Soil-Temperature-Estimation

Soil temperature is one of the critical parameters for analyzing hydrological, ecological, meteorological and land surface processes. However, studies related to soil temperature variability are very scarce in Indian Himalayan Region (IHR). Thus, Tthis study analyzed the spatio-temporal variability of soil temperature in two lesser Himalayan hillslopes. Both grassed (GA) and agro-forested (AgF) hillslope were instrumented with Odyssey water level and decagon soil moisture and temperature sensors. The soil temperature of south aspect hillslope (i.e. GA hillslope) was higher than the north aspect hillslope (i.e. AgF hillslope). After analyzing 40 rainfall events from both the hillslope, it was observed that a rainfall duration of greater than 7.5 h or an event with average rainfall intensity of greater than 7.5 mm/h results in more than 2 o C soil temperature drop. Further, the drop in soil temperature less than 1 o C was also observed during very high-intensity rainfall which has a very low event duration. During rainy season, the soil temperature drop of GA hillslope is higher than the AgF hillslope as the former one infiltrates more water. This observation indicates the significant correlation between soil moisture rise and soil temperature drop, which was also observed. The potential of four machine learning algorithms was also explored in predicting soil temperature under data-scarce conditions. Among the four machine learning algorithms, extreme gradient boosting system (XGBoost) was performed better for both the hillslopes followed by Rrandom forests (RF), multilayer perceptron (MLP), and support vector machine (SVM). The addition of rainfall to meteorological and meteorological + soil moisture datasets did not improve the models considerably. However, the addition of soil moisture to meteorological parameters improved the model significantly.