Paper Contents
Abstract
Accurate crop yield prediction is a critical component of sustainable agriculture and food security. Traditional yield forecasting methods rely heavily on expert intuition and historical observations, lacking precision and scalability. This study proposes a web-based system powered by machine learning models to predict crop yield based on environmental and climatic variables such as temperature, rainfall, fertilizer usage, and crop type. Among various tested models, the Decision Tree Regressor was chosen for deployment due to its ability to model complex, non-linear relationships in agricultural datasets. The platform supports real-time data input, provides instant predictions, and facilitates user-admin communication through query management and FAQs, enabling informed decision-making for farmers and planners.
Copyright
Copyright © 2025 Spandana K. This is an open access article distributed under the Creative Commons Attribution License.
