Detecting Spatiotemporal b-Value Anomalies with a Progressive Deep Learning Architecture

TL;DR

This paper introduces a deep learning framework for detecting spatiotemporal anomalies in seismicity, specifically in the Japanese subduction zone, to predict large earthquakes using evolving b-value fields and a progressive training scheme.

Contribution

It presents a novel hybrid deep learning architecture combined with a progressive training method for real-time seismic anomaly detection.

Findings

Effective detection of earthquake precursors demonstrated

Hybrid model captures spatial and temporal seismic patterns

Progressive training improves model robustness

Abstract

Identifying systematic patterns in seismicity that precede large earthquakes remains a central challenge in statistical seismology. In this work, we present a methodological framework for detecting spatiotemporal anomalies in seismicity using the evolution of gridded b-values. Focusing on the Japanese subduction zone, we construct daily b-value fields on a fine spatial grid by aggregating local seismicity over moving time windows, yielding a continuous 2+1D representation of seismic-state evolution. We formulate the problem as a binary classification task in which spatiotemporal blocks extracted from these $b$-value fields are labeled according to the occurrence of a target earthquake with \Mw $\geq 5$ in the central region within the next day. To model this data, we introduce a hybrid deep-learning architecture that combines a spatial convolutional encoder with a temporal convolutional network, enabling joint learning of spatial structure and temporal dynamics. A progressive meta-epoch training scheme is employed, in which the model is iteratively updated using a time-forward strategy that mirrors operational deployment and mitigates issues related to nonstationarity. This paper is strictly methodological in scope. It describes the construction of b-value fields, the spatiotemporal sampling strategy, the network architecture, and the progressive training and internal validation framework used for model development and parameter selection.