Estimation and validation of furrow infiltration parameters and roughness based on LSSVM-GA

Infiltration parameters and roughness are essential parameters in the design and management of furrow irrigation. Accurate determination of these parameters is essential for achieving reliable irrigation techniques and improving furrow irrigation performance. Therefore, this study proposed a method combining least squares support vector machines (LSSVM) and genetic algorithm (GA) to invert infiltration parameters and roughness. During the parameters inversion, it is necessary to know the simulated values of advance and recession time to construct the objective function, but the relationship between the furrow irrigation advance, recession time and soil infiltration parameters and roughness is implicit in the zero-inertia model, lacking a direct solution. Manually inputting parameters into WinSRFR for validation would severely hinder the efficiency of parameter estimation. Therefore, this study utilized LSSVM to map the complex nonlinear relationship the furrow irrigation advance, recession times and soil infiltration parameters and roughness. The advance time LSSVM regression model (regularization constant 60, RBF kernel width 35) and recession time LSSVM regression model (regularization constant 70, RBF kernel width 20) were constructed. Results showed that the root mean square error (RMSE) for advance and recession time in training samples ranged from 0.84 to 1.75 min and 2.18 to 3.16 min, respectively. For testing samples, the RMSE values ranged from 0.85 to 1.77 min and 2.41 to 3.62 min, demonstrating high prediction accuracy. This approach reduces the computational burden of manual input in WinSRFR by using LSSVM regression models to simulate advance/recession time, thus facilitating parameter estimation with GA. The key to implementing the LSSVM-GA method lies in the data transfer and iteration between LSSVM and GA when calculating the fitness function. To further verify the reliability of the proposed method, furrow irrigation experiments were conducted on closed-end furrows in cornfields in Shuangzhao Village, Xianyang, Shaanxi Province, China. Two typical furrow lengths were selected, each with two test plots to observe the actual advance and recession times. Each scheme was repeated three times, and the final experimental data were averaged. Multiple nonlinear regression (MNR) and Merriam-Keller post-irrigation volume balance analysis (MK-PIVB) from WinSRFR were also used for comparison. Results indicated that for the advance process simulation, the parameters estimated by MK-PIVB and LSSVM-GA provided similar curves, with RMSE ranging from 1.30 to 2.94 min and coefficient of determination (R²) from 0.97 to 0.99. In contrast, MNR performed slightly worse, particularly for F1, with an RMSE of 5.52 min. Further analysis of the recession process showed that MNR's parameter estimates were not ideal, with RMSE ranging from 4.77 to 6.00 min and R² below 0.60. MK-PIVB's estimates were satisfactory only for F2, but were inaccurate for the other three furrows with RMSE of 4.75, 4.13, and 4.18 minutes and R² of 0.49, 0.70, and 0.54, respectively. The LSSVM-GA method provided improved parameter estimates for both processes, with RMSEs ranging from 1.06 to 2.12 minutes for advance and 2.28 to 3.11 minutes for recession. The LSSVM-GA method effectively combined nonlinear mapping and heuristic algorithms, overcoming the limitations of the other two methods, such as the need for predefined regression functions, reliance on manual experience and judgment, and high computational cost.