6.3. The Analogy to Other Datasets and Agricultural Regions

Aside from creating a map, it is an essential component of the 10 m to 60 m region
of cropland commodity to quantify the cropland region statistics. Pakistan features two
distinct types of croplands (croplands and pastures under management). For 2018–2019,
Pakistan’s gross cropland region was estimated to have been 370,200 square kilometers.
Table 5 presents statistics for the cropland area produced for Pakistan in this study com-
pared to other sources like the Pakistan Statistical Bureau. However, the area created by
this analysis of the cultivated land in Pakistan between 10 m and 60 m is high. Every pixel
up to 60 m is approximately 0.099 ha. It is, therefore, necessary, also at the farm stage, vast
or small-scale, to catch regions at the sub-national level. It is a significant advantage in
contrast to other current cropland goods.
ISPRS Int. J. Geo-Inf. 2023, 12, 81 17 of 24

Table 5. Net cropland areas derived based on the 10 m to 60 m Sentinel-2 MSI.

Agriculture Land Govt. of Pakistan Net Cropland Agriculture Land

% of the Total
in Sq. Km (Agriculture Census Area in Sq. Km. (Pakistan Bureau
Country. Agriculture
(The World Organization-2010) in (Estimated in the of Statistics) in
Land Areas
Bank Data) Sq. Km. Current Study) Sq. Km.
Pakistan 368,440 274,814 370,200 303,400 47.79%

6.4. Input Parameters for Cropland Extent Mapping

After examining the literature and conducting tests, we decided to use nine bands
for this analysis: green, red, blue, SWIR1, SWIR2, and near-infrared, as well as the vege-
tation indices EVI, NDVI, and LSWI (see Table 6). NDVI was used to detect dense plant
groupings, such as forests. The Enhanced Vegetation Index (EVI) is a modified version
of the Normalized Difference Vegetation Index (NDVI) that was created to detect plants
that were too faintly luminous to be seen with the naked eye. The cultivable land was
determined using the Normalized Difference Water Index (NDWI). The USGS formerly
performed Top of Atmosphere (TOA) processing before the images were used: when this
study was undertaken for Sentinel-2 on GEE, insufficient Surface Reflectance images were
available. In addition, we have chosen to incorporate GDEM-derived elevation, which
helps machine learning classifiers differentiate between classes with similar spectral sig-
natures but different characteristics. It is especially beneficial for separating rice fields in
river deltas and other low-lying agricultural regions from higher-lying agricultural and
non-crop areas in the uplands. Combining ground data with sub-meter to 5-m data and
supplementary data based on their relative elevation permits the identification of several
spectrally-related groups.

Table 6. Characteristics of Sentinel 2 MSI data used in this study.

Band Name Sentinel 2-MSI Wavelength (nm) Vegetation Index (VI) Equation
Blue 496.6 nm (S2A)/492.1 nm (S2B) EVI = 2.5 (NIR-red)/(NIR +
EVI
Green 560 nm (S2A)/559 nm (S2B) 6*red–7.5*blue + 1)
Red 664.5 nm (S2A)/665 nm (S2B)
NIR 835.1 nm (S2A)/833 nm (S2B) NDWI NDWI = (NIR-SWIR1)/(NIR + SWIR1)
SWIR1 1613.7 nm (S2A)/1610.4 nm (S2B)
SWIR2 2202.4 nm (S2A)/2185.7 nm (S2B) NDVI NDVI = (NIR-red)/(NIR + red)

7. Conclusions
Using Sentinel-2 data for the notional years 2018–2014, this research created the first
map of Pakistan’s farmland expanse at a resolution of 60 m. This research used the Google
Earth Engine to showcase the efficacy of pixel-based CART, Random Forest, Naive Bayes,
and Support Vector machine learning algorithms for agricultural farmland mapping across
extensive regions, with a resolution of 60 m. (GEE). The CART algorithm has the best
validation accuracy (82%) among the various machine learning techniques. Table 4 displays
the detailed accuracy evaluation analysis and confusion matrix for Pakistan’s 60 m Landsat-
derived agricultural extent product for 2018–2019. The research team used “48 input bands
derived from seasonal composites of remotely sensed observations, topographic variables,
857 reference training samples, and 200 reference validation samples spread across 14 Agro-
Ecological zones to develop a novel approach to creating cropland versus non-cropland
maps”. According to the agricultural map, the study area has 370,200 square kilometers of
cropland, or 47.79% of Pakistan’s total agricultural land.
Considering the “computer capacity and ever-expanding archive of satellite observa-
tion accessible in GEE, the classification technique used in this work may be duplicated
ISPRS Int. J. Geo-Inf. 2023, 12, 81 18 of 24

to map net croplands for additional years in the same study regions, as well as in any
other location and period given the inputs”. Research into environmental monitoring,
climate change, land cover change, land use, food security, water, agriculture, and policy
development all stand to benefit significantly from the findings given here.

8. Future Work
Large-scale optical and SAR crop mapping considers the worldwide coverage of the
Landsat-8, Proba-V, Sentinel-1, and Sentinel-2 satellites. We want to implement a parcel-
based classification approach based on the GEE-linked pixel method, in addition toother
methods, to improve the pixel-based crop classification map.

