Hybrid Time Series Methods and Machine Learning for Seismic Analysis and Volcano Eruption Predict

Aug 4, 2026

Upload by Rowan

Volcanic eruption represents a severe natural hazard for communities around active volcanoes, making continuous monitoring essential for detecting signals before an eruption. This study introduces a hybrid time series framework combined with machine learning to improve identification and classification of eruption-related seismic events. It applies STA/LTA, template matching, and autocorrelation, then uses the hybrid approach to reduce noise and isolate genuine events. Using Merapi data from 2019–2021, experiments with learning rate 0.01 show higher accuracy than single techniques, reaching 0.93–0.95, supporting forecasting and risk mitigation.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages19

Reading Time48 min

AccessFree to download

Introduction

Seismic monitoring in the Ring of Fire

Merapi hazard context and data reliability

Motivation for hybrid time series and ML

Methods

Hybrid time series components (STA/LTA, template matching, autocorrelation)

Noise removal and event classification pipeline

Dataset and experimental setup

Results and Discussion

Classification accuracy comparison

Implications for forecasting and risk mitigation

Hybrid Time Series Methods and Machine Learning for Seismic Analysis and Volcano Eruption Predict Fridy Mandita 1, 2, Ahmad Ashari 3*, Moh. Edi Wibowo 3 , Wiwit Suryanto 4 1 Department of Engineering, Universitas 17 Agustus 1945 Surabaya, Surabaya 60118, Indonesia. 2 Doctoral Programme of Computer Science, Universitas Gadjah Mada, Yogyakarta 55281, Indonesia. 3 Department of Computer Science and Electronics, Universitas Gadjah Mada,, Yogyakarta 55281, Indonesia. 4 Department of Physics, Universitas Gadjah Mada, Yogyakarta 55281, Indonesia. Received 02 September 2024; Revised 15 January 2025; Accepted 03 February 2025; Published 01 March 2025 Abstract Volcanic eruption refers to a natural catastrophe on Earth that poses imminent danger to communities surrounding volcanoes. Therefore, ongoing monitoring of volcanic processes is crucial for effective analysis and observation of volcanic activities preceding an eruption. In response to this, the study presents a novel hybrid time series approach, integrated with machine learning techniques, to enhance the identification and classification of seismic events associated with volcanic eruptions. In this case, time series techniques, including STA/LTA, template matching, and autocorrelation, were implemented to facilitate the detection and classification process. The challenges, however, lie in addressing noise and ensuring accuracy in the analysis of seismic signals. To resolve this, a new hybrid time series method was proposed to improve signal analysis accuracy by integrating multiple time series techniques. In practice, the dataset was collected from Mount Merapi in Indonesia between 2019 and 2021, consisting of a compilation of seismic data categorized by event type, thus enhancing classification accuracy. On top of that, prior to implementing machine learning techniques for signal classification, the hybrid method was employed to efficiently remove noise, ensuring that genuine seismic events were clearly distinguished from spurious signals. Notably, the experimental learning rate was set at 0.01. The results demonstrated that the proposed hybrid method outperformed stand-alone time series techniques, achieving an accuracy of 0.93 to 0.95. This signifies the effectiveness of precise seismic event recognition and categorization, greatly enhancing the volcano monitoring system. Furthermore, the findings offer substantial improvements in the forecasting and risk mitigation associated with volcanic eruptions, hence, advancing reliable seismic analysis methodologies. Ultimately, the method enhances hybrid methods and machine learning for seismic event analysis and volcano monitoring. Keywords: Seismic Events; Hybrid Time Series; Machine Learning; Volcano Eruption. 1. Introduction Indonesia is situated in the convergence of three tectonic plate boundaries and occupies a geographically unique position referred to as the Ring of Fire (ROF), characterized by intense tectonic activity, leading to numerous active volcanoes in Indonesia, including [1] approximately 130 active volcanoes, from Sabang to Merauke [2]. This geographical position significantly increases the potential for spontaneous volcanic eruptions, such as the eruptions recorded in one of the active and hazardous volcanoes in Indonesia, Mount Merapi [3, 4] . * Corresponding author: [ashari@ugm.ac.id](ashari@ugm.ac.id) [http://dx.doi.org/10.28991/HIJ-2025-06-01-08](http://dx.doi.org/10.28991/HIJ-2025-06-01-08) 􀂾 This is an open access article under the CC-BY license ([https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/)) .© Authors retain all copyrights. As illustrated in Figure 1, Mount Merapi volcano, located in Central Java, is marked by densely populated slopes, where many residents live as close as 28 km (17 miles) north of Yogyakarta, the city near Mount Merapi with a population of 2.4 million. Considering the dense population, in addition to 73 recorded

FAQs

What problem does the proposed study address in volcanic monitoring?

The study targets accurate identification and classification of seismic events associated with volcanic eruptions under noisy signal conditions.

Which time series techniques are integrated in the hybrid method?

The method integrates STA/LTA, template matching, and autocorrelation to support detection and classification of seismic events.

How effective is the hybrid approach compared with stand-alone time series techniques?

Experiments show the hybrid method outperforms single techniques, achieving an accuracy in the range of 0.93 to 0.95.

Aug 4, 2026

Upload by Rowan