Preprints
https://doi.org/10.5194/hess-2024-129
https://doi.org/10.5194/hess-2024-129
08 May 2024
 | 08 May 2024
Status: this preprint is currently under review for the journal HESS.

Downscaling satellite-derived soil moisture in the Three North region using ensemble machine learning and multiple-source knowledge integration

Kai Liu, Hongyan Zhang, Yong Bo, Dehui Li, Long Li, Hang Li, Shudong Wang, and Xueke Li

Abstract. Soil moisture plays a crucial role in hydrological and ecological systems. While remote sensing has advanced large-scale soil moisture monitoring, current satellite products often face spatial resolution limitations. This study presents a reliable framework for downscaling satellite-derived soil moisture, leveraging ensemble machine learning and multiple knowledge sources. Our approach efficiently converges outputs from diverse machine learning algorithms through Bayesian model, harnessing spatiotemporal domains and point-wise data. Covering approximately five million square kilometres in the Three Northern region of China, our model generates 1-km daily soil moisture maps, accurately reflecting soil water content patterns and showing spatial consistency with outputs from two credible numerical models. Validation against in situ measurements from three ground networks confirms the accuracy of the downscaled dataset. Comparative analysis demonstrates the superiority of the Bayesian-based method over four individual machine learning methods. The high-resolution dataset produced proves effective in capturing drought dynamics, particularly extreme drought patterns. The robustness of our framework is further affirmed through uncertainty analysis, employing leave-one-out and progressive sample reduction approaches. In summary, our ensemble machine learning-based framework offers an efficient solution for acquiring accurate and high-resolution soil moisture data across large regions, with implications for water resource management and drought monitoring.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Kai Liu, Hongyan Zhang, Yong Bo, Dehui Li, Long Li, Hang Li, Shudong Wang, and Xueke Li

Status: open (until 03 Jul 2024)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
Kai Liu, Hongyan Zhang, Yong Bo, Dehui Li, Long Li, Hang Li, Shudong Wang, and Xueke Li
Kai Liu, Hongyan Zhang, Yong Bo, Dehui Li, Long Li, Hang Li, Shudong Wang, and Xueke Li

Viewed

Total article views: 225 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
162 54 9 225 15 4 6
  • HTML: 162
  • PDF: 54
  • XML: 9
  • Total: 225
  • Supplement: 15
  • BibTeX: 4
  • EndNote: 6
Views and downloads (calculated since 08 May 2024)
Cumulative views and downloads (calculated since 08 May 2024)

Viewed (geographical distribution)

Total article views: 211 (including HTML, PDF, and XML) Thereof 211 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 24 May 2024
Download
Short summary
Our framework brings together remote sensing, machine learning, and numerical modeling to enhance soil moisture records. We merge outputs from various machine learning algorithms to ensure the model reliability. The ability of our approach in capturing drought dynamics is noticeable, making it invaluable in arid and semi-arid regions globally, such as northern China and the northern-central United States, where drought susceptibility is high.