Spatial Heterogeneity of Driving Factors in Multi-Vegetation Indices RSEI Based on the XGBoost-SHAP Model: A Case Study of the Jinsha River Basin, Yunnan

The Jinsha River Basin in Yunnan serves as a crucial ecological barrier in southwestern China. Objective ecological assessment and identification of key driving factors are essential for the region’s sustainable development. The Remote Sensing Ecological Index (RSEI) has been widely applied in ecolo...

Full description

Saved in:
Bibliographic Details
Main Authors: Jisheng Xia, Guoyou Zhang, Sunjie Ma, Yingying Pan
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Land
Subjects:
Online Access:https://www.mdpi.com/2073-445X/14/5/925
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849710996296302592
author Jisheng Xia
Guoyou Zhang
Sunjie Ma
Yingying Pan
author_facet Jisheng Xia
Guoyou Zhang
Sunjie Ma
Yingying Pan
author_sort Jisheng Xia
collection DOAJ
description The Jinsha River Basin in Yunnan serves as a crucial ecological barrier in southwestern China. Objective ecological assessment and identification of key driving factors are essential for the region’s sustainable development. The Remote Sensing Ecological Index (RSEI) has been widely applied in ecological assessments. In recent years, interpretable machine learning (IML) has introduced novel approaches for understanding complex ecological driving mechanisms. This study employed Google Earth Engine (GEE) to calculate three vegetation indices—NDVI, SAVI, and kNDVI—for the study area from 2000 to 2022, along with their corresponding RSEI models (NDVI-RSEI, SAVI-RSEI, and kNDVI-RSEI). Additionally, it analyzed the spatiotemporal variations of these RSEI models and their relationship with vegetation indices. Furthermore, an IML model (XGBoost-SHAP) was employed to interpret the driving factors of RSEI. The results indicate that (1) the RSEI levels in the study area from 2000 to 2022 were primarily moderate; (2) compared to NDVI-RSEI, SAVI-RSEI is more susceptible to soil factors, while kNDVI-RSEI exhibits a lower saturation tendency; and (3) potential evapotranspiration, land cover, and elevation are key drivers of RSEI variations, primarily affecting the ecological environment in the western, southeastern, and northeastern parts of the study area. The XGBoost-SHAP approach provides valuable insights for promoting regional sustainable development.
format Article
id doaj-art-74967fdc0090415ea54a974b18f91fa8
institution DOAJ
issn 2073-445X
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Land
spelling doaj-art-74967fdc0090415ea54a974b18f91fa82025-08-20T03:14:43ZengMDPI AGLand2073-445X2025-04-0114592510.3390/land14050925Spatial Heterogeneity of Driving Factors in Multi-Vegetation Indices RSEI Based on the XGBoost-SHAP Model: A Case Study of the Jinsha River Basin, YunnanJisheng Xia0Guoyou Zhang1Sunjie Ma2Yingying Pan3School of Earth Sciences, Yunnan University, Kunming 650091, ChinaSchool of Earth Sciences, Yunnan University, Kunming 650091, ChinaSchool of Earth Sciences, Yunnan University, Kunming 650091, ChinaInstitute of International Rivers and Eco-Security, Yunnan University, Kunming 650500, ChinaThe Jinsha River Basin in Yunnan serves as a crucial ecological barrier in southwestern China. Objective ecological assessment and identification of key driving factors are essential for the region’s sustainable development. The Remote Sensing Ecological Index (RSEI) has been widely applied in ecological assessments. In recent years, interpretable machine learning (IML) has introduced novel approaches for understanding complex ecological driving mechanisms. This study employed Google Earth Engine (GEE) to calculate three vegetation indices—NDVI, SAVI, and kNDVI—for the study area from 2000 to 2022, along with their corresponding RSEI models (NDVI-RSEI, SAVI-RSEI, and kNDVI-RSEI). Additionally, it analyzed the spatiotemporal variations of these RSEI models and their relationship with vegetation indices. Furthermore, an IML model (XGBoost-SHAP) was employed to interpret the driving factors of RSEI. The results indicate that (1) the RSEI levels in the study area from 2000 to 2022 were primarily moderate; (2) compared to NDVI-RSEI, SAVI-RSEI is more susceptible to soil factors, while kNDVI-RSEI exhibits a lower saturation tendency; and (3) potential evapotranspiration, land cover, and elevation are key drivers of RSEI variations, primarily affecting the ecological environment in the western, southeastern, and northeastern parts of the study area. The XGBoost-SHAP approach provides valuable insights for promoting regional sustainable development.https://www.mdpi.com/2073-445X/14/5/925GEEremote sensing ecologic indexinfluencing factorsexplainable machine learning
spellingShingle Jisheng Xia
Guoyou Zhang
Sunjie Ma
Yingying Pan
Spatial Heterogeneity of Driving Factors in Multi-Vegetation Indices RSEI Based on the XGBoost-SHAP Model: A Case Study of the Jinsha River Basin, Yunnan
Land
GEE
remote sensing ecologic index
influencing factors
explainable machine learning
title Spatial Heterogeneity of Driving Factors in Multi-Vegetation Indices RSEI Based on the XGBoost-SHAP Model: A Case Study of the Jinsha River Basin, Yunnan
title_full Spatial Heterogeneity of Driving Factors in Multi-Vegetation Indices RSEI Based on the XGBoost-SHAP Model: A Case Study of the Jinsha River Basin, Yunnan
title_fullStr Spatial Heterogeneity of Driving Factors in Multi-Vegetation Indices RSEI Based on the XGBoost-SHAP Model: A Case Study of the Jinsha River Basin, Yunnan
title_full_unstemmed Spatial Heterogeneity of Driving Factors in Multi-Vegetation Indices RSEI Based on the XGBoost-SHAP Model: A Case Study of the Jinsha River Basin, Yunnan
title_short Spatial Heterogeneity of Driving Factors in Multi-Vegetation Indices RSEI Based on the XGBoost-SHAP Model: A Case Study of the Jinsha River Basin, Yunnan
title_sort spatial heterogeneity of driving factors in multi vegetation indices rsei based on the xgboost shap model a case study of the jinsha river basin yunnan
topic GEE
remote sensing ecologic index
influencing factors
explainable machine learning
url https://www.mdpi.com/2073-445X/14/5/925
work_keys_str_mv AT jishengxia spatialheterogeneityofdrivingfactorsinmultivegetationindicesrseibasedonthexgboostshapmodelacasestudyofthejinshariverbasinyunnan
AT guoyouzhang spatialheterogeneityofdrivingfactorsinmultivegetationindicesrseibasedonthexgboostshapmodelacasestudyofthejinshariverbasinyunnan
AT sunjiema spatialheterogeneityofdrivingfactorsinmultivegetationindicesrseibasedonthexgboostshapmodelacasestudyofthejinshariverbasinyunnan
AT yingyingpan spatialheterogeneityofdrivingfactorsinmultivegetationindicesrseibasedonthexgboostshapmodelacasestudyofthejinshariverbasinyunnan