A Hierarchical Reconstruction Framework for the Gap Area of ESA CCI Soil Moisture Product Using Deep Learning Model

Remote sensing holds significant advantages in large-scale soil moisture (SM) monitoring, providing numerous satellite SM products with valuable spatio-temporal insights and timely data updates. However, some popularly used satellite SM products, such as the European Space Agency Climate Change Initiative (ESA CCI) SM product, suffer from substantial data gaps due to factors such as radio-frequency interference, revisit time, frozen soil, and snow cover. These gaps severely hamper its utility in large-scale meteorological and hydrological applications. To address these limitations, this study introduces an innovative gap-filling approach for reconstructing daily SM time series using the ESA CCI SM product. Our method employs a hierarchical framework that integrates the k-means clustering algorithm with a self-attention filling model and is applied to China Mainland. Through the application of the k-means clustering algorithm, the study region is systematically divided into four distinct sub-regions according to the climatic differences. In each sub-region, a specialized deep learning imputation model is individually trained, providing a targeted strategy for filling gaps. The hierarchical structure ensures a nuanced understanding of spatial variations in SM characteristics. The deep learning models, intricately trained on the specific characteristics of each sub-region, excel in capturing subtle patterns and relationships within the SM data. Rigorous validation, including comparisons with simulated gaps and existing SM datasets, verifies the precision and reliability of our hierarchical reconstruction framework. By specifically addressing data gaps on a regional level, our approach not only improves the completeness of the ESA CCI SM product but also provides a scalable solution adaptable to diverse geographical contexts. The results emphasize the effectiveness of our framework, making a promising contribution to the advancement of SM monitoring and environmental research.