The Seismic Wavefield Common Task Framework

2025-12-22

AI Summary

Seismology faces fundamental challenges in seismic wavefield prediction, reconstruction, and source/medium parameter modeling—including massive simulation requirements, sparse real-world observations, and oversimplified physical models. Existing machine learning (ML) approaches suffer from inconsistent feature engineering, nonstandardized evaluation protocols, and a lack of benchmark datasets. To address these issues, we propose the Common Task Framework (CTF) for seismic wavefields: a unified task-oriented framework that introduces three standardized, multi-scale datasets—global, crustal, and local—and formally defines core tasks (prediction, reconstruction, generalization) with task-specific metrics and hidden test sets. CTF integrates multi-scale physics-based simulations and real seismic network data, unifying foundational models (e.g., Waveform Transformer), classical inversion methods, and modern ML algorithms. It adopts rigorous robustness assessment and cross-dataset generalization evaluation. Initial benchmarking on two established benchmarks reveals performance boundaries and domain-specific applicability of diverse methods, advancing seismological ML toward reproducible, verifiable scientific evaluation.

Technology Category

• Machine Learning: Semi-Supervised Learning
• Search and Optimization: Metareasoning and Metaheuristics
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Machine learning and data science for the Web

Abstract

Seismology faces fundamental challenges in state forecasting and reconstruction (e.g., earthquake early warning and ground motion prediction) and managing the parametric variability of source locations, mechanisms, and Earth models (e.g., subsurface structure and topography effects). Addressing these with simulations is hindered by their massive scale, both in synthetic data volumes and numerical complexity, while real-data efforts are constrained by models that inadequately reflect the Earth's complexity and by sparse sensor measurements from the field. Recent machine learning (ML) efforts offer promise, but progress is obscured by a lack of proper characterization, fair reporting, and rigorous comparisons. To address this, we introduce a Common Task Framework (CTF) for ML for seismic wavefields, starting with three distinct wavefield datasets. Our CTF features a curated set of datasets at various scales (global, crustal, and local) and task-specific metrics spanning forecasting, reconstruction, and generalization under realistic constraints such as noise and limited data. Inspired by CTFs in fields like natural language processing, this framework provides a structured and rigorous foundation for head-to-head algorithm evaluation. We illustrate the evaluation procedure with scores reported for two of the datasets, showcasing the performance of various methods and foundation models for reconstructing seismic wavefields from both simulated and real-world sensor measurements. The CTF scores reveal the strengths, limitations, and suitability for specific problem classes. Our vision is to replace ad hoc comparisons with standardized evaluations on hidden test sets, raising the bar for rigor and reproducibility in scientific ML.

Problem

• Addresses seismic forecasting and reconstruction challenges
• Manages variability in earthquake sources and Earth models
• Standardizes ML evaluation for seismic wavefield tasks

Innovation

• Introduces Common Task Framework for seismic wavefield ML
• Provides curated multi-scale datasets with task-specific metrics
• Enables standardized algorithm evaluation on hidden test sets