Scribd
Upload
4 views4 pages

Project Status Report

The project titled 'From Rainfall To Harvest' aims to develop an intelligent web application for predicting crop yield in Telangana by analyzing weather patterns and climate risks. Currently, the project is in the training phase of its machine learning model and has completed initial data collection and analysis. Future steps include finalizing the model, developing pest and irrigation recommendation modules, and ensuring a user-friendly interface for farmers.

Uploaded by

sarikakawle5
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
4 views4 pages

Project Status Report

The project titled 'From Rainfall To Harvest' aims to develop an intelligent web application for predicting crop yield in Telangana by analyzing weather patterns and climate risks. Currently, the project is in the training phase of its machine learning model and has completed initial data collection and analysis. Future steps include finalizing the model, developing pest and irrigation recommendation modules, and ensuring a user-friendly interface for farmers.

Uploaded by

sarikakawle5
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

Stanley College Of Engineering And Technology For Women

(Autonomous)
Chapel Road, Abids, Hyderabad –500 001
(Approved by AICTE, Affiliated to Osmania University,
Accredited by NBA & NAAC with “A” Grade)
DEPARTMENT OF INFORMATION TECHNOLOGY

Student Project status report

Project Title: From Rainfall To Harvest:


AI INNOVATIONS RESHAPING CROP YIELD AND FARMING
EFFICIENCY
Student’s Name: Palle Sriharsha (160621737037)
Pobbathi Amaravathi (160621737039)
Safooraa Amjad Khan (160621737043)
Course Name: Information Technology
Instructor/Supervisor Name: Ms. J. Sumedha (Assistant Professor of IT)
Date: 10/01/2025
Semester: VIII – 4TH YEAR
1. PROJECT OVERVIEW
Brief Description:

This project aims to develop an intelligent system for predicting crop yield in Telangana
by analyzing historical weather patterns, rainfall trends, and climate risks like droughts,
floods, and cyclones. The system integrates weather data and cropped area statistics to
provide farmers with smart irrigation recommendations and actionable insights into pest
and disease outbreaks. The project will be implemented as a user-friendly web
application tailored for rural farmers.

2. GOALS/OBJECTIVES

The current objectives of the project include data preprocessing for weather and crop
datasets, developing the backend for crop yield prediction using Flask, and building
basic web pages for user interaction. Future objectives involve completing the machine
learning model training for crop yield prediction, integrating modules for pest and
irrigation recommendations, and optimizing and deploying the web application to
ensure seamless functionality and accessibility.

3. PROGRESS TO DATE
Work Completed:
The project began with the collection of datasets containing weather information and
cropped area statistics, which serve as the foundation for the system's predictive
capabilities. These datasets were carefully analyzed to ensure their relevance and
alignment with the project objectives. Initial exploratory data analysis was conducted to
understand the patterns and relationships within the data, focusing on key parameters
such as rainfall, temperature, and humidity

Work In Progress:
The machine learning model for crop yield prediction is currently undergoing training,
utilizing preprocessed weather and crop data to identify patterns and correlations. This
phase involves fine-tuning algorithms to ensure the model can accurately forecast yields
based on historical weather trends, rainfall patterns, and crop-specific requirements. By
leveraging advanced techniques, the model aims to deliver precise predictions that will
support farmers in making informed decisions for sustainable agricultural practices.

Problems Encountered:
Minor issues with missing and inconsistent data in weather datasets, which are being
addressed through imputation techniques.

4. TIMELINE/DEADLINES
The project timeline consists of three phases over nine weeks.

• Weeks 1–3 focus on data collection and preprocessing, including acquiring


and cleaning datasets like rainfall, climate, and crop data.
• Weeks 4–6 involve training and evaluating machine learning models for
predictions such as crop yield and risk factors.
• Finally, in weeks 7–9, the frontend is developed, integrated with predictive
models, and rigorously tested before deployment.

5. NEXT STEPS/PLAN FOR THE COMING PERIOD


The next steps for the project include finalizing the machine learning model for yield
prediction to ensure accurate and reliable results. Following this, the development and
testing of pest and irrigation recommendation modules will be undertaken to provide
actionable insights for farmers. Additionally, the frontend design will be completed,
focusing on creating a user-friendly interface, and all modules will be seamlessly
integrated into the web application to deliver a cohesive and functional platform.

6. RESOURCES NEEDED/SUPPORT
• Guidance on optimizing ML models for large datasets.
• Access to additional pest and disease-related datasets (if available).
7. FEEDBACK AND SUGGESTIONS
• Instructor/Supervisor Feedback:

• Student’s Reflection/Comments:
The project has provided significant learning opportunities in data
preprocessing and machine learning. Addressing data inconsistency and
integrating multiple modules has been challenging but insightful.

8. REFERENCES
• Datasets from Telangana State Weather Department and Agricultural Statistics.
https://data.telangana.gov.in/dataset/telangana-weather-data-2022
https://data.telangana.gov.in/dataset/cropped-area
• Research papers on crop yield prediction methodologies and pest outbreak
modeling.

Guide Name: Head of Department


Ms. J. Sumedha Dr. B. Srinivasu
Assistant Professor of IT

You might also like