A Comparative Analysis of Remote Sensing Soil Moisture Datasets Fusion Methods: Novel LSTM Approach Versus Widely Used Triple Collocation Technique

Abstract

Microwave remote sensing technology has emerged to provide valuable products to monitor and assess soil moisture content at regional or global scales. However, each soil moisture product exhibits different advantages and shortcomings. Data fusion could help improve accuracy by merging information from different sources. In this research, a traditional triple collocation (TC) based method and a novel long short term memory network (LSTM) are used to merge soil moisture products from the soil moisture active passive mission, Advanced Microwave Scanning Radiometer 2 (AMSR2), and The Advanced SCATterometer for a study area located in western Europe. This research reveals that the LSTM outperforms the traditional TC based method for data fusion. The study identifies that both climate forcing and physiographic attributes significantly influence the spatial and temporal variations observed in the LSTM merging scheme. Consequently, the study highlights the considerable potential of the LSTM method for large-scale integration of remote sensing soil moisture data.

Keywords

• Data fusion
• long short term memory model
• remote sensing
• satellites
• soil moisture
• triple collocation