Advancing food sustainability: a case study on improving rice yield prediction in Sri Lanka using weather-based, feature-engineered machine learning models

Abstract

Food sustainability is crucial aspect in achieving several United Nations (UN) Sustainable Development Goals (SDGs). By integrating advanced technologies for reliable and accurate decision-making, we can advance food sustainability and, consequently, make significant advances toward achieving the UN SDGs. Rice, a staple crop in many Asian and some African nations, is crucial to Sri Lanka as well. Serving as the primary food for most Sri Lankans, it plays a vital role in sustaining the livelihoods of over 1.8 million farmers. In Sri Lanka, rice is grown during two distinct seasons of the year (Yala and Maha). This study focuses on ML with feature engineering for rice yield prediction using weather data: Rainfall, Maximum temperature, Minimum temperature, and Radiation. The data from two districts in Yala and Maha seasons collected from 1982 to 2019 were used for evaluating two sets of models respectively. Data were pre-processed to handle the outliers and missing values and scaled using normalization. The machine learning models considered are Linear Regression (LR), Support Vector Machine (SVM), k-Nearest Neighbour (KNN), and Random Forest (RF). The performance of these models was evaluated using metrics: Root Mean Squared Error (RMSE), Relative Root Mean Squared Error (RRMSE), and Mean Absolute Error (MAE). The results demonstrate that Random Forest Regression with less number of features can yield comparable results compared to the original set of features.