Predicting the Spatial Distribution of Geological Hazards in Southern Sichuan, China, Using Machine Learning and ArcGIS

Ruizhi Zhang (), Dayong Zhang, Bo Shu and Yang Chen
Additional contact information
Ruizhi Zhang: School of Architecture, Southwest Jiaotong University, Chengdu 611756, China
Dayong Zhang: School of Architecture and Urban Planning, Lanzhou Jiaotong University, Lanzhou 730070, China
Bo Shu: School of Design, Southwest Jiaotong University, Chengdu 611756, China
Yang Chen: School of Design, Southwest Jiaotong University, Chengdu 611756, China

Land, 2025, vol. 14, issue 3, 1-23

Abstract: Geological hazards in Southern Sichuan have become increasingly frequent, posing severe risks to local communities and infrastructure. This study aims to predict the spatial distribution of potential geological hazards using machine learning models and ArcGIS-based spatial analysis. A dataset comprising 2700 known geological hazard locations in Yibin City was analyzed to extract key environmental and topographic features influencing hazard susceptibility. Several machine learning models were evaluated, including random forest, XGBoost, and CatBoost, with model optimization performed using the Sparrow Search Algorithm (SSA) to enhance prediction accuracy. This study produced high-resolution susceptibility maps identifying high-risk zones, revealing a distinct spatial pattern characterized by a concentration of hazards in mountainous areas such as Pingshan County, Junlian County, and Gong County, while plains exhibited a relatively lower risk. Among different hazard types, landslides were found to be the most prevalent. The results further indicate a strong spatial overlap between predicted high-risk zones and existing rural settlements, highlighting the challenges of hazard resilience in these areas. This research provides a refined methodological framework for integrating machine learning and geospatial analysis in hazard prediction. The findings offer valuable insights for rural land use planning and hazard mitigation strategies, emphasizing the necessity of adopting a “small aggregations and multi-point placement” approach to settlement planning in Southern Sichuan’s mountainous regions.

Keywords: rural settlements; potential geological hazards; machine learning; hazard prevention and mitigation; Southern Sichuan region (search for similar items in EconPapers)
JEL-codes: Q15 Q2 Q24 Q28 Q5 R14 R52 (search for similar items in EconPapers)
Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2073-445X/14/3/577/pdf (application/pdf)
https://www.mdpi.com/2073-445X/14/3/577/ (text/html)

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:gam:jlands:v:14:y:2025:i:3:p:577-:d:1608714

Access Statistics for this article

Land is currently edited by Ms. Carol Ma

More articles in Land from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().