Spatiotemporal Magnitude Classification: A New Approach Using a Graph Convolution LSTM Model
Environmetrics · 2026-05 · 37 (4)
DOI: 10.1002/env.70094 ↗Kurz gefasst
Fachartikel in der Zeitschrift Environmetrics, online erschienen am 27.04.2026. Verfasst von Orietta Nicolis und 2 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Gefördert von: Fondo Nacional de Desarrollo Científico y Tecnológico.
Abstract (Originalsprache)
Earthquake prediction remains one of the most challenging tasks in natural hazard research due to the complexity and heterogeneity of seismic processes in space and time. To address this, we propose a deep learning (DL) framework based on graph convolutional and recurrent neural networks (RNNs) to forecast the maximum seismic magnitude in different regions of Chile. Using a cleaned and spatially segmented catalog of seismic events, we construct a graph where each node represents a seismic cluster derived from K‐means clustering, with edges reflecting spatial proximity. Two models are evaluated: a standard Long Short‐Term Memory (LSTM) network and a hybrid Graph Convolutional Network‐LSTM (GCN‐LSTM), which incorporates both temporal dynamics and spatial dependencies. Our results show that the GCN‐LSTM model significantly outperforms the simple LSTM in terms of F1‐score and recall, especially in regions with complex seismic activity. This demonstrates the advantage of graph‐based neural models in capturing spatial correlations and improving earthquake magnitude prediction at a regional scale.
Förderung
- Fondo Nacional de Desarrollo Científico y Tecnológico
Zitieren
APA
Nicolis, O., Riveros, A., & Peralta, B. (2026). Spatiotemporal Magnitude Classification: A New Approach Using a Graph Convolution LSTM Model. Environmetrics, 37(4). https://doi.org/10.1002/env.70094
Vancouver
Nicolis O, Riveros A, Peralta B. Spatiotemporal Magnitude Classification: A New Approach Using a Graph Convolution LSTM Model. Environmetrics. 2026;37(4). doi:10.1002/env.70094
BibTeX
@article{Nicolis2026,
author = {Nicolis, Orietta and Riveros, Alonso and Peralta, Billy},
title = {Spatiotemporal Magnitude Classification: A New Approach Using a Graph Convolution LSTM Model},
journal = {Environmetrics},
year = {2026},
volume = {37},
number = {4},
doi = {10.1002/env.70094}
}
EUVIMED