Estimating maize evapotranspiration based on hybrid back-propagation neural network models and meteorological, soil, and crop data

Crop evapotranspiration is a key parameter influencing water-saving irrigation and water resources management of agriculture. However, current models for estimating maize evapotranspiration primarily rely on meteorological data and empirical coefficients, and the estimated evapotranspiration contains uncertainties. In this study, the evapotranspiration data of summer maize were collected from typical stations in Northern China (Yucheng Station), and a back-propagation neural network (BP) model for predicting maize evapotranspiration was constructed based on meteorological data, soil data, and crop data. To further improve its accuracy, the maize evapotranspiration model was optimized using three bionic optimization algorithms, namely the sand cat swarm optimization (SCSO) algorithms, hunter–prey optimizer (HPO) algorithm, and golden jackal optimization (GJO) algorithm. The results showed that the fusion of meteorological, soil moisture, and crop data can effectively improve the accuracy of the maize evapotranspiration model. The model showed higher accuracy with the hybrid optimization model SCSO-BP compared to the stand-alone BP neural network model, with improvements of 2.7–4.8%, 17.2–25.5%, 13.9–26.8%, and 3.3–5.6% in terms of R², RMSE, MAE, and NSE, respectively. Comprehensively compared with existing maize evapotranspiration models, the SCSO-BP model presented the highest accuracy, with R² = 0.842, RMSE = 0.433 mm/day, MAE = 0.316 mm/day, NSE = 0.840, and overall global evaluation index (GPI) ranking the first. The results have reference value for the calculation of daily evapotranspiration of maize in similar areas of northern China.