Enhancing the classification of seismic events with supervised machine learning and feature importance DOI Creative Commons

Eman Lotfy Habbak,

Mohamed S. Abdalzaher, Adel S. Othman

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Dec. 24, 2024

Abstract The accurate classification of seismic events into natural earthquakes (EQ) and quarry blasts (QB) is crucial for geological understanding, hazard mitigation, public safety. This paper proposes a machine-learning approach to discriminate events, particularly differentiating between EQs man-made QBs. core this study integrate different features unified dataset train some linear nonlinear supervised machine learning (ML) models. proposed considers collection 837 (EQs QBs) with local magnitudes $$1.5 \le M_{L} 3.3$$ 1.5 ≤ M L 3.3 from the Egyptian National Seismic Network (ENSN) event catalog 2009 2015. paper’s principal contribution applying feature selection techniques importance analysis identify best leading events’ discrimination. In other words, enhances accuracy provides insights which are most distinguishing EQ QB events. results show that only three features, corner frequency, power event, spectral ratio, best-developed ML model accomplishes discrimination 100% among several benchmarks non-linear

Language: Английский

Emerging technologies and supporting tools for earthquake disaster management: A perspective, challenges, and future directions DOI Creative Commons
Mohamed S. Abdalzaher, Moez Krichen, Francisco Falcone

et al.

Progress in Disaster Science, Journal Year: 2024, Volume and Issue: 23, P. 100347 - 100347

Published: July 3, 2024

Seismology is among the ancient sciences that concentrate on earthquake disaster management (EQDM), which directly impact human life and infrastructure resilience. Such a pivot has made use of contemporary technologies. Nevertheless, there need for more reliable insightful solutions to tackle daily challenges intricacies natural stakeholders must confront. To consolidate substantial endeavors in this field, we undertake comprehensive survey interconnected More particularly, analyze data communication networks (DCNs) Internet Things (IoT), are main infrastructures seismic networks. In accordance, present conventional innovative signal-processing techniques seismology. Then, shed light evolution EQ sensors including acoustic based optical fibers. Furthermore, address role remote sensing (RS), robots, drones EQDM. Afterward, highlight social media contribution. Subsequently, elucidation diverse optimization employed seismology prolonging presented. Besides, paper analyzes important functions artificial intelligence (AI) can fulfill several areas Lastly, guide how prevent disasters preserve lives.

Language: Английский

Citations

7
Performance enhancement of artificial intelligence: A survey DOI
Moez Krichen, Mohamed S. Abdalzaher

Journal of Network and Computer Applications, Journal Year: 2024, Volume and Issue: unknown, P. 104034 - 104034

Published: Sept. 1, 2024

Language: Английский

Citations

5
Development of seismic risk models for low-rise masonry structures considering age and deterioration effects DOI
Siqi Li,

Peng-Fei Qin,

Peng-Chi Chen

et al.

Bulletin of Earthquake Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 20, 2024

Language: Английский

Citations

4
A simple and effective MLP-Based seismic signal classifier using temporal and spectral envelope features with genetic Algorithm-Optimization DOI

E.H. Ait Laasri,

Abderrahman Atmani,

Es-Saïd Akhouayri

et al.

Measurement, Journal Year: 2025, Volume and Issue: unknown, P. 116776 - 116776

Published: Jan. 1, 2025

Language: Английский

Citations

0
Enhancing the classification of seismic events with supervised machine learning and feature importance DOI Creative Commons

Eman Lotfy Habbak,

Mohamed S. Abdalzaher, Adel S. Othman

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Dec. 24, 2024

Abstract The accurate classification of seismic events into natural earthquakes (EQ) and quarry blasts (QB) is crucial for geological understanding, hazard mitigation, public safety. This paper proposes a machine-learning approach to discriminate events, particularly differentiating between EQs man-made QBs. core this study integrate different features unified dataset train some linear nonlinear supervised machine learning (ML) models. proposed considers collection 837 (EQs QBs) with local magnitudes $$1.5 \le M_{L} 3.3$$ 1.5 ≤ M L 3.3 from the Egyptian National Seismic Network (ENSN) event catalog 2009 2015. paper’s principal contribution applying feature selection techniques importance analysis identify best leading events’ discrimination. In other words, enhances accuracy provides insights which are most distinguishing EQ QB events. results show that only three features, corner frequency, power event, spectral ratio, best-developed ML model accomplishes discrimination 100% among several benchmarks non-linear

Language: Английский

Citations

0