Simulation of daily maize evapotranspiration at different growth stages using four machine learning models in semi-humid regions of northwest China.

• Construct four classical RF, SVM, ANN and ELM models. • The ELM and SVM performed slightly better than RF and ANN. • The RF and ANN models can also simulate accurately with less parameter input. • Meteorological factors and crop coefficient have significant effects on maize ET c in different growth stages. The accurate estimation of crop evapotranspiration (ET c) is essential for precision irrigation, optimal allocation of regional water resources, and efficiency improvement of agricultural water resources. This study developed Random Forest (RF), Support Vector Machine (SVM), Artificial Neural Network (ANN) and Extreme Learning Machine (ELM) models for maize ET c estimation in northwest China. The meteorological data and crop data from 2011 to 2012 were used to train the RF, SVM, ANN and ELM. The models' simulation accuracy was verified by using the data of 2013 under six different input combinations. The input combinations included daily data for crop coefficient (K c), global solar radiation (R s), wind speed (u 2), maximum and minimum air temperatures (T max and T min), and maximum and minimum relative humidity (RH max and RH min). The results showed that the SVM model achieved the highest simulation accuracy at the seedling emergence to jointing stage and at the grouting to harvest stage of summer maize, with the coefficient of determination (R2) ranging 0.701–0.895 and 0.637–0.841, mean absolute error (MAE) ranging 0.310–0.654 and 0.468–0.743 mm/d, and mean square error (MSE) ranging 0.227–0.722 and 0.513–1.227 mm/d, respectively. The ELM model achieved the highest simulation accuracy at the booting to silking stage and during the whole growth period, the coefficient of determination (R2) ranging 0.601–0.828 and 0.891–0.954, mean absolute error (MAE) ranging 0.418–1.194 and 0.285–0.530 mm/d, and mean square error (MSE) ranging 0.887–2.515 and 0.182–0.587 mm/d, respectively. Considering the accessibility and simulation accuracy of input parameters, the SVM Ⅰ-2 , ELM Ⅱ-5 , SVM III-4 , and ELM IV-2 models were recommended for simulating ET c at the seedling emergence to jointing stage, at the booting to silking stage, at the grouting to harvest stage, and during the whole growth period, with the coefficient of determination (R2) of 0.796, 0.879, 0.800 and 0.896, mean absolute error (MAE) of 0.416, 0.418, 0.553 and 0.328 mm/d, and mean square error (MSE) of 0.327, 0.887, 0.655 and 0.190 mm/d, respectively. In conclusion, machine learning models can accurately simulate the daily evapotranspiration of maize in northwest China. [ABSTRACT FROM AUTHOR]