Ensemble Machine-Learning-Based Framework for Estimating Surface Soil Moisture Using Sentinel-1/2 Data: A Case Study of an Arid Oasis in China

Junhao Liu, Zhe Hao, Jianli Ding (), Yukun Zhang, Zhiguo Miao, Yu Zheng, Alimira Alimu, Huiling Cheng and Xiang Li
Additional contact information
Junhao Liu: College of Geography and Remote Sensing Sciences, Xinjiang University, Urumqi 830046, China
Zhe Hao: Xinjiang Uygur Autonomous Region Comprehensive Land Management Center, Urumqi 830063, China
Jianli Ding: College of Geography and Remote Sensing Sciences, Xinjiang University, Urumqi 830046, China
Yukun Zhang: Xinjiang Uygur Autonomous Region Comprehensive Land Management Center, Urumqi 830063, China
Zhiguo Miao: Xinjiang Uygur Autonomous Region Comprehensive Land Management Center, Urumqi 830063, China
Yu Zheng: Xinjiang Uygur Autonomous Region Comprehensive Land Management Center, Urumqi 830063, China
Alimira Alimu: Xinjiang Uygur Autonomous Region Comprehensive Land Management Center, Urumqi 830063, China
Huiling Cheng: Xinjiang Uygur Autonomous Region Comprehensive Land Management Center, Urumqi 830063, China
Xiang Li: College of Geography and Remote Sensing Sciences, Xinjiang University, Urumqi 830046, China

Land, 2024, vol. 13, issue 10, 1-21

Abstract: Soil moisture (SM) is a critical parameter in Earth’s water cycle, significantly impacting hydrological, agricultural, and meteorological research fields. The challenge of estimating surface soil moisture from synthetic aperture radar (SAR) data is compounded by the influence of vegetation coverage. This study focuses on the Weigan River and Kuche River Delta Oasis in Xinjiang, employing high-resolution Sentinel-1 and Sentinel-2 images in conjunction with a modified Water Cloud Model (WCM) and the grayscale co-occurrence matrix (GLCM) for feature parameter extraction. A soil moisture inversion method based on stacked ensemble learning is proposed, which integrates random forest, CatBoost, and LightGBM. The findings underscore the feasibility of using multi-source remote sensing data for oasis moisture inversion in arid regions. However, soil moisture content estimates tend to be overestimated above 10% and underestimated below 5%. The CatBoost model achieved the highest accuracy (R 2 = 0.827, RMSE = 0.014 g/g) using the top 16 feature parameter groups. Additionally, the R 2 values for Stacking1 and Stacking2 models saw increases of 0.008 and 0.016, respectively. Thus, integrating multi-source remote sensing data with Stacking models offers valuable support and reference for large-scale estimation of surface soil moisture content in arid oasis areas.

Keywords: machine learning; Sentinel-1 SAR; soil moisture inversion; water cloud model (search for similar items in EconPapers)
JEL-codes: Q15 Q2 Q24 Q28 Q5 R14 R52 (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2073-445X/13/10/1635/pdf (application/pdf)
https://www.mdpi.com/2073-445X/13/10/1635/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jlands:v:13:y:2024:i:10:p:1635-:d:1494093

Access Statistics for this article

Land is currently edited by Ms. Carol Ma

More articles in Land from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().