MVPS’s KBT College of Engineering

Department of Information Technology

Academic year : 2024-25

A Seminar On
“ Artificial Intelligence in Agriculture with focus on Plant
Disease”

Presented By
Vedant Gokul Patil (TE_IT)

Under the Guidance of

Ms. Tejaswini S. Pawar
 Contents

➢ Introduction
➢ Motivation
➢ Literature Survey(Minimum 8 Papers)
➢ Scope
➢ Objectives
➢ Details Of Technology / Block Diagram
➢ Methodology
➢ Applications
➢ Conclusion
➢ Future scope
➢ Reference
 Introduction
WHAT IS AI?
Artificial intelligence is the simulation of human
intelligence processes by machines, especially
computer systems. Examples of AI applications
include expert systems, natural language
processing (NPL), speech
recognition and machine vision.
IMPORTANCE OF AGRICULTURE
Food security

Economic development

Foreign exchange

Poverty reduction

Innovation and Technological Development

Raw Materials
ROLE OF AI IN AGRICULTURE
•Plant Disease Detection

•Precision Farming

•Yield Prediction

•Soil and Crop Monitoring

•Weather Forecasting

•Sustainable Farming
 SCOPE

•AI enables data-driven decision-making for:

•Optimizing resource use
•Increasing crop yields
•Enhancing sustainability

•AI supports predictive analytics to:

•Forecast weather patterns
•Predict pest outbreaks

•AI contributes to improving:

•Food security
•Agricultural resilience
OBJECTIVES

Enhancing Productivity

Automation

Early Disease Detection

Resource Optimization
MOTIVATION
Labor Shortage Challenges of Traditional Methods:

Global Food Security : Climate Change

 LITERATURE SURVEY
Author & Research Technology
SR NO Paper Title Advantages Limitations
Year Focus Used

Role of AI in
Agriculture: An Plant disease Machine
1 Ruchi Rani et Data scarcity in
Analysis & detection using leaning,Deep High accuracy
al., 2023 agriculture
Focus on Plant AI learning
Diseases​

Fast and
Revolutionizing Review of AI-
Jafar et al. Deep learning, scalable for Potential issues with
Agriculture with based disease
2 (2024) IoT, Image real-time generalizing models
Artificial detection in
Processing disease to new environments
Intelligence various crops
detection.
CNN with
Plant Disease Inception and lower accuracy on
Identification Residual High accuracy cassava dataset
Arnab Kumar CNN to identify
3 Using a connections, on rice (76.59%) due to
Maji,2022 plant disease depthwise
Convolutional (99.66%) complex
Neural Network separable backgrounds.
convolution
 Research Technology
SR NO Paper Title Author & Year Advantages Limitations
Focus Used

Real-Time Plant
Disease Dataset Limited to maize,
Development Deep Learning rice, and wheat;
Diana S. ML, Deep
4 and Detection of to identify plant High accuracy focuses on
Joseph,2024 learning
Plant Disease disease specific stages
Using Deep of disease
Learning

IoT-based
AI and IoT for
disease Real-time data Limited to
5 Precision Liu et al., 2022 IoT, ML
prediction for tea collection specific crops
Farming
plants

CNN-Based Citrus disease

Hassam et al., High accuracy, Requires large
6 Citrus Disease detection using DL
2020 scalable datasets
Detection CNN
. TECHNOLOGY USED

1.Machine Learning (ML) Algorithms

-Supervised Learning
-Unsupervised Learning
2.Deep Learning
-Convolutional Neural Networks (CNNs)
3.Computer Vision
4.Internet of Things (IoT)
5. Natural Language Processing (NLP)
BLOCK DIAGRAM
SUPPORT VECTOR MACHINE (SVM)
SVM is a supervised machine learning algorithm primarily used for classification tasks. It
works by finding the hyperplane that best separates the data points into different classes.
HOW SVM WORKS
• Hyperplane: Finds the optimal boundary that separates different classes in the feature
space.
• Support Vectors: Identifies the closest data points to the hyperplane that define its position
and orientation.
• Maximizing Margin: Aims to maximize the distance between the hyperplane and the support
vectors.
• Kernel Trick: Transforms data into higher dimensions to handle non-linear separability using
different kernel functions (e.g., linear, polynomial, RBF).
• Optimization: Solves for the best hyperplane using an optimization problem to minimize
classification error.
RANDOM FOREST
Random Forest is an ensemble learning technique used for classification and regression tasks. It
consists of multiple decision trees, each trained on random subsets of the data. The final output is
determined by aggregating the predictions from all individual trees, typically through majority voting (for
classification) or averaging (for regression)
HOW TO IDENTIFY THE PLANT DISEASE
1.Data Collection:
-Gather data from various sources, including images of plants (healthy and diseased),
environmental parameters, and historical data on plant diseases.
2.Data Preprocessing:
-Clean and prepare the data for analysis. This may involve resizing images, augmenting
data to increase variability, and labeling data for supervised learning tasks.
3.Model Training:
•Split the dataset into training, validation, and testing sets. Train machine learning or deep
learning models on the training set to recognize patterns associated with plant diseases.
4.Model Evaluation:
Test the model on the validation and testing sets to evaluate its accuracy, precision, recall,
and F1 score. Fine-tune the model based on performance metrics.
5.Deployment
-Implement the trained model in a real-world setting, where it can be used to
monitor crops and detect diseases in real-time.
6.Decision Support Systems:
-Integrate AI models with decision support systems that provide farmers with
recommendations on disease management, including treatment options and
preventive measures.
7.Continuous Learning:
-Update the models regularly with new data to improve accuracy and adapt to
emerging plant diseases.
EXAMPLES OF PLANTS DISEASES
TOMATO APPLE RICE Cucumber

Early Blight Apple Scab Rice Spot Powdery Mildew

USING SVM AND RANDOM FOREST

 DEEP LEARNING : CNN
• Convolutional Layers: Apply filters to the input image to extract features like edges, textures, and
shapes.
• Pooling Layers: Reduce the size of feature maps, retaining key information while lowering
computational cost.
• Fully Connected Layers: Connect flattened features to the output, providing the final classification
decision.
• Activation Functions: Apply non-linear functions like ReLU to enable the model to learn complex,
non-linear patterns.

