Machine learning-based comparative analysis of weather-driven rice and sugarcane yield forecasting models

Abstract

This study investigates the use of various machine learning algorithms for predicting rice and sugarcane yields for Navsari district of Gujarat, India. Recognizing the critical role of weather in crop productivity, accurate forecasting becomes essential for effective resource management. In methodology, weekly averages and weighted weather indices were computed based on daily weather data to develop forecast models using machine learning algorithms such as Random Forest (RF), Support Vector Regression (SVR), K-Nearest Neighbors (KNN), XGBoost (XGB), Gradient Boost Regression (GBR), and Decision Tree (DT). Results show that RF and GBR algorithms outperform others in rice yield forecasting, while Gradient Booster and XGBoost demonstrate high accuracy in sugarcane yield prediction. However, the Mean Absolute Percentage Error (MAPE) values remained above 8%, indicating room for improvement. The study also emphasizes the importance of tuning hyperparameters for each machine learning algorithms (MLA) to achieve the most accurate predictions. Overall, the findings contribute valuable insights for stakeholders, including agricultural planners, policymakers, and researchers, emphasizing the need for continued refinement and validation of models to optimize agricultural planning and decision-making in this region. MLA highlight that features associated with temperature and relative humidity (RH) play a crucial role as the most significant contributors to the forecasting models for both rice and sugarcane yield. Introducing additional features, particularly remote sensing data, holds the potential to decrease the current error range of 8 to 10% to a more favourable and lower value.