Author Contributions: Conceptualization, Jinliao He and Muhammad Umer; Methodology, Rana

Muhammad Amir Latif; Software, Rana Muhammad Amir Latif and Muhammad Umer; Validation,
Jinliao He; Formal analysis, Rana Muhammad Amir Latif; Investigation, Rana Muhammad Amir Latif
and Muhammad Umer; Resources, Jinliao He; Data curation, Muhammad Umer; Writing—original
draft, Rana Muhammad Amir Latif; Writing—review & editing, Jinliao He; Funding acquisition,
Jinliao He. All authors have read and agreed to the published version of the manuscript.
Funding: This study was founded by National Natural Science Foundation of China, grant number
42130510 and 42171214.
Data Availability Statement: Data is contained within the article.
Conflicts of Interest: The authors declare that they have no conflict of interest.

Appendix A
// Get a collection.
var sen_collection = ee.ImageCollection(‘COPERNICUS/S2’);
// Filter to scenes that intersect your boundary
var sen_StudyArea = sen_collection.filterBounds(roi);
// Filter to scenes for a given time period
var sen_filter = sen_StudyArea.filterDate(‘2018-09-28’, ‘2018-12-28’);
//reduce to median value per pixel
var median_sen = sen_filter.median();
// Filter to scenes that intersect your boundary
var sen_StudyArea2 = sen_collection.filterBounds(roi2);
// Filter to scenes for a given time period
var sen_filter2 = sen_StudyArea2.filterDate(‘2018-09-28’, ‘2018-12-28’);
//reduce to median value per pixel
var median_sen2 = sen_filter2.median();
// Filter to scenes that intersect your boundary
var sen_StudyArea3 = sen_collection.filterBounds(roi3);
// Filter to scenes for a given time period
var sen_filter3 = sen_StudyArea3.filterDate(‘2018-09-28’, ‘2018-12-28’);
//reduce to median value per pixel
var median_sen3 = sen_filter3.median();
// Filter to scenes that intersect your boundary
var sen_StudyArea4 = sen_collection.filterBounds(roi4);
// Filter to scenes for a given time period
var sen_filter4 = sen_StudyArea4.filterDate(‘2018-09-28’, ‘2018-12-28’);
//reduce to median value per pixel
var median_sen4 = sen_filter4.median();
// Filter to scenes that intersect your boundary
var sen_StudyArea5 = sen_collection.filterBounds(roi5);
// Filter to scenes for a given time period
var sen_filter5 = sen_StudyArea5.filterDate(‘2018-09-28’, ‘2018-12-28’);
ISPRS Int. J. Geo-Inf. 2023, 12, 81 19 of 24

//reduce to median value per pixel

var median_sen5 = sen_filter5.median();
// Filter to scenes that intersect your boundary
var sen_StudyArea6 = sen_collection.filterBounds(roi6);
// Filter to scenes for a given time period
var sen_filter6 = sen_StudyArea6.filterDate(‘2018-09-28’, ‘2018-12-28’);
//reduce to median value per pixel
var median_sen6 = sen_filter6.median();
// Filter to scenes that intersect your boundary
var sen_StudyArea7 = sen_collection.filterBounds(roi7);
// Filter to scenes for a given time period
var sen_filter7 = sen_StudyArea7.filterDate(‘2018-09-28’, ‘2018-12-28’);
//reduce to median value per pixel
var median_sen7 = sen_filter7.median();
var classNames = cropland.merge(noncropland);
print(classNames);
var bands = [‘B1’, ‘B2’, ‘B3’, ‘B4’, ‘B8’, ‘B10’, ‘B11’, ‘B12’];
var training = median_sen.select(bands).sampleRegions({
collection: classNames,
properties: [‘agri_land’],
scale: 30
});
print(training);
var training2 = median_sen2.select(bands).sampleRegions({
collectionmainmain: classNames,
properties: [‘agri_land’],
scale: 30
});
var training3 = median_sen3.select(bands).sampleRegions({
collection: classNames,
properties: [‘agri_land’],
scale: 30
});
var training4 = median_sen4.select(bands).sampleRegions({
collection: classNames,
properties: [‘agri_land’],
scale: 30
});
var training5 = median_sen5.select(bands).sampleRegions({
collection: classNames,
properties: [‘agri_land’],
scale: 30
});
var training6 = median_sen6.select(bands).sampleRegions({
collection: classNames,
properties: [‘agri_land’],
scale: 30
});
var training7 = median_sen7.select(bands).sampleRegions({
collection: classNames,
properties: [‘agri_land’],
scale: 30
});
ISPRS Int. J. Geo-Inf. 2023, 12, 81 20 of 24

var training8 = training7.merge(training6).merge(training5).merge(training4).

merge(training3).merge(training2).merge(training);
var classifier = ee.Classifier.cart().train({
features: training8,
classProperty: ‘agri_land’,
inputProperties: bands
});
Export.table.toAsset({
collection: training8,
description: ‘foo’,
assetId: ‘foo’
});
var classified = median_sen3.select(bands).classify(classifier);
//Display classification
Map.centerObject(classNames, 11);
Map.addLayer(classified,
min: 0, max: 3, palette: [‘red’, ‘blue’, ‘green’,’yellow’],
‘classification’);

