Improved GNSS-R soil moisture retrieval over vegetated surfaces using a bivariate semi-empirical model.
Saved in:
| Title: | Improved GNSS-R soil moisture retrieval over vegetated surfaces using a bivariate semi-empirical model. |
|---|---|
| Authors: | Dong, Zhounan1,2,3 (AUTHOR), Jin, Shuanggen1,4 (AUTHOR) sgjin@shao.ac.cn, Chen, Dai1 (AUTHOR), Wang, Peng1 (AUTHOR) |
| Source: | Advances in Space Research. Jul2026, Vol. 78 Issue 2, p1176-1194. 19p. |
| Subjects: | Soil moisture, Bivariate analysis, Machine learning, Empirical research, Remote sensing, Artificial satellites |
| Abstract: | Spaceborne Global Navigation Satellite System-Reflectometry (GNSS-R) is an innovative remote sensing technique for measuring terrestrial surface soil moisture (SSM). While previous studies have utilized semi-empirical retrieval models and machine learning (ML) approaches to estimate SSM from the Cyclone Global Navigation Satellite System (CYGNSS) mission, achieving accurate SSM estimates over vegetation-covered areas remains a challenge. This limitation persists despite the use of vegetation extinction correction in semi-empirical models or the incorporation of vegetation-related contextual parameters in ML methods. To overcome this challenge, in this study, a parameterized pixel-wise binary regression algorithm is proposed for GNSS-R SSM estimation, specifically improving performance over vegetation-covered surfaces. Comprehensive comparisons were conducted against well-established pixel-wise univariate linear regression models and state-of-the-art ML approaches, including XGBoost and Random Forest. Experimental results demonstrate that the proposed pixel-wise binary regression model improves accuracy by 7% on a full-year test dataset compared with pixel-wise linear regression, significantly outperforming both ML models. By leveraging this bivariate linear regression framework, the SSM retrieval accuracy was significantly improved over vegetation-covered surfaces. These results demonstrate the effectiveness of parameterized regression methods for spaceborne GNSS-R SSM retrieval in vegetated areas and support their incorporation into future studies. [ABSTRACT FROM AUTHOR] |
| Copyright of Advances in Space Research is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 194701189 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Improved GNSS-R soil moisture retrieval over vegetated surfaces using a bivariate semi-empirical model. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Dong%2C+Zhounan%22">Dong, Zhounan</searchLink><relatesTo>1,2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Jin%2C+Shuanggen%22">Jin, Shuanggen</searchLink><relatesTo>1,4</relatesTo> (AUTHOR)<i> sgjin@shao.ac.cn</i><br /><searchLink fieldCode="AR" term="%22Chen%2C+Dai%22">Chen, Dai</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Peng%22">Wang, Peng</searchLink><relatesTo>1</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Advances+in+Space+Research%22">Advances in Space Research</searchLink>. Jul2026, Vol. 78 Issue 2, p1176-1194. 19p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Soil+moisture%22">Soil moisture</searchLink><br /><searchLink fieldCode="DE" term="%22Bivariate+analysis%22">Bivariate analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Empirical+research%22">Empirical research</searchLink><br /><searchLink fieldCode="DE" term="%22Remote+sensing%22">Remote sensing</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+satellites%22">Artificial satellites</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Spaceborne Global Navigation Satellite System-Reflectometry (GNSS-R) is an innovative remote sensing technique for measuring terrestrial surface soil moisture (SSM). While previous studies have utilized semi-empirical retrieval models and machine learning (ML) approaches to estimate SSM from the Cyclone Global Navigation Satellite System (CYGNSS) mission, achieving accurate SSM estimates over vegetation-covered areas remains a challenge. This limitation persists despite the use of vegetation extinction correction in semi-empirical models or the incorporation of vegetation-related contextual parameters in ML methods. To overcome this challenge, in this study, a parameterized pixel-wise binary regression algorithm is proposed for GNSS-R SSM estimation, specifically improving performance over vegetation-covered surfaces. Comprehensive comparisons were conducted against well-established pixel-wise univariate linear regression models and state-of-the-art ML approaches, including XGBoost and Random Forest. Experimental results demonstrate that the proposed pixel-wise binary regression model improves accuracy by 7% on a full-year test dataset compared with pixel-wise linear regression, significantly outperforming both ML models. By leveraging this bivariate linear regression framework, the SSM retrieval accuracy was significantly improved over vegetation-covered surfaces. These results demonstrate the effectiveness of parameterized regression methods for spaceborne GNSS-R SSM retrieval in vegetated areas and support their incorporation into future studies. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Advances in Space Research is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=194701189 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1016/j.asr.2026.04.118 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 19 StartPage: 1176 Subjects: – SubjectFull: Soil moisture Type: general – SubjectFull: Bivariate analysis Type: general – SubjectFull: Machine learning Type: general – SubjectFull: Empirical research Type: general – SubjectFull: Remote sensing Type: general – SubjectFull: Artificial satellites Type: general Titles: – TitleFull: Improved GNSS-R soil moisture retrieval over vegetated surfaces using a bivariate semi-empirical model. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Dong, Zhounan – PersonEntity: Name: NameFull: Jin, Shuanggen – PersonEntity: Name: NameFull: Chen, Dai – PersonEntity: Name: NameFull: Wang, Peng IsPartOfRelationships: – BibEntity: Dates: – D: 15 M: 07 Text: Jul2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 02731177 Numbering: – Type: volume Value: 78 – Type: issue Value: 2 Titles: – TitleFull: Advances in Space Research Type: main |
| ResultId | 1 |
