Weather based wheat yield prediction using machine learning

Wheat crops are highly affected by the influence of weather parameters. Thus, there is a need to develop and validate weather -based models using machine learning for its reliable prediction. Wheat yield and weather data during the crop growing period were collected from IARI, New Delhi, Hisar, Amritsar, Ludhiana and Patiala. The yield prediction model was developed using stepwise multi linear regression (SMLR), support vector regression (SVR), least absolute shrinkage and selection operator (LASSO) and hybrid machine learning model LASSO-SVR and SMLRSVR in R software. Analysis was done by fixing 70% of the data for calibration and the remaining 30% data for validation. Wheat yield prediction models for study areas were developed using long term crop yield data along with long period daily weather data from the 46 th to 15 th standard meteorological weeks. On examining these models for wheat yield prediction for different locations, LASSO performed best having nRMSE value ranged between 0.6 % for Patiala to 4.8% for Ludhiana. The model performance of SVR is increased if a hybrid model in combination with LASSO and SMLR is applied. The hybrid model LASSO-SVR has shown more improvement in SVR model compared with SMLR-SVR.