References
1. Estévez, J.; Salinero-Delgado, M.; Berger, K.; Pipia, L.; Rivera-Caicedo, J.P.; Wocher, M.; Reyes-Muñoz, P.; Tagliabue, G.; Boschetti,
M.; Verrelst, J. Gaussian processes retrieval of crop traits in Google Earth Engine based on Sentinel-2 top-of-atmosphere data.
Remote Sens. Environ. 2022, 273, 112958. [CrossRef]
2. Suni, T.; Guenther, A.; Hansson, H.C.; Kulmala, M.; Andreae, M.O.; Arneth, A.; Artaxo, P.; Blyth, E.; Brus, M.; Ganzeveld, L.; et al.
The significance of land-atmosphere interactions in the Earth system—iLEAPS achievements and perspectives. Anthropocene 2015,
12, 69–84. [CrossRef]
3. Lutter, S.; Pfister, S.; Giljum, S.; Wieland, H.; Mutel, C. Spatially explicit assessment of water embodied in European trade:
A product-level multi-regional input-output analysis. Glob. Environ. Chang. 2016, 38, 171–182. [CrossRef]
4. van Zanten, H.H.; Mollenhorst, H.; Klootwijk, C.W.; van Middelaar, C.E.; de Boer, I.J. Global food supply: Land use efficiency of
livestock systems. Int. J. Life Cycle Assess. 2016, 21, 747–758. [CrossRef]
5. Pfister, S.; Vionnet, S.; Levova, T.; Humbert, S. Ecoinvent 3: Assessing water use in LCA and facilitating water footprinting. Int.
J. Life Cycle Assess. 2016, 21, 1349–1360. [CrossRef]
6. Davis, K.F.; Rulli, M.C.; Seveso, A.; D’Odorico, P. Increased food production and reduced water use through optimized crop
distribution. Nat. Geosci. 2017, 10, 919–924. [CrossRef]
7. Waldner, F.; Canto, G.S.; Defourny, P. Automated annual cropland mapping using knowledge-based temporal features. ISPRS
J. Photogramm. Remote Sens. 2015, 110, 1–13. [CrossRef]
8. Gumma, M.K.; Thenkabail, P.S.; Maunahan, A.; Islam, S.; Nelson, A. Mapping seasonal rice cropland extent and area in the high
cropping intensity environment of Bangladesh using MODIS 500 m data for the year 2010. ISPRS J. Photogramm. Remote Sens.
2014, 91, 98–113. [CrossRef]
9. Estel, S.; Kuemmerle, T.; Alcántara, C.; Levers, C.; Prishchepov, A.; Hostert, P. Mapping farmland abandonment and recultivation
across Europe using MODIS NDVI time series. Remote Sens. Environ. 2015, 163, 312–325. [CrossRef]
10. Shao, Y.; Lunetta, R.S.; Ediriwickrema, J.; Iiames, J. Mapping cropland and major crop types across the Great Lakes Basin using
MODIS-NDVI data. Photogramm. Eng. Remote Sens. 2010, 76, 73–84. [CrossRef]
11. Shao, Y.; Lunetta, R.S. Sub-pixel mapping of tree canopy, impervious surfaces, and cropland in the Laurentian Great Lakes Basin
using MODIS time-series data. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2010, 4, 336–347. [CrossRef]
12. He, Y.; Lee, E.; Warner, T.A. A time series of annual land use and land cover maps of China from 1982 to 2013 generated using
AVHRR GIMMS NDVI3g data. Remote Sens. Environ. 2017, 199, 201–217. [CrossRef]
13. Pittman, K.; Hansen, M.C.; Becker-Reshef, I.; Potapov, P.V.; Justice, C.O. Estimating global cropland extent with multi-year MODIS
data. Remote Sens. 2010, 2, 1844–1863. [CrossRef]
14. Thenkabail, P. Global Food Security Support Analysis Data at Nominal 1 km (GFSAD1km) Derived from Remote Sensing
in Support of Food Security in the Twenty-First Century: Current Achievements and Future Possibilities. In Land Resources
Monitoring, Modeling, and Mapping with Remote Sensing; CRC Press: Boca Raton, FL, USA, 2018; pp. 865–894.
15. Liang, D.; Zuo, Y.; Huang, L.; Zhao, J.; Teng, L.; Yang, F. Evaluation of the consistency of MODIS Land Cover Product (MCD12Q1)
based on Chinese 30 m GlobeLand30 datasets: A case study in Anhui Province, China. ISPRS Int. J. Geo-Inf. 2015, 4, 2519–2541.
[CrossRef]
16. Ran, Y.; Li, X. First comprehensive fine-resolution global land cover map in the world from China—Comments on global land
cover map at 30-m resolution. Sci. China Earth Sci. 2015, 58, 1677. [CrossRef]
ISPRS Int. J. Geo-Inf. 2023, 12, 81 21 of 24

