Soil salinity estimation based on machine learning using the GF-3 radar and Landsat-8 data in the Keriya Oasis, Southern Xinjiang, China

Aims Soil salinization has been an important environmental problem globally, particularly in oasis areas in arid zones. The advantages of using multi-source data, combining radar and optical remote sensing data, and applying machine learning-based algorithms to these data could be beneficial for add...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Plant and soil Jg. 498; H. 1-2; S. 451 - 469
Hauptverfasser: Xiao, Sentian, Nurmemet, Ilyas, Zhao, Jing
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Cham Springer International Publishing 01.05.2024
Springer
Springer Nature B.V
Schlagworte:
Agriculture
Algorithms
Analysis
Arid zones
Aridity
Biomedical and Life Sciences
China
Digital Elevation Models
Earth resources technology satellites
Ecology
Electrical conductivity
Electrical resistivity
Landsat
Learning algorithms
Life Sciences
Machine learning
Mapping
Oases
Plant Physiology
Plant Sciences
Radar
Radar data
Radar systems
Remote sensing
Research Article
Root-mean-square errors
Salinity
Salinity effects
Salinization
Soil chemistry
Soil mapping
Soil research
Soil salinity
soil salinization
Soil Science & Conservation
Soils
Soils, Salts in
China
Random forest model
GF-3 data
Soil salinization estimation
Polarization decomposition
Multi-source data prediction
ISSN:0032-079X, 1573-5036
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Aims Soil salinization has been an important environmental problem globally, particularly in oasis areas in arid zones. The advantages of using multi-source data, combining radar and optical remote sensing data, and applying machine learning-based algorithms to these data could be beneficial for addressing the soil salinization problem. Methods This study combines the environmental covariates extracted from the Gaofen-3 (GF-3) radar data, Landsat-8 multispectral data, and digital elevation model (DEM) data to explore the advantages of radar remote sensing in detecting soil salinity. The soil salinity distribution degree in the Keriya Oasis is mapped using a machine-learning-based method, and the advantages of different sensor images in predicting soil salinity are evaluated. Three soil salinity inversion models are constructed using measured electrical conductivity (EC) data, the random forest (RF), gradient boosting tree (GDBT), and extreme gradient boosting (XGBoost) models. Results The best accuracy corresponding to an R 2 of 0.87, and a root mean square error (RMSE) of 6.02 is achieved by the RF model on the GF-3 + Landsat-8 data. Therefore, the use of multi-source data is a more effective method for mapping soil salinity in the study area. The mapping results of the optimal model demonstrate that natural factors significantly influence the distribution of soil salinity. Conclusion The radar polarization decomposition characteristics are incorporated into the inversion of soil salinity modeling as an environmental covariate, providing an innovative and efficient method for soil salinity estimation in arid areas.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0032-079X
1573-5036
DOI:10.1007/s11104-023-06446-0