Steps in CNN-Based Plant Disease Detection:

1.Data Collection
2.Preprocessing
3.Feature Extraction
4.Training the Model
5.Prediction and Classification
6.Deployment
 Internet Of Things(IOT)
• Sensors, drones, and smartphones
are used to gather large amounts of
data, such as images, environmental
conditions, and soil health. These
datasets are essential for training AI
models to accurately diagnose plant
diseases.

• IoT Devices: Internet of Things (IoT)

devices such as soil sensors or
weather sensors can complement
image data, providing AI systems with
real-time data to analyze
environmental factors that might
influence disease spread.
Computer Vision
Computer vision is a powerful tool in modern agriculture, enhancing the ability to identify
plant diseases accurately and efficiently. By leveraging advanced image processing
techniques and machine learning, farmers can take timely actions to protect their crops
and optimize yields.
LIVE DEMONSTRATION
https://teachablemachine.withgoogle.com/train/image
APPLICATIONS
1.Yield Prediction
Machine learning predicts crop yields
based on historical weather and soil data.

2. Precision Agriculture
AI provides data-driven insights to optimize
resource usage, reducing waste and
improving crop health.
3. Automated Monitoring Systems

Drones equipped with AI continuously

monitor fields for disease symptoms,
alerting farmers to potential issues.

4. Crop Breeding and Genetics

AI analyzes genetic data to develop disease-
resistant crop varieties by identifying beneficial
traits.
5.Customized Treatment Recommendations

AI provides specific treatment plans based on

identified diseases, recommending targeted
interventions.

6.Supply Chain Optimization

AI helps manage supply chains by

considering how plant diseases may affect
crop availability and pricing.
CASE STUDY
Background:
A large-scale tomato farm in California (2003) faced recurring losses
due to late blight, a devastating fungal disease.
Outcome:
With the AI system, the farm could detect late blight at an early
stage, allowing for targeted pesticide application, reducing the
spread of the disease.
AI Solution:
The farm implemented an AI-powered system using Convolutional
Neural Networks (CNNs) for real-time disease detection. Drones
equipped with high-resolution cameras captured images of the
tomato plants, and the AI model analyzed these images to detect
early signs of late blight.
CHALLANGES
FUTURE SCOPE
• Advanced Machine Learning Techniques

• Integration of IoT and AI

• Predictive Analytics and Decision Support

• Remote Sensing and Drone Technology

• Mobile Applications and Accessibility

• Sustainable Agriculture Practice

CONCLUSION
The application of AI in agriculture, particularly in plant disease
management, enhances crop health monitoring and improves yields.
By leveraging various technologies and methodologies, farmers can
make data-driven decisions, leading to more efficient and
sustainable farming practices.
REFERENCES
1.Rani, R., Sahoo, J., Bellamkonda, S., Kumar, S., & Pippal, S. K. (2023). Role of Artificial
Intelligence in Agriculture: An Analysis and Advancements With Focus on Plant Diseases.
IEEE Access, 11, 137999-138015. doi:10.1109/ACCESS.2023.3339375

2.Kamilaris, A., & Prenafeta-Boldu, F. X. (2018). Deep learning in agriculture: A survey.

Computers and Electronics in Agriculture, 147, 70-90. doi:10.1016/j.compag.2018.02.016.

3.Fuentes, A., Yoon, S., Kim, S., & Park, D. (2017). A robust deep-learning-based detector
for real-time tomato plant diseases and pests recognition. Sensors, 17(9), 2022.
doi:10.3390/s17092022.

4.Gao, Z., Khot, L. R., Naidu, R. A., & Zhang, Q. (2020). Early detection of grapevine
leafroll disease in a red-berried wine grape cultivar using hyperspectral imaging. Computers
and Electronics in Agriculture, 179, 105807. doi:10.1016/j.compag.2020.105807.

5.Liu, C., Zhang, L., Huang, Q., & Xu, W. (2022). Internet of Things (IoT) and machine
learning model of plant disease prediction—Blister blight for tea plant. IEEE Access, 10,
44934-44944. doi:10.1109/ACCESS.2022.3162835.
6.Hassam, R., Majeed, M., & Muhammad, M. (2020). A CNN-based approach for
identifying citrus diseases using image data. Computers and Electronics in Agriculture,
177, 105708. doi:10.1016/j.compag.2020.105708.

7. Yang, Y., Wu, L., Chen, Y., & Liang, M. (2022). Few-shot learning for crop disease
detection based on deep learning and image processing. Plant Methods, 18(1), 12.
doi:10.1186/s13007-022-00822-2.

8. Lu, Y., Chen, D., Olaniyi, E., & Huang, Y. (2021). Generative adversarial networks
(GANs) for image augmentation in agriculture: A systematic review. Computers and
Electronics in Agriculture, 200, 107208. doi:10.1016/j.compag.2022.107208.

9. Zhang, X., Wu, X., & Chen, C. (2023). Machine learning for crop disease identification:
A review. Agriculture, 13(5), 987. doi:10.3390/agriculture13050987.

10. Thakur, P. S., Khanna, P., & Sheorey, T. (2022). Trends in vision-based machine
learning techniques for plant disease identification: A systematic review. Expert Systems
with Applications, 208, 118117. doi:10.1016/j.eswa.2022.118117.
THANK YOU…