17. Arsanjani, J.J.; Tayyebi, A.; Vaz, E. GlobeLand30 as an alternative fine-scale global land cover map: Challenges, possibilities, and
implications for developing countries. Habitat Int. 2016, 55, 25–31. [CrossRef]
18. Yang, Y.; Xiao, P.; Feng, X.; Li, H. Accuracy assessment of seven global land cover datasets over China. ISPRS J. Photogramm.
Remote Sens. 2017, 125, 156–173. [CrossRef]
19. Chen, Z.; Zhao, S. Automatic monitoring of surface water dynamics using Sentinel-1 and Sentinel-2 data with Google Earth
Engine. Int. J. Appl. Earth Obs. Geoinf. 2022, 113, 103010. [CrossRef]
20. Belgiu, M.; Csillik, O. Sentinel-2 cropland mapping using pixel-based and object-based time-weighted dynamic time warping
analysis. Remote Sens. Environ. 2018, 204, 509–523. [CrossRef]
21. Gumma, M.K.; Thenkabail, P.S.; Deevi, K.C.; Mohammed, I.A.; Teluguntla, P.; Oliphant, A.; Xiong, J.; Aye, T.; Whitbread, A.M.
Mapping cropland fallow areas in myanmar to scale up sustainable intensification of pulse crops in the farming system. GIScience
Remote Sens. 2018, 55, 926–949. [CrossRef]
22. Vogels, M.F.; de Jong, S.M.; Sterk, G.; Addink, E.A. Agricultural cropland mapping using black-and-white aerial photography,
object-based image analysis and random forests. Int. J. Appl. Earth Obs. Geoinf. 2017, 54, 114–123. [CrossRef]
23. Löw, F.; Prishchepov, A.V.; Waldner, F.; Dubovyk, O.; Akramkhanov, A.; Biradar, C.; Lamers, J.P. Mapping cropland abandonment
in the Aral Sea Basin with MODIS time series. Remote Sens. 2018, 10, 159. [CrossRef]
24. Liu, J.; Zhu, W.; Cui, X. A shape-matching cropping index (CI) mapping method to determine agricultural cropland intensities in
China using MODIS time-series data. Photogramm. Eng. Remote Sens. 2012, 78, 829–837. [CrossRef]
25. Biradar, C.M.; Thenkabail, P.; Turral, H.; Noojipady, P.; Jie, L.Y.; Velpuri, M.; Dheeravath, V.; Venkateswarlu, V.; Vithanage, J.;
Jagath, L.; et al. A global map of rainfed cropland areas (GMRCA) at the end of last millennium using remote sensing. Int. J. Appl.
Earth Obs. Geoinf. 2009, 11, 114–129. [CrossRef]
26. Nellis, M.D.; Price, K.P.; Rundquist, D. Remote sensing of cropland agriculture. In The SAGE Handbook of Remote Sensing; SAGE
Publications, Inc.: New York, NY, USA, 2009; Volume 1, pp. 368–380.
27. Sweeney, S.; Ruseva, T.; Estes, L.; Evans, T. Mapping cropland in smallholder-dominated savannas: Integrating remote sensing
techniques and probabilistic modeling. Remote Sens. 2015, 7, 15295–15317. [CrossRef]
28. Oliphant, A.J.; Thenkabail, P.S.; Teluguntla, P.; Xiong, J.; Gumma, M.K.; Congalton, R.G.; Yadav, K. Mapping cropland extent of
Southeast and Northeast Asia using multi-year time-series Landsat 30-m data using a random forest classifier on the Google
Earth Engine Cloud. Int. J. Appl. Earth Obs. Geoinf. 2019, 81, 110–124. [CrossRef]
29. Alberto, R.; Serrano, S.C.; Damian, G.B.; Camaso, E.E.; Celestino, A.B.; Hernando, P.J.C.; Isip, M.F.; Orge, K.M.; Quinto, M.J.C.;
