analiza aiqbench
This study advances seismic hazard modeling by integrating VQ-VAE-derived spatial features with proven seismic statistical features, achieving high predictive accuracy in localized 24 km radius predictions. The approach effectively replaces traditional $b$-value metrics with a novel spatial error measure, demonstrating that deep learning autoencoders can capture crustal stress dynamics more efficiently than generic time series features. For the tech community, this highlights the practical utility of combining unsupervised representation learning with domain-specific statistical features to solve complex geophysical problems.
Spatiotemporal Seismic Hazard Assessment Using VQ-VAE and Seismic Statistical Features
arXiv:2606.10069v1 Announce Type: new Abstract: In this paper we build upon a previous study in which we demonstrated, using XGBoost and earthquake catalogue data from Japan and Chile, that a set of 60 seismic statistical features (SSFs) had much greater predictive value than a set of 428 generic time series features from the tsfresh package. We here extend this previous work in two key ways, focusing on data from Japan as a large dataset is necessary in order to allow for the training of a deep learning (autoencoder) model. First, we move from whole-region prediction (considering, for each candidate event, the likelihood of an event M $\geq$ 5.0 anywhere in the region in the next 15 days) to localised predictions in which both the region of feature computation and the region of prediction are restricted to a circle of radius 24 km around the candidate event, and we show that performance remains excellent, similar to our previous whole-region study for the same area. Second, we here couple this proven set of SSFs, based on one-dimensional (catalogue) data, with a novel feature based on two-dimensional seismic maps, obtained by training a VQ-VAE model to reproduce such maps as output and identifying a measure of its error in doing so with a localised build-up of crustal stress. We show that while localised prediction based on SSFs can be effective alone, with test AUC values as high as those obtained in the case of Japan in our previous whole-region study, the inclusion of the new natively-spatial VQ-VAE-derived feature, top-ranked by SHAP analysis, can enhance performance and additionally appears to near-wholly replace the traditionally-computed $b$-value in terms of feature usage.
Abstract:In this paper we build upon a previous study in which we demonstrated, using XGBoost and earthquake catalogue data from Japan and Chile, that a set of 60 seismic statistical features (SSFs) had much greater predictive value than a set of 428 generic time series features from the tsfresh package. We here extend this previous work in two key ways, focusing on data from Japan as a large dataset is necessary in order to allow for the training of a deep learning (autoencoder) model. First, we move from whole-region prediction (considering, for each candidate event, the likelihood of an event M $\geq$ 5.0 anywhere in the region in the next 15 days) to localised predictions in which both the region of feature computation and the region of prediction are restricted to a circle of radius 24 km around the candidate event, and we show that performance remains excellent, similar to our previous whole-region study for the same area. Second, we here couple this proven set of SSFs, based on one-dimensional (catalogue) data, with a novel feature based on two-dimensional seismic maps, obtained by training a VQ-VAE model to reproduce such maps as output and identifying a measure of its error in doing so with a localised build-up of crustal stress. We show that while localised prediction based on SSFs can be effective alone, with test AUC values as high as those obtained in the case of Japan in our previous whole-region study, the inclusion of the new natively-spatial VQ-VAE-derived feature, top-ranked by SHAP analysis, can enhance performance and additionally appears to near-wholly replace the traditionally-computed $b$-value in terms of feature usage.
Machine Learning (cs.LG); Geophysics (physics.geo-ph)
arXiv:2606.10069 [cs.LG]
(or arXiv:2606.10069v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2606.10069 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 367 cuvinte
Subiecte conexe
SAGE-XGBoost: Spatially Augmented Graph Embeddings--Machine Learning Framework for Natural Hazards Susceptibility Mapping under Data Scarcity
arXiv · 21 aug. 2026
Using Seismic Statistical Features and VQ-VAE to Improve Spatiotemporal Seismicity Predictability
arXiv · 4 aug. 2026
TrajGenAgent: A Hierarchical LLM Agent for Human Mobility Trajectory Generation
arXiv · 12 iun. 2026
Siam-ALS: An Explainable Siamese Deep Learning Framework for Early ALS Detection Using EEG and Eye-Tracking Signals
arXiv · 15 oct. 2026