Temporal convolution-network-based models for modeling maize evapotranspiration under mulched drip irrigation

Accurate prediction of crop actual evapotranspiration (ETc) has great significance in designing irrigation plans and improving the water-resource use efficiency. However, existing experiment methods are either expensive or labor-costly, and the crop-coefficient (K-c) approach always results in high errors in calculating ETc, especially for nonstandard conditions like drip irrigation under plastic-film mulch. In this study, a Temporal Convolution Network (TCN) with two engineering methods (Principal Component Analysis (PCA) and Maximal Information Coefficient (MIC)) was developed to predict ETc using a two-year dataset from lysimeters for maize under drip irrigation with film mulch. The TCN models comprised of Long Short-Term Memory Networks (LSTM) and Deep Neural Networks (DNN). To further test the results of the TCN models, they were compared in predicting K-c values with FAO-56 K-c values in the literature. The results suggested that plant height, mean temperature, maximal temperature, relative humidity, solar radiation, leaf-area index, and soil temperature are the seven most important features affecting maize evapotranspiration. TCN models all performed well in predicting ETc with R-2 in the range of 0.91-0.95, MSE 0.144-0.296 mm/d, and MAE 0.309-0.434 mm/d. Compared with the LSTM and DNN models, TCN with all input features (TCN-all) improved R-2 by 0.13 and 0.06, respectively, and decreased MSE and MAE by 0.402 and 0.233 mm/d, and 0.187 and 0.153 mm/d, respectively. TCNs with features selected by the PCA and MIC methods both outperformed the PCA-based LSTM and DNN models, and the MIC-based LSTM and DNN models. K-c values predicted by the TCN-all model were closer to the actual K-c value than those modified by FAO-56.