Tagaca, R.C.; et al. Object Based Agricultural Land Cover Classification Map of Shadowed Areas from Aerial Image and Lidar
Data Using Support Vector Machine. In Proceedings of the 2016 ISPRS Congress, Prague, Czech Republic, 12–19 July 2016;
Volume 3.
30. Sitthi, A.; Nagai, M.; Dailey, M.; Ninsawat, S. Exploring land use and land cover of geotagged social-sensing images using naive
bayes classifier. Sustainability 2016, 8, 921. [CrossRef]
31. Xiong, J.; Thenkabail, P.S.; Gumma, M.K.; Teluguntla, P.; Poehnelt, J.; Congalton, R.G.; Yadav, K.; Thau, D. Automated cropland
mapping of continental Africa using Google Earth Engine cloud computing. ISPRS J. Photogramm. Remote Sens. 2017, 126, 225–244.
[CrossRef]
32. Friesz, A.M.; Wylie, B.K.; Howard, D.M. Temporal expansion of annual crop classification layers for the CONUS using the C5
decision tree classifier. Remote Sens. Lett. 2017, 8, 389–398. [CrossRef]
33. Teluguntla, P.; Thenkabail, P.S.; Xiong, J.; Gumma, M.K.; Congalton, R.G.; Oliphant, A.; Poehnelt, J.; Yadav, K.; Rao, M.; Massey,
R. Spectral matching techniques (SMTs) and automated cropland classification algorithms (ACCAs) for mapping croplands of
Australia using MODIS 250-m time-series (2000–2015) data. Int. J. Digit. Earth 2017, 10, 944–977. [CrossRef]
34. Teluguntla, P.; Thenkabail, P.S.; Xiong, J.; Gumma, M.K.; Congalton, R.G.; Oliphant, J.A.; Sankey, T.; Poehnelt, J.; Yadav, K.; Massey,
R.; et al. NASA Making Earth System Data Records for Use in Research Environments (MEaSUREs) Global Food Security-support
Analysis Data (GFSAD) Cropland Extent 2015 Australia, New Zealand, China, Mongolia 30 m V001. 2017. Available online:
http://oar.icrisat.org/10980/ (accessed on 5 December 2022).
35. Zhong, L.; Hu, L.; Yu, L.; Gong, P.; Biging, G.S. Automated mapping of soybean and corn using phenology. ISPRS J. Photogramm.
Remote Sens. 2016, 119, 151–164. [CrossRef]
36. Bellón, B.; Bégué, A.; Lo Seen, D.; De Almeida, C.A.; Simões, M. A remote sensing approach for regional-scale mapping of
agricultural land-use systems based on NDVI time series. Remote Sens. 2017, 9, 600. [CrossRef]
37. Xie, Y.; Lark, T.J.; Brown, J.F.; Gibbs, H.K. Mapping irrigated cropland extent across the conterminous United States at 30 m
resolution using a semi-automatic training approach on Google Earth Engine. ISPRS J. Photogramm. Remote Sening. 2019, 155,
136–149. [CrossRef]
38. Useya, J.; Chen, S.; Murefu, M. Cropland Mapping and Change Detection: Toward Zimbabwean Cropland Inventory. IEEE Access
2019, 7, 53603–53620. [CrossRef]
39. Del Valle, T.M. Comparison of common classification strategies for large-scale vegetation mapping over the Google Earth Engine
platform. Int. J. Appl. Earth Obs. Geoinf. 2022, 115, 103092. [CrossRef]
40. Quang, N.H.; Nguyen, M.N.; Paget, M.; Anstee, J.; Viet, N.D.; Nones, M.; Tuan, V.A. Assessment of Human-Induced Effects on
Sea/Brackish Water Chlorophyll-a Concentration in Ha Long Bay of Vietnam with Google Earth Engine. Remote Sens. 2022, 14, 4822.
[CrossRef]
ISPRS Int. J. Geo-Inf. 2023, 12, 81 22 of 24

