Explainable AI for transparent seismic signal classification
Jiang, Jiaxin and Stankovic, Vladimir and Stankovic, Lina and Murray, David and Pytharouli, Stella; (2024) Explainable AI for transparent seismic signal classification. In: 2024 IEEE International Geoscience and Remote Sensing Symposium. IEEE International Symposium on Geoscience and Remote Sensing (IGARSS) . IEEE, GRC, pp. 8801-8805. ISBN 9798350360325 (https://doi.org/10.1109/IGARSS53475.2024.10641214)
Preview |
Text.
Filename: Jiang-etal-IGARSS-2024-Explainable-AI-for-transparent-seismic-signal-classification.pdf
Accepted Author Manuscript License: Download (1MB)| Preview |
Abstract
Deep learning has found extensive applications in classifying seismic signals in recent years. However, as a black box algorithm, deep learning is still rarely exploited in real-world applications, such as landslide monitoring. This is particularly a concern for geoscientists who prefer to classify seismic signals based on their physical properties, through feature engineering. To build trust in deep learning model outputs, we propose a CNN multi-classifier architecture to classify seismic signals into four classes (earthquake, micro-quake, rockfall and noise), and explain its outputs based on Layer-wise Relevance Propagation. We demonstrate that the provided explanations can lead to a more interpretable model by relating network outputs to geophysical phenomena and showing that distinguishing features extracted by the network are aligned with those identified by geoscientists as pertinent to classes of interest.
ORCID iDs
Jiang, Jiaxin, Stankovic, Vladimir ORCID: https://orcid.org/0000-0002-1075-2420, Stankovic, Lina ORCID: https://orcid.org/0000-0002-8112-1976, Murray, David ORCID: https://orcid.org/0000-0002-5040-9862 and Pytharouli, Stella ORCID: https://orcid.org/0000-0002-2899-1518;-
-
Item type: Book Section ID code: 90417 Dates: DateEvent5 September 2024Published15 March 2024AcceptedSubjects: Geography. Anthropology. Recreation > Physical geography
Technology > Electrical engineering. Electronics Nuclear engineering
Science > Mathematics > Electronic computers. Computer scienceDepartment: Faculty of Engineering > Electronic and Electrical Engineering
Faculty of Engineering > Civil and Environmental EngineeringDepositing user: Pure Administrator Date deposited: 30 Aug 2024 08:27 Last modified: 11 Oct 2024 00:15 Related URLs: URI: https://strathprints.strath.ac.uk/id/eprint/90417