Forecasting future earthquakes with deep neural networks: application to California
Geophysical Journal International · 08.11.2024 · 240 (1) · 81-95
DOI: 10.1093/gji/ggae373 ↗Kurz gefasst
Fachartikel in der Zeitschrift Geophysical Journal International, online erschienen am 18.10.2024. Verfasst von Ying Zhang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Shenzhen Science and Technology Innovation Commission, Southern University of Science and Technology.
Abstract (Originalsprache)
We use the spatial map of the logarithm of past estimated released earthquake energies as input of fully convolutional networks (FCN) to forecast future earthquakes. This model is applied to California and compared with an elaborated version of the epidemic type aftershock sequence (ETAS) model. Our long-term earthquake forecast simulations show that the FCN model is close to the ETAS model in forecasting earthquakes with $M \ge 3.0,\,\,4.0,\,\,{\rm{and\,\,}}5.0$ according to the Molchan diagram. Moreover, training and implementing the FCN model is 2000–4000 times faster than calibrating the ETAS model and generating its probabilistic forecasts. The FCN model is straightforward in terms of its neural network structure and feature engineering. It does not require extensive knowledge of statistical seismology or the analysis of earthquake catalogue completeness. Using the earthquake catalogue with $M \ge 0$ as FCN input can enhance the model's performance in some time–magnitude forecasting windows.
Förderung
- National Natural Science Foundation of China
- Shenzhen Science and Technology Innovation Commission
- Southern University of Science and Technology
Zitieren
APA
Zhang, Y., Zhan, C., Huang, Q., & Sornette, D. (2024). Forecasting future earthquakes with deep neural networks: application to California. Geophysical Journal International, 240(1), 81-95. https://doi.org/10.1093/gji/ggae373
Vancouver
Zhang Y, Zhan C, Huang Q, Sornette D. Forecasting future earthquakes with deep neural networks: application to California. Geophysical Journal International. 2024;240(1):81-95. doi:10.1093/gji/ggae373
BibTeX
@article{Zhang2024,
author = {Zhang, Ying and Zhan, Chengxiang and Huang, Qinghua and Sornette, Didier},
title = {Forecasting future earthquakes with deep neural networks: application to California},
journal = {Geophysical Journal International},
year = {2024},
volume = {240},
number = {1},
pages = {81--95},
doi = {10.1093/gji/ggae373}
}
EUVIMED