41. Onačillová, K.; Gallay, M.; Paluba, D.; Péliová, A.; Tokarčík, O.; Laubertová, D. Combining Landsat 8 and Sentinel-2 Data in Google Earth
Engine to Derive Higher Resolution Land Surface Temperature Maps in Urban Environment. Remote Sens. 2022, 14, 4076. [CrossRef]
42. Erickson, T. Multi-Source Geospatial Data Analysis with Google Earth Engine; American Geophysical Union (AGU): Fall Meeting
Abstracts, Washington, DC, USA, 2014.
43. Gorelick, N.; Hancher, M.; Dixon, M.; Ilyushchenko, S.; Thau, D.; Moore, R. Google Earth Engine: Planetary-scale geospatial
analysis for everyone. Remote Sens. Environ. 2017, 202, 18–27. [CrossRef]
44. Praticò, S.; Solano, F.; Di Fazio, S.; Modica, G. Machine learning classification of mediterranean forest habitats in google earth
engine based on seasonal sentinel-2 time-series and input image composition optimisation. Remote Sens. 2021, 13, 586. [CrossRef]
45. Seydi, S.T.; Akhoondzadeh, M.; Amani, M.; Mahdavi, S. Wildfire damage assessment over Australia using sentinel-2 imagery and
MODIS land cover product within the google earth engine cloud platform. Remote Sens. 2021, 13, 220. [CrossRef]
46. Sun, Y.; Qin, Q.; Ren, H.; Zhang, Y. Decameter Cropland LAI/FPAR Estimation from Sentinel-2 Imagery Using Google Earth
Engine. IEEE Trans. Geosci. Remote Sens. 2021, 60, 1–14. [CrossRef]
47. Ahmad, D.; Chani, M.I.; Humayon, A.A. Major crops forecasting area, production and yield evidence from agriculture sector of
Pakistan. Sarhad J. Agric. 2017, 33, 385–396. [CrossRef]
48. Yan, L.; Roy, D.P.; Li, Z.; Zhang, H.K.; Huang, H. Sentinel-2A multi-temporal misregistration characterization and an orbit-based
sub-pixel registration methodology. Remote Sens. Environ. 2018, 215, 495–506. [CrossRef]
49. Li, J.; Roy, D.P. A global analysis of Sentinel-2A, Sentinel-2B and Landsat-8 data revisit intervals and implications for terrestrial
monitoring. Remote Sens. 2017, 9, 902. [CrossRef]
50. FAO. Pakistan: Review of the Wheat Sector and Grain Storage; Food and Agriculture Organization: Rome, Italy, 2013.
51. Pakistan Bureau of Statistics. Agricultural Census 2010—Pakistan Report; Pakistan Bureau of Statistics: Islamabad, Pakistan, 2010.
52. Basso, B.; Cammarano, D.; Carfagna, E. Review of crop yield forecasting methods and early warning systems. In Proceedings of
the First Meeting of the Scientific Advisory Committee of the Global Strategy to Improve Agricultural and Rural Statistics, Rome,
Italy, 18 July 2013.
53. Boryan, C.; Yang, Z.; Mueller, R.; Craig, M. Monitoring US agriculture: The US department of agriculture, national agricultural
statistics service, cropland data layer program. Geocarto Int. 2011, 26, 341–358. [CrossRef]
54. Pelletier, C.; Webb, G.I.; Petitjean, F.J.R.S. Temporal convolutional neural network for the classification of satellite image time
series. Remote Sens. 2019, 11, 523. [CrossRef]
55. Pelletier, C.; Valero, S.; Inglada, J.; Champion, N.; Dedieu, G. Assessing the robustness of Random Forests to map land cover with
high resolution satellite image time series over large areas. Remote Sens. Environ. 2016, 187, 156–168. [CrossRef]
56. Xiong, J.; Thenkabail, P.S.; Tilton, J.C.; Gumma, M.K.; Teluguntla, P.; Oliphant, A.; Congalton, R.G.; Yadav, K.; Gorelick, N.
Nominal 30-m cropland extent map of continental Africa by integrating pixel-based and object-based algorithms using Sentinel-2
and Landsat-8 data on Google Earth Engine. Remote Sens. 2017, 9, 1065. [CrossRef]
57. Csillik, O.; Belgiu, M. Cropland mapping from Sentinel-2 time series data using object-based image analysis. In Proceedings of
the 20th AGILE International Conference on Geographic Information Science Societal Geo-Innovation Celebrating, Wageningen,
The Netherlands, 9 May 2017.
58. Lebourgeois, V.; Dupuy, S.; Vintrou, É.; Ameline, M.; Butler, S.; Bégué, A. A combined random forest and OBIA classification
scheme for mapping smallholder agriculture at different nomenclature levels using multisource data (simulated Sentinel-2 time
series, VHRS and DEM). Remote Sens. 2017, 9, 259. [CrossRef]
59. Castaldi, F.; Hueni, A.; Chabrillat, S.; Ward, K.; Buttafuoco, G.; Bomans, B.; Vreys, K.; Brell, M.; van Wesemael, B. Evaluating the
capability of the Sentinel 2 data for soil organic carbon prediction in croplands. ISPRS J. Photogramm. Remote Sens. 2019, 147,
267–282. [CrossRef]
60. Lambert, M.J.; Traoré, P.C.S.; Blaes, X.; Baret, P.; Defourny, P. Estimating smallholder crops production at village level from
Sentinel-2 time series in Mali’s cotton belt. Remote Sens. Environ. 2018, 216, 647–657. [CrossRef]
61. Kolecka, N.; Ginzler, C.; Pazur, R.; Price, B.; Verburg, P.H. Regional scale mapping of grassland mowing frequency with sentinel-2
time series. Remote Sens. 2018, 10, 1221. [CrossRef]
62. Van Tricht, K.; Gobin, A.; Gilliams, S.; Piccard, I. Synergistic use of radar Sentinel-1 and optical Sentinel-2 imagery for crop
mapping: A case study for Belgium. Remote Sens. 2018, 10, 1642. [CrossRef]
63. Poortinga, A.; Tenneson, K.; Shapiro, A.; Nquyen, Q.; San Aung, K.; Chishtie, F.; Saah, D. Mapping plantations in Myanmar by
fusing landsat-8, sentinel-2 and sentinel-1 data along with systematic error quantification. Remote Sens. 2019, 11, 831. [CrossRef]
64. Kanjir, U.; Ðurić, N.; Veljanovski, T. Sentinel-2 Based Temporal Detection of Agricultural Land Use Anomalies in Support of
Common Agricultural Policy Monitoring. ISPRS Int. J. Geo-Inf. 2018, 7, 405. [CrossRef]
65. Mahdianpari, M.; Salehi, B.; Mohammadimanesh, F.; Homayouni, S.; Gill, E. The first wetland inventory map of newfoundland at
a spatial resolution of 10 m using sentinel-1 and sentinel-2 data on the google earth engine cloud computing platform. Remote
Sens. 2019, 11, 43. [CrossRef]
66. Shelestov, A.; Lavreniuk, M.; Kussul, N.; Novikov, A.; Skakun, S. Exploring Google earth engine platform for big data processing:
Classification of multi-temporal satellite imagery for crop mapping. frontiers in Earth Science. Environ. Inform. Remote Sens. 2017, 5, 17.
[CrossRef]
67. Kang, B.; Nguyen, T.Q. Random forest with learned representations for semantic segmentation. IEEE Trans. Image Process. 2019,
28, 3542–3555. [CrossRef]
ISPRS Int. J. Geo-Inf. 2023, 12, 81 23 of 24

