Machine learning techniques on spatio-temporal data for landslide susceptibility assessment at Dieng Mountainous Region, Banjarnegara district, Central Java, Indonesia

Yusuf Susena, Danang Sri Hadmoko () and Sandy Budi Wibowo
Additional contact information
Yusuf Susena: Universitas Gadjah Mada
Danang Sri Hadmoko: Universitas Gadjah Mada
Sandy Budi Wibowo: Universitas Gadjah Mada

Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards, 2025, vol. 121, issue 8, No 38, 9925-9962

Abstract: Abstract This research was conducted in the mountainous area of Dieng, Central Java. The study area is among the highest-ranked landslide-prone areas on Java due to steep slopes and intensively weathered Tertiary volcanic rocks, which dominate the area. The annual rainfall in the Dieng region is very high, over 3000 mm/year, which represents a primary trigger for landslides. This present contribution aims at assessing landslide susceptibility through a combination of multi-temporal remote-sensing and machine learning such as Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Networks (ANN). The multi-temporal remote sensing approach was utilized to inventory landslide occurrences over the period from 2014 to 2024 using PlanetScope and Google Earth Platform. Those images and platform enabled us to map landslide occurrences comprehensively and accurately, in a relatively efficient manner, thereby reducing the extensive and costly fieldwork. Machine learning was applied as a solution to the accuracy issues inherent in semi-quantitative and probabilistic statistical methods for landslide prediction. The assessment of landslide susceptibility revealed that all three models achieved very high accuracy and could be applied to both the study area and other regions. However, accuracy assessment with various indicators showed that ANN produced the best results, followed by RF and SVM. Thus, the findings of this study can be adopted by national or local authorities in disaster mitigation as part of disaster risk reduction instruments. This is highly relevant to support the Sustainable Development Goals (SDGs) number 11: Sustainable Cities and Communities, which aims to make cities and human settlements inclusive, safe, resilient, and sustainable, including disaster risk reduction.

Keywords: Machine learning; Landslide susceptibility mapping; Random forest; Support vector machine; Artificial neural network; Remote sensing (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11069-025-07136-z Abstract (text/html)
Access to the full text of the articles in this series is restricted.

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:spr:nathaz:v:121:y:2025:i:8:d:10.1007_s11069-025-07136-z

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/11069

DOI: 10.1007/s11069-025-07136-z

Access Statistics for this article

Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards is currently edited by Thomas Glade, Tad S. Murty and Vladimír Schenk

More articles in Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards from Springer, International Society for the Prevention and Mitigation of Natural Hazards
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().