Journal Article

Multistage sugarcane yield prediction using machine learning algorithms

SRIDHARA, SHANKARAPPA, KASHYAP, GIRISH R., SOUMYA B. R.

2024

Overview

Sugarcane is one of the leading commercial crops grown in India. The prevailing weather during the various crop-growth stages significantly impacts sugarcane productivity and the quality of its juice. The objective of this study was to predict the yield of sugarcane during different growth periods using machine learning techniques viz., random forest (RF), support vector machine (SVM), stepwise multiple linear regression (SMLR) and artificial neural networks (ANN). The performance of different yield forecasting models was assessed based on the coefficient of determination (R2), root mean square error (RMSE), normalized root mean square error (nRMSE) and model efficiency (EF). Among the models, ANN model was able to predict the yield at different growth stages with higher R2 and lower nRMSE during both calibration and validation. The performance of models across the forecasts was ranked based on the model efficiency as ANN > RF > SVM > SMLR. This study demonstrated that the ANN model can be used for reliable yield forecasting of sugarcane at different growth stages.

• Publisher: Association of Agrometeorologist,Association of agrometeorologists
• Subject: Agricultural production / Algorithms / ANN (Artificial Neural Networks) / Artificial intelligence / Artificial neural networks / Crop growth / Crop yield / Forecasting / Forecasting models / Learning algorithms / Machine learning / Mathematical models / Multistage yield forecast / Neural networks / Random Forest / Root-mean-square errors / Stepwise Multiple Linear Regression (SMLR) / Sugarcane / Sugarcane yield / Support vector machine / Support vector machines / Wind / Yield forecasting / Yields