出版社：Thai Society of Higher Eduction Institutes on Environment
摘要：Constructing a silt pit is one of the most widely adopted and effective practices used in oilpalm plantations to conserve soil and water. The objective of this study was to utilize theHYDRUS-2D/3D to determine the optimal dimensions of silt pit and optimise the simulationresults employing the multiple linear regression (MLR) and/or artifcial neural network (ANN).Both methods were used to select the optimal size and dimensions of silt pit sizes dependingon the amount of rain and soil properties. The treatments that were adopted included: 1) sevensoil textures, 2) fve surface slopes, and 3) three silt pits sizes. Each silt pit size comprised ofthree depth levels to accommodate the amount of water available in the pit. The approach frstutilised the HYDRUS-2D/3D software to simulate the time-to-empty (TTE) of various silt pitsizes on different soil and slopes. Secondly, trends were then distinguished from the data, andthe best ft was determined using MLR and ANN models to estimate the optimal silt pit size.The TTE was affected by the water head in the pits (H), pit width (W), the amount of waterapplied (Vw), and the pit volume (Vp), but was not affected by the surface slope (Slope). Thefndings demonstrated that the MLR models did not perform sufciently to represent the resultsof TTE (R2 = 0.632; MSE = 85.83) compared with the ANN models (R2 = 0.977; MSE = 10.33).This was mainly due to the non-linear relations of these factors. The results demonstrated thatby using the same input data, the ANN models could favourably be used for TTE predictions.
关键词：Soil water conservation; Silt pit; HYDRUS-2D/3D; Multiple Linear Regression;
Artifcial Neural Network
