A New Approach for Soil Moisture Downscaling in the Presence of Seasonal Difference

Abstract

The variation of soil moisture (SM) is a complex and synthetic process, which is impacted by numerous factors. The effects of these factors on soil moisture are dynamic. As a result, the relationship between soil moisture and explanatory variables varies with time and season. This kind of change should be considered in obtaining fine spatial resolution soil moisture products. We chose a study area with four distinct seasons in the temperate monsoon region. In this research, we established seasonal downscaling models to avoid the influence of seasonal differences. Precipitation, land surface temperature, evapotranspiration, vegetation index, land cover, elevation, slope, aspect and soil texture were taken as explanatory variables to produce fine spatial resolution SM. SM products derived from Advanced Microwave Scanning Radiometer–Earth Observing System (AMSR-E) and Advanced Microwave Scanning Radiometer 2 (AMSR2) were downscaled with the help of machine learning algorithms. We compared three machine learning algorithms of random forest (RF), support vector machine (SVM), and K-nearest neighbors (KNN) to determine the most suitable algorithm for this study. The results show that season-based downscaling is even better than continuous time series. In the analysis of seasonal differences, precipitation plays a dominant role, but its contribution rate is different in each season. Moreover, the influence of vegetation is more prominent in winter, while the influence of terrain is more important in the other three seasons. It could be noted that the accuracy of the RF model is the best among three machine learning algorithms, and the RF-downscaled products have superior matching performance to both AMSR (AMSR-E and AMSR2) SM products and in-situ measurements. The analysis indicates considering seasonal difference and the application of machine learning has high potential for spatial downscaling in remote sensing applications.

Machine Learning Downscaling of SoilMERGE in the United States Southern Great Plains

“…Random Forest (RF) served as our baseline machine learning algorithm, which has been used to down-scale soil moisture estimates in many studies e.g., [12,13,[24][25][26][27]. We also executed eXtreme Gradient Boosting (XGBoost) [12] and Gradient Boost (GBoost) [12].…”

A Spatial Downscaling Framework for SMAP Soil Moisture Based on Stacking Strategy

“…They found that XGBoost was selected most frequently and had the highest accuracy, followed by RF. Similarly, Yan et al [16] compared three ML algorithms: RF, SVR, and k-nearest neighbors (KNN) for AMSR-E and AMSR2 products. They found that RF had the best accuracy and used it to establish seasonal downscaling models.…”

Estimation of soil moisture using environmental covariates and machine learning algorithms in Cathedral Peak Catchment, South Africa

“…Since the early 1980s, when the Scanning Multichannel Microwave Radiometer, carried by Nimbus‐8, began providing SM products, there have been developments to improve the spatial and temporal accuracy and resolution of products (Fan et al., 2022). As such, the market presents numerous remote sensing‐based SM projects retrieved from various satellites using various algorithms, for example, the Soil Moisture and Ocean Salinity of the European Space Agency with a spatial resolution of 35–50 km (Xiao et al., 2017), the Soil Moisture Active and Passive of the National Aeronautics and Space Administration with a spatial resolution of 36 km (Fan et al., 2022), and the Advanced Microwave Scanning Radiometer–Earth Observing System (AMSR‐E/2), of Japan Aerospace Exploration Agency's; with a spatial resolution of 25 km (Yan & Bai, 2020). The challenge with these SM products is their coarse spatial resolution; hence, an alternative method to estimate SM at a local scale is required.…”