Domain knowledge informed multitask learning for landslide induced seismic classification

Li, Jiangfeng and Ye, Minxiang and Stankovic, Lina and Stankovic, Vladimir and Pytharouli, Stella (2023) Domain knowledge informed multitask learning for landslide induced seismic classification. IEEE Geoscience and Remote Sensing Letters, 20. pp. 1-5. 7503005. ISSN 1545-598X (https://doi.org/10.1109/LGRS.2023.3279068)

[thumbnail of Li-etal-IEEE-GRSL-2023-Domain-knowledge-informed-multitask-learning-for-landslide]
Preview
Text. Filename: Li_etal_IEEE_GRSL_2023_Domain_knowledge_informed_multitask_learning_for_landslide.pdf
Accepted Author Manuscript
License: Creative Commons Attribution 4.0 logo

Download (1MB)| Preview

Abstract

Automatic seismic signal classification methods are extensively investigated to reduce or replace manual interpretation, with great potential in previous research. Discriminative seismic wave propagation physical characteristics, such as velocities and accelerations, are rarely considered for classification. A multitask learning scheme is proposed that utilizes the seismic wave equation and 3-D P-wave velocity Vp model for signal representation learning. The classifier uses the obtained latent feature maps on a convolutional neural network (CNN) architecture for classification of rockfall, slide quake, earthquake, and natural/anthropogenic noise events, recorded at an ongoing landslide. Our experimental results show that our approach outperforms state-of-the-art methods.

Persistent Identifier

https://doi.org/10.17868/strath.00085576