Estimation of Surface Soil Moisture Based on Improved Multi-index Models and Surface Energy Balance System

Soil moisture is a vital resource that plays a critical role in arid and semi-arid areas. In the present study, a new approach was adopted to estimate surface soil moisture based on multi-index models using reflective and thermal indices as well as surface energy balance system-Iran (SEBS-Iran) in pastures and farmlands in Qom province, Iran in 2016-2017. To select the best model based on remote sensing (RS) indices, 12 models were designed and after analysis, the best ones were selected. Afterward, the results of the SEBS-Iran algorithm and the improved multi-index model [normalized multi-band drought index (NMDI), normalized difference vegetation index (NDVI), land surface temperature (LST) and the temperature vegetation dryness index (TVDI)] were calibrated with field data in the two studied fields (pastures and farmlands). The findings indicated that the multi-index model NMDI-TDVI-LST-NDVI (R = 0.95) and SEBS-Iran (R = 0.93) both had significant correlations with measured soil moisture. Regarding both models in farmlands and pastures, the SEBS-Iran regression model was closer to the line of fit, andR(2)in the two fields was 0.95 and 0.96, respectively. Compared to SEBS-Iran, the multi-index model showed lower coefficient of determination in pastures (0.71) due to the higher accuracy of SEBS-Iran in areas with lower vegetation density. Generally, both methods were found to be suitable for soil moisture estimation. The multi-index model can be used to estimate soil moisture in densely vegetated areas on a large scale due to its simplicity and good accuracy. Moreover, the highly accurate SEBS-Iran model can be used even in sparsely vegetated areas.