Analysis and prediction of the changes in groundwater resources under heavy precipitation and ecological water replenishment

Abstract Identifying the influence of heavy precipitation and ecological water replenishment (EWR) on groundwater resources is essential for management risk prevention. This study innovatively developed a resource analysis prediction model integrated with level fluctuation method, correlation analysis, machine learning method under EWR. Water results showed that compared January 1, 2021, area increased 4.46 × 108 m3 August 28. Compared small flow EWR, was main contributor to rise in level. Correlation found elevation, specific yield, permeability coefficient show positive correlations recharge. Machine among models 35 monitoring wells, extreme gradient boosting (XGB) random forest (RF) performed best 30 wells five respectively. The increase storage predicted deviated from actual value by only 0.6 107 (prediction bias 1.3%), indicating performance good condition. can help better understand change trend conditions