Comprehensive modeling of monthly mean soil temperature using multivariate adaptive regression splines and support vector machine

Soil temperature (T-s) and its thermal regime are the most important factors in plant growth, biological activities, and water movement in soil. Due to scarcity of the T-s data, estimation of soil temperature is an important issue in different fields of sciences. The main objective of the present study is to investigate the accuracy of multivariate adaptive regression splines (MARS) and support vector machine (SVM) methods for estimating the T-s. For this aim, the monthly mean data of the T-s (at depths of 5, 10, 50, and 100 cm) and meteorological parameters of 30 synoptic stations in Iran were utilized. To develop the MARS and SVM models, various combinations of minimum, maximum, and mean air temperatures (T-min, T-max, T); actual and maximum possible sunshine duration; sunshine duration ratio (n, N, n/N); actual, net, and extraterrestrial solar radiation data (R-s, R-n, R-a); precipitation (P); relative humidity (RH); wind speed at 2 m height (u(2)); and water vapor pressure (V-p) were used as input variables. Three error statistics including root-mean-square-error (RMSE), mean absolute error (MAE), and determination coefficient (R-2) were used to check the performance of MARS and SVM models. The results indicated that the MARS was superior to the SVM at different depths. In the test and validation phases, the most accurate estimations for the MARS were obtained at the depth of 10 cm for T-max, T-min, T inputs (RMSE = 0.71 degrees C, MAE = 0.54 degrees C, and R-2 = 0.995) and for RH, V-p, P, and u(2) inputs (RMSE = 0.80 degrees C, MAE = 0.61 degrees C, and R-2 = 0.996), respectively.