68. Bihani, A.; Daigle, H.; Santos, J.E.; Landry, C.; Prodanović, M.; Milliken, K. MudrockNet: Semantic segmentation of mudrock
SEM images through deep learning. Comput. Geosci. 2022, 158, 104952. [CrossRef]
69. Ravì, D.; Bober, M.; Farinella, G.M.; Guarnera, M.; Battiato, S. Semantic segmentation of images exploiting DCT based features
and random forest. Pattern Recognit. 2016, 52, 260–273. [CrossRef]
70. Mountrakis, G.; Im, J.; Ogole, C. Support vector machines in remote sensing: A review. ISPRS J. Photogramm. Remote Sens. 2011,
66, 247–259. [CrossRef]
71. Shayeganpour, S.; Tangestani, M.H.; Gorsevski, P.V. Machine learning and multi-sensor data fusion for mapping lithology: A case
study of Kowli-kosh area, SW Iran. Adv. Space Res. 2021, 68, 3992–4015. [CrossRef]
72. Du, B.; Mao, D.; Wang, Z.; Qiu, Z.; Yan, H.; Feng, K.; Zhang, Z. Mapping wetland plant communities using unmanned aerial
vehicle hyperspectral imagery by comparing object/pixel-based classifications combining multiple machine-learning algorithms.
IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2021, 14, 8249–8258. [CrossRef]
73. Jiang, D.; Li, G.; Tan, C.; Huang, L.; Sun, Y.; Kong, J. Semantic segmentation for multiscale target based on object recognition
using the improved Faster-RCNN model. Future Gener. Comput. Syst. 2021, 123, 94–104. [CrossRef]
74. Liu, T.; Abd-Elrahman, A.; Morton, J.; Wilhelm, V.L. Comparing fully convolutional networks, random forest, support vector
machine, and patch-based deep convolutional neural networks for object-based wetland mapping using images from small
unmanned aircraft system. GIScience Remote Sens. 2018, 55, 243–264. [CrossRef]
75. Chen, B.; Xia, M.; Huang, J. Mfanet: A multi-level feature aggregation network for semantic segmentation of land cover. Remote
Sens. 2021, 13, 731. [CrossRef]
76. Boulila, W. A top-down approach for semantic segmentation of big remote sensing images. Earth Sci. Inform. 2019, 12, 295–306.
[CrossRef]
77. Mallick, J.; Talukdar, S.; Pal, S.; Rahman, A. A novel classifier for improving wetland mapping by integrating image fusion
techniques and ensemble machine learning classifiers. Ecol. Inform. 2021, 65, 101426. [CrossRef]
78. Balado, J.; Martínez-Sánchez, J.; Arias, P.; Novo, A. Road environment semantic segmentation with deep learning from MLS point
cloud data. Sensors 2019, 19, 3466. [CrossRef]
79. Sun, Y.; Zhang, X.; Xin, Q.; Huang, J. Developing a multi-filter convolutional neural network for semantic segmentation using
high-resolution aerial imagery and LiDAR data. ISPRS J. Photogramm. Remote Sens. 2018, 143, 3–14. [CrossRef]
80. Singh, R.; Goel, A.; Raghuvanshi, D.K. Computer-aided diagnostic network for brain tumor classification employing modulated
Gabor filter banks. Vis. Comput. 2021, 37, 2157–2171. [CrossRef]
81. Vijayan, T.; Sangeetha, M.; Kumaravel, A.; Karthik, B. WITHDRAWN: Gabor filter and machine learning based diabetic
retinopathy analysis and detection. In Microprocessors and Microsystems; Elsevier: Amsterdam, The Netherlands, 2020; in press.
82. More, S.S.; Narain, B.; Jadhav, B. Role of modified gabor filter algorithm in multimodal biometric images. In Proceedings of
the 2019 6th International Conference on Computing for Sustainable Global Development (INDIACom), New Delhi, India,
13–15 March 2019.
83. Gumma, M.K.; Thenkabail, P.S.; Teluguntla, P.G.; Oliphant, A.; Xiong, J.; Giri, C.; Pyla, V.; Dixit, S.; Whitbread, A.M. Agricultural
cropland extent and areas of South Asia derived using Landsat satellite 30-m time-series big-data using random forest machine
learning algorithms on the Google Earth Engine cloud. GIScience Remote Sens. 2020, 57, 302–322. [CrossRef]
84. Gumma, M.K.; Thenkabail, P.S.; Teluguntla, P.; Rao, M.N.; Mohammed, I.A.; Whitbread, A.M. Mapping rice-fallow cropland
areas for short-season grain legumes intensification in South Asia using MODIS 250 m time-series data. Int. J. Digit. Earth 2016, 9,
981–1003. [CrossRef]
85. Gathala, M.K.; Timsina, J.; Islam, M.S.; Krupnik, T.J.; Bose, T.R.; Islam, N.; Rahman, M.M.; Hossain, M.I.; Harun-Ar-Rashid, M.;
Ghosh, A.K.; et al. Productivity, profitability, and energetics: A multi-criteria assessment of farmers’ tillage and crop establishment
options for maize in intensively cultivated environments of South Asia. Field Crops Res. 2016, 186, 32–46. [CrossRef]
86. Maciel, D.A.; Barbosa, C.C.F.; de Moraes Novo, E.M.L.; Júnior, R.F.; Begliomini, F.N. Water clarity in Brazilian water assessed
using Sentinel-2 and machine learning methods. ISPRS J. Photogramm. Remote Sens. 2021, 182, 134–152. [CrossRef]
87. Khan, A.; Hansen, M.C.; Potapov, P.; Stehman, S.V.; Chatta, A.A. Landsat-based wheat mapping in the heterogeneous cropping
system of Punjab, Pakistan. Int. J. Remote Sens. 2016, 37, 1391–1410. [CrossRef]
88. Jayne, T.S.; Chamberlin, J.; Muyanga, M. Global Agro-Ecological Zones (GAEZ v3. 0)-Model Documentation; Technical Report; IIASA:
Laxenburg, Austria; FAO: Rome, Italy, 2012.
89. Sibanda, M.; Mutanga, O.; Rouget, M. Examining the potential of Sentinel-2 MSI spectral resolution in quantifying above ground
biomass across different fertilizer treatments. ISPRS J. Photogramm. Remote Sens. 2015, 110, 55–65. [CrossRef]
90. Sibanda, M.; Mutanga, O.; Rouget, M. Discriminating rangeland management practices using simulated hyspIRI, landsat 8 OLI,
sentinel 2 MSI, and VENµs spectral data. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2016, 9, 3957–3969. [CrossRef]
91. Varma, M.K.S.; Rao, N.K.K.; Raju, K.K.; Varma, G.P.S. Pixel-based classification using support vector machine classifier. In Proceedings
of the 2016 IEEE 6th International Conference on Advanced Computing (IACC), Bhimavaram, India, 27–28 February 2016.
92. Li, L.; Solana, C.; Canters, F.; Kervyn, M. Testing random forest classification for identifying lava flows and mapping age groups
on a single Landsat 8 image. J. Volcanol. Geotherm. Res. 2017, 345, 109–124. [CrossRef]
93. Teluguntla, P.; Thenkabail, P.S.; Oliphant, A.; Xiong, J.; Gumma, M.K.; Congalton, R.G.; Yadav, K.; Huete, A. A 30-m landsat-
derived cropland extent product of Australia and China using random forest machine learning algorithm on Google Earth Engine
cloud computing platform. ISPRS J. Photogramm. Remote Sens. 2018, 144, 325–340. [CrossRef]
ISPRS Int. J. Geo-Inf. 2023, 12, 81 24 of 24

