POSEIDON: Physics-Optimized Seismic Energy Inference and Detection Operating Network

2026-01-05

arXiv.org

AI Summary

This work proposes a unified multi-task energy-based model that integrates seismological physical laws to address the limitations of existing machine learning approaches in earthquake forecasting and hazard assessment—namely, their disregard for physical principles and poor interpretability. For the first time, the Gutenberg-Richter law and the Omori-Utsu aftershock decay law are incorporated as learnable constraints within a physics-informed energy modeling framework. Leveraging precomputed seismic energy features, spatial grid indexing, and normalized quality metrics, the model simultaneously performs aftershock sequence identification, tsunami generation potential estimation, and foreshock detection. Experimental results demonstrate state-of-the-art performance across all tasks, with F1 scores significantly outperforming baseline methods such as gradient boosting, random forests, and convolutional neural networks, while the learned physical parameters remain scientifically interpretable.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Relational Probabilistic Models
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Earthquake prediction and seismic hazard assessment remain fundamental challenges in geophysics, with existing machine learning approaches often operating as black boxes that ignore established physical laws. We introduce POSEIDON (Physics-Optimized Seismic Energy Inference and Detection Operating Network), a physics-informed energy-based model for unified multi-task seismic event prediction, alongside the Poseidon dataset -- the largest open-source global earthquake catalog comprising 2.8 million events spanning 30 years. POSEIDON embeds fundamental seismological principles, including the Gutenberg-Richter magnitude-frequency relationship and Omori-Utsu aftershock decay law, as learnable constraints within an energy-based modeling framework. The architecture simultaneously addresses three interconnected prediction tasks: aftershock sequence identification, tsunami generation potential, and foreshock detection. Extensive experiments demonstrate that POSEIDON achieves state-of-the-art performance across all tasks, outperforming gradient boosting, random forest, and CNN baselines with the highest average F1 score among all compared methods. Crucially, the learned physics parameters converge to scientifically interpretable values -- Gutenberg-Richter b-value of 0.752 and Omori-Utsu parameters p=0.835, c=0.1948 days -- falling within established seismological ranges while enhancing rather than compromising predictive accuracy. The Poseidon dataset is publicly available at https://huggingface.co/datasets/BorisKriuk/Poseidon, providing pre-computed energy features, spatial grid indices, and standardized quality metrics to advance physics-informed seismic research.

Problem

• earthquake prediction
• seismic hazard assessment
• physics-informed modeling
• aftershock prediction
• foreshock detection

Innovation

• physics-informed modeling
• energy-based model
• seismic event prediction
• Gutenberg-Richter law
• Omori-Utsu law