Mapping eruption affected area using Sentinel-2A imagery and machine learning techniques - Research Article

Aug 2, 2026

Volcanic eruptions are high-impact natural disasters requiring prompt detection and monitoring to support hazard assessment, mitigation planning, and emergency response. Remote sensing provides an effective way to identify eruption impacts, but challenges arise from very large image data dimensions. Machine learning offers scalable automation and improved handling of big data. This study compares Random Forest, Support Vector Machine, Gaussian Mixture Model, and K-Nearest Neighbors using Sentinel-2A imagery for Mount Agung, Bali (2017).

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Abstract

Introduction

Methods and Algorithms (machine learning classifiers)

Results (accuracy and mapped affected areas)

Implications for mitigation and risk reduction

JOURNAL OF DEGRADED AND MINING LANDS MANAGEMENT Volume 11, Number 1 (October 2023):5073-5083, doi:10.15243/jdmlm.2023.111.5073 ISSN: 2339-076X (p); 2502-2458 (e), [www.jdmlm.ub.ac.id](www.jdmlm.ub.ac.id) Research Article Mapping eruption affected area using Sentinel-2A imagery and machine learning techniques Ni Made Trigunasih1*, I Wayan Narka1, Moh Saifulloh2 1 Soil Sciences and Environment, Faculty of Agriculture, Udayana University, Jl. Raya Kampus UNUD, Bukit Jimbaran, Kuta Selatan, Badung-Bali 80361, Indonesia 2 Spatial Data Infrastructure Development Center (PPIDS), Udayana University, Jl. Raya Kampus UNUD, Bukit Jimbaran, Kuta Selatan, Badung-Bali 80361, Indonesia * corresponding author: [trigunasih@unud.ac.id](trigunasih@unud.ac.id) | | Abstract
Volcanic eruptions are natural disasters with significant environmental and societal impacts. Timely detection and monitoring of volcanic eruptions are crucial for effective hazard assessment, mitigation strategies, and emergency response planning. Remote sensing technology has emerged as a valuable tool for detecting and assessing the effects of volcanic eruptions. One of the challenges in remote sensing image processing is handling large data dimensions that are difficult to address using traditional methods. Machine learning approaches offer a suitable solution to tackle these challenges. Machine learning demonstrates increasing computational capabilities, the ability to handle big data and automation. This study aimed to compare different machine learning classification algorithms, including Random Forest (RF), Support Vector Machine (SVM), Gaussian Mixture Model (GMM), and K-Nearest Neighbors (KNN) . The data utilized in this study was derived from Sentinel-2A MultiSpectral Instrument (MSI) imagery, which was tested in areas affected by the eruption of Mount Agung, Bali Province, in 2017. The results indicated that the GMM algorithm performed the best among the machine learning classifiers, achieving an Overall Accuracy (OA) value of 82.04% . It was followed by RF (78.86%) and KNN (77.55%) . The areas affected by volcanic eruptions were determined by overlaying disaster-prone regions with areas mapped using the machine learning approach. The total affected area was measured as 29.89 km2, with an additional 3.31 km2 outside the designated zone. The findings of this study serve as a guideline for governmental entities, stakeholders, and communities to implement effective mitigation efforts for disaster risk reduction. | | | --- | --- | --- | | Article history:
Received 25 May 2023
Received 1 July 2023 Accepted 1 August 2023 | | | | Keywords: eruption
land cover machine learning Mount Agung-Bali remote sensing Sentinel-2A | | | | To cite this article: Trigunasih, N.M., Narka, I.W. and Saifulloh, M. 2023. Mapping eruption affected area using Sentinel-2A imagery and machine learning techniques. Journal of Degraded and Mining Lands Management 11(1):5073-5083, doi:10.15243/jdmlm.2023.111.5073 . | | | | Introduction
Mount eruptions are natural geological events with profound environmental implications, influencing various terrestrial and atmospheric processes. These eruptions not only result in immediate catastrophic effects, such as the release of ash, pyroclastic flows, and lava flows but also trigger long-term consequences that can significantly alter the landscape and ecological balance of affected regions (Thouret et al., | | 2007; Lavigne et al., 2013) . The correlation between mount eruptions and land degradation, vegetation change, and the utilization of remote sensing data for monitoring and assessment has garnered increasing attention from the scientific community in recent years. Mount eruptions are known to cause extensive land degradation through mechanisms such as soil erosion, ash deposition, and alteration of landforms (Suwa and Yamakoshi, 1999; Carn et al., 2004; Komorowski et al., 2013; Harsanto, 2015) . | Open Access 5

FAQs

What problem does the study address in mapping volcanic eruption impacts?

It targets timely detection and monitoring of eruption-affected areas using remote sensing, while overcoming the difficulty of processing large image data dimensions with traditional methods.

Which machine learning classifiers are compared, and how is performance evaluated?

Random Forest, Support Vector Machine, Gaussian Mixture Model, and K-Nearest Neighbors are compared using Sentinel-2A imagery and assessed by overall accuracy.

What mapping result and best-performing algorithm does the study report?

Gaussian Mixture Model performs best with an Overall Accuracy of 82.04%, producing a total affected area of 29.89 km² and an additional 3.31 km² outside the designated zone.

Aug 2, 2026

Upload by Lucas Martin