Enhancing Crop Yield Prediction using Machine Learning Techniques
T Anitha, S. Sujeetha, T. Vasundhara, M. K. Dharani · 2025
The advanced machine learning technique is important in enhancing the accuracy of crop yield forecasting, which is crucial for advancing agricultural productivity and ensuring global food security. This project aims to create a reliable model for predicting crop yields by incorporating diverse data sources, such as rainfall trends, soil characteristics, and farming inputs. By building a detailed dataset, the model is trained using the proposed Random Forest (RF) machine learning algorithm. The performance of the proposed model is assessed using evaluation metrics like Mean Squared Error (MSE) and R-squared (R2) and it is compared with traditional Linear Regression and Gradient Boosting algorithms. The analysis of feature importance indicated that average temperature, pesticide utilization, and rainfall were key factors that played critical roles in the prediction of crop yield. These variables have greatly influenced the accuracy of the model when forecasting, therefore critical towards agricultural productivity. Likewise, it featured an interactive widget interface for accessing real-time yield predictions by inputting some conditions such as climate and agronomic practices. This interfaces would serve efficient, yet instant access tools for borrowers and other stakeholders to draw insights from one another and make better decisions for early interventions towards enhancing crop yield management outcomes.