Abstract
The Guangdong–Hong Kong–Macao Greater Bay Area (GBA) has experienced intensive anthropogenic disturbance driven by rapid economic growth and accelerated urban expansion, resulting in increasing spatial heterogeneity of ecological processes and differentiated ecological risks. In this study, the Remote Sensing Ecological Index (RSEI) was used to assess the spatiotemporal evolution of ecological environmental quality in the GBA from 2015 to 2024. The Hurst exponent was applied to characterize the temporal persistence of ecological change, while Moran’s I was employed to identify spatial clustering patterns and spatial heterogeneity. In addition, Permutation Importance (PI) and Partial Dependence Plots (PDP) were integrated with the Random Forest model to quantify dominant driving factors and their nonlinear effects. The results showed that the overall ecological quality of the GBA remained generally stable during the study period, with only slight interannual fluctuations in RSEI (Slope = − 0.00104, R² = 0.0288). Spatially, high RSEI values were mainly distributed in peripheral mountainous areas, whereas low-value clusters were concentrated in core urban agglomerations, including Guangzhou, Foshan, Dongguan, and Shenzhen. The global Moran’s I values ranged from 0.6562 to 0.7063, indicating significant and stable positive spatial autocorrelation. Hurst exponent analysis revealed that most regions exhibited persistent evolutionary characteristics, while core urban areas showed relatively stronger anti-persistent behaviour and greater uncertainty in future ecological trends. Mechanism analysis demonstrated that elevation (PI = 0.3283) and land surface temperature (PI = 0.2898) were the dominant driving factors, followed by population density (PI = 0.2569) and night-time light intensity (PI = 0.2114). These factors exhibited significant nonlinear and threshold effects on ecological quality. This study provides new insights into the temporal persistence, spatial heterogeneity, and nonlinear driving mechanisms of ecological environmental quality in highly urbanized regions, offering scientific support for ecological governance and sustainable regional development.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
Reprints and permissions
About this article
Cite this article
Ge, Y., Zhou, W., Chen, Z. et al. Research on ecological quality drivers based on RSEI and machine learning a case study of the Guangdong-Hong Kong-Macao Greater Bay Area.
Sci Rep (2026). https://doi.org/10.1038/s41598-026-73693-3
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-73693-3
Keywords
- RSEI
- Hurst exponent
- Moran’s I
- Machine learning
- Driving forces
Source: Ecology - nature.com
