Land Use and Ecosystem Services Open access Peer reviewed

Uncovering Dynamic and Nonlinear Driving Mechanisms of Production–Living–Ecological Space Change in Metropolitan Areas Using Interpretable Machine Learning

Jia Liao, Bin Quan, Kui Liu, Zhiwei Deng

Sustainability | Jun 9, 2026

Abstract

Abstract

Rapid urbanization reshapes Production–Living–Ecological Space (PLES), creating challenges for metropolitan spatial planning, ecological protection, and adaptive land governance. However, the temporal heterogeneity and nonlinear mechanisms associated with PLES change remain insufficiently explored. Taking the Changsha–Zhuzhou–Xiangtan Metropolitan Area (CZXMA) as an empirical study, this research develops an integrated framework to identify stage-based land transitions, dynamic predictor importance, and nonlinear response patterns of PLES from 2010 to 2025. The study aims to clarify how PLES transition intensity changes across development stages and how key predictive factors vary over time. The results show the following: (1) PLES evolution is characterized by persistent expansion of living space and contraction of ecological space, with living space predominantly encroaching upon production space, while overall change intensity peaked during 2010–2015. (2) The dominant driving forces shifted from administrative planning and proximity to government in the early stage to demographic and market-oriented factors during later metropolitan integration. (3) SHapley Additive exPlanations (SHAP) analysis reveals nonlinear responses, with population growth showing an inverted U-shaped association with living-space expansion, suggesting possible land-use saturation. Compared with conventional static monitoring or single-method driver detection, this framework improves the diagnosis of dynamic land-system change by linking transition intensity with interpretable, period-specific predictive associations. The main policy insight is that metropolitan land governance should move from static zoning toward adaptive planning that monitors expansion intensity, demographic pressure, and ecological constraints. This study supports more resilient and efficient land-use strategies in rapidly urbanizing metropolitan regions.

Direct answer

What can I do from this paper page?

Use this page to scan "Uncovering Dynamic and Nonlinear Driving Mechanisms of Production–Living–Ecological Space Change in Metropolitan Areas Using Interpretable Machine Learning" quickly: start with the summary and abstract, then check the authors, source, topics, and related papers. From here, open Scollr to follow Land Use and Ecosystem Services research, save the paper, or map adjacent work.

Authors

Researchers on this paper

Jia Liao

first | Hengyang Normal University

Bin Quan

middle | Hengyang Normal University | ORCID 0000-0001-7009-6560

Kui Liu

middle | Hengyang Normal University

Zhiwei Deng

last | Hunan Normal University | ORCID 0000-0002-6750-1892

Research areas

Follow related topics

Citation

BibTeX

@article{Liao2026Uncovering,
  title = {Uncovering Dynamic and Nonlinear Driving Mechanisms of Production–Living–Ecological Space Change in Metropolitan Areas Using Interpretable Machine Learning},
  author = {Jia Liao and Bin Quan and Kui Liu and Zhiwei Deng},
  journal = {Sustainability},
  year = {2026},
  doi = {10.3390/su18125894},
  url = {https://doi.org/10.3390/su18125894}
}

FAQ

Using this paper in a discovery workflow

How do I find related work for this paper?

Use the related papers and topic links on this page as starting points. In Scollr, you can also open the paper and build a literature map around its references, citing papers, and related work.

How can I keep up with new Land Use and Ecosystem Services research papers?

Follow Land Use and Ecosystem Services research in Scollr. New papers from the topic flow into a personalized feed, and you can save useful studies to revisit later.

Can I cite this paper from this page?

This page includes a static BibTeX block for Uncovering Dynamic and Nonlinear Driving Mechanisms of Production–Living–Ecological Space Change in Metropolitan Areas Using Interpretable Machine Learning. Always verify the DOI, source, and publication details against the publisher record before submitting a manuscript.

Follow this research in Scollr

Follow the topics and authors behind this paper, save useful studies, and build a literature map when you are ready to go deeper.

Get the app