Crop Insight: A Machine Learning-Based Smart Agriculyural Assistance System for Crop,Pest and Yield Prediction
Dhawal Jain 1, Aparna B B2*, B Akshita Chowdary 3, B Bhavish Shetty 4, Jain Pradnya Vardhaman5
1Assistant Professor, CSE Dept., Sri Dharmasthala Manjunatheshwara Institute of Technology, Ujire – 574 240 and affiliated to Visvesvaraya Technological University, Belagavi, Karnataka, India
2, 3, 4 & 5 B.E Scholars, CSE Dept., Sri Dharmasthala Manjunatheshwara Institute of Technology, Ujire – 574 240 and affiliated to Visvesvaraya Technological University, Belagavi, Karnataka, India
dhawalj@sdmit.in,22a12@sdmit.in, 22a19@sdmit.in, 22a20@sdmit.in, 22a47@sdmit.in.
Correspondence should be addressed to Sahana Kumari B: kumaribsahana07@gmail.com
ABSTRACT-Agriculture in India faces several challenges such as unpredictable climatic conditions, pest infestations, lack of timely information, and limited access to agricultural services. Farmers often rely on traditional practices and delayed guidance, which leads to reduced productivity and financial loss. Crop Insight is a smart agricultural assistance system designed to support farmers by integrating data-driven decision-making with accessible technology. The project provides a platform where farmers can register and receive essential services such as real-time weather updates, crop information, pest prediction, and yield forecasting.Using machine learning techniques developed in Python, the system analyzes soil characteristics, regional factors, and weather patterns to recommend suitable crops and predict possible pest attacks in advance. The web application offers two modules: Farmer and Admin. Farmers can view subsidies, identify nearby agricultural shops through map support, submit feedback, and raise queries directly to the admin. Administrators manage crop and farmer data, update subsidy information, and respond to queries, ensuring smooth communication. By combining predictive analytics, resource accessibility, and digital connectivity, Crop Insight aims to enhance agricultural decision-making and improve crop productivity. The system empowers farmers to minimize risks, reduce dependency on guesswork, and adopt modern farming practices. Ultimately, this project contributes toward promoting sustainable agriculture and strengthening the livelihood of farming communities through technology-driven solutions.
KEYWORDS- Smart Agriculture, Crop Prediction, Yield Prediction, Pest Prediction, Machine Learning, Weather Forecasting, Soil Features, Farmer Support System, Real-Time Updates, Web Application, Subsidy Management, Agricultural Decision Making, Apache Tomcat, Python, HeidiSQL, Data-Driven Farming, Resource Optimization, Sustainable Agriculture.
