Vegetation coverage variability and its driving factors in the semi-arid to semi-humid transition zone of North China

Huimin Bai, Zhiqiang Gong, Li Li, Junjie Ma and Muhammad Mubashar Dogar

Chaos, Solitons & Fractals, 2025, vol. 191, issue C

Abstract: North China (NC), a transition zone between semi-arid and semi-humid as well as agriculture and livestock systems, is highly sensitive to climate change. Effective prediction of vegetation coverage changes in such transition zones under the context of climate change is critical for maintaining ecosystem stability and enhancing climate change adaptation capacity. In this study, we construct a model to simulate summer anomalies of vegetation coverage in NC based on machine learning. Considering that the change of vegetation coverage depends on regional climate characteristics, we finely divide NC into six climatic sub-regions based on climate similarity using K-means Cluster and then apply eXtreme Gradient Boosting (XGBoost) to characterize the relationship between meteorological elements and vegetation coverage. The integration of K-means Cluster and XGBoost (XGB) effectively simulates the change in summer vegetation coverage in NC, outperforming the traditional linear model by 14% and the Support Vector Machine (SVM) by 5%. XGB can characterize the nonlinear relationship between meteorological elements and vegetation coverage and identify the factors that contribute significantly to vegetation coverage change in specific climate sub-regions. The results indicate that the water factor plays a pivotal role in the semi-arid zone, while the energy factor controls the vegetation coverage in the semi-humid region. By investigating the effects of meteorological conditions on vegetation coverage in the NC, this study helps agriculturalists understand how climate change affects crops and other vegetation.

Keywords: North China; Machine learning; Vegetation coverage; Transition zone (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0960077924014693
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:chsofr:v:191:y:2025:i:c:s0960077924014693

DOI: 10.1016/j.chaos.2024.115917

Access Statistics for this article

Chaos, Solitons & Fractals is currently edited by Stefano Boccaletti and Stelios Bekiros

More articles in Chaos, Solitons & Fractals from Elsevier
Bibliographic data for series maintained by Thayer, Thomas R. ().