Assessment of data intelligence algorithms in modeling daily reference evapotranspiration under input data limitation scenarios in semi-arid climatic condition

Abstract

Crop evapotranspiration is essential for planning and designing an efficient irrigation system. The present investigation assessed the capability of four machine learning algorithms, namely, XGBoost linear regression (XGBoost Linear), XGBoost Ensemble Tree, Polynomial Regression (Polynomial Regr), and Isotonic Regression (Isotonic Regr) in modeling daily reference evapotranspiration (ETo) at IARI, New Delhi. The models were developed considering full and limited dataset scenarios. The efficacy of the constructed models was assessed against the Penman–Monteith (PM56) model estimated daily ETo. Results revealed the under full and limited dataset conditions, XGBoost Ensemble Tree gave the best results for daily ETo modeling during the model training period, while in the testing period under scenarios S1(Tmax) and S2 (Tmax, and Tmin), the Isotonic Regr models yielded superior results over other models. In addition, the XGBoost Ensemble Tree models outperformed others for the rest of the input data scenarios. The XGBoost Ensemble Tree algorithms reported the best values of correlation coefficient (r), mean absolute error (MAE), mean square error (MSE), root mean square error (RMSE), and mean absolute percentage error (MAPE). Thus, we recommend applying the XGBoost Ensemble Tree algorithm for precisely modeling daily ETo in semi-arid climatic conditions. HIGHLIGHTS Four machine learning algorithms were tested for daily ETo modeling.; Five input scenarios were developed using cross-correlation analysis.; The performance was assessed using five statistical performance indicators.; The XGBoost Ensemble Tree algorithm is found best in daily ETo modeling.; The weighted score-based model ranking was done.;

Keywords

• box plot
• irrigation scheduling
• machine learning
• mean absolute error
• model ranking
• taylor diagram