94. Saranya, J.; Sathik, M.M.; Nisha, S.S. Agricultural Crop Classification Models In Data Mining Techniques. Int. Res. J. Eng. Technol.
(IRJET) 2019, 6, 282–285.
95. Shaharum, N.S.N.; Shafri, H.Z.M.; Ghani, W.A.W.A.K.; Samsatli, S.; Al-Habshi, M.M.A.; Yusuf, B. Oil palm mapping over Peninsular
Malaysia using Google Earth Engine and machine learning algorithms. Remote Sens. Appl. Soc. Environ. 2020, 17, 100287. [CrossRef]
96. Teluguntla, P.; Thenkabail, P.S.; Xiong, J.; Gumma, M.K.; Giri, C.; Milesi, C.; Ozdogan, M.; Congalton, R.; Tilton, J.; Sankey, T.T.;
et al. Global Cropland Area Database (GCAD) derived from remote sensing in support of food security in the twenty-first century:
Current achievements and future possibilities. In Land Resources: Monitoring, Modelling, and Mapping; Taylor & Francis: Oxford,
UK, 2015.
97. Tamiminia, H.; Salehi, B.; Mahdianpari, M.; Quackenbush, L.; Adeli, S.; Brisco, B. Google Earth Engine for geo-big data
applications: A meta-analysis and systematic review. ISPRS J. Photogramm. Remote Sens. 2020, 164, 152–170. [CrossRef]
98. Lebrini, Y.; Boudhar, A.; Laamrani, A.; Htitiou, A.; Lionboui, H.; Salhi, A.; Chehbouni, A.; Benabdelouahab, T. Mapping and
characterization of phenological changes over various farming systems in an arid and semi-arid region using multitemporal
moderate spatial resolution data. Remote Sens. 2021, 13, 578. [CrossRef]
99. Murmu, S.; Biswas, S.J.A.P. Application of fuzzy logic and neural network in crop classification: A review. Aquat. Procedia 2015, 4,
1203–1210. [CrossRef]
100. Li, Q.; Qiu, C.; Ma, L.; Schmitt, M.; Zhu, X.X. Mapping the land cover of Africa at 10 m resolution from multi-source remote
sensing data with Google Earth Engine. Remote Sens. 2020, 12, 602. [CrossRef]
101. Congalton, R.G.; Yadav, K.; McDonnell, K.; Poehnelt, J.; Stevens, B.; Gumma, M.K.; Teluguntla, P.; Thenkabail, P.S. Global Food
Security-Support Analysis Data (GFSAD) Cropland Extent 2015 Validation 30 m V001; NASA EOSDIS Land Processes DAAC: Sioux
Falls, SD, USA, 2017.
102. Hansen, M.C.; Potapov, P.; Hancher, M.; Turubanova, S.; Tyukavina, A.; Thau, D.; Stehman, S.V.; Goetz, S.J.; Loveland, T.R.;
Kommareddy, A.; et al. High-resolution global maps of 21st-century forest cover change. Science 2013, 342, 850–853. [CrossRef]
103. Carroll, M.L.; Townshend, J.R.; DiMiceli, C.M.; Noojipady, P.; Sohlberg, R.A. A new global raster water mask at 250 m resolution.
Int. J. Digit. Earth 2009, 2, 291–308. [CrossRef]

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.