A Simulation Study Using Machine Learning and Formula Methods to Assess the Soybean Groundwater Contribution in a Drought-Prone Region

Groundwater contributes to the delivery of phreatic water crop aeration zones via evapotranspiration, which is important for growth in drought-prone regions. Most studies on groundwater contribution have not considered influence stage or daily evapotranspiration. In this study, a neural network based genetic algorithm and Levenberg–Marquardt backpropagation algorithm, as well formula methods an accelerated were built assess soybean contribution; addition, performance comparison was conducted. The results indicated that machine learning had best fitting errors, with values relative mean error (RME), root square percentage (RMSPE), correlation coefficient 1.088, 2.165, 0.762, respectively; validation it RME, RMSPE, 1.069, 2.136, 0.735, respectively. method recommended readers seeking calculate contribution.