Prioritizing ground‐motion validation metrics using semisupervised and supervised learning

Abstract

It has become common practice to validate ground‐motion simulations based on a variety of time and frequency metrics scaled to quantify the level of agreement between synthetics and data or other reference solutions. There is, however, no agreement about the importance or weight that it ought to be given to each metric. This leads to their selection often being subjective, either based on intended applications or personal preferences. As a consequence, it is difficult for simulators to identify what modeling improvements are needed, which would be easier if they could focus on a reduced number of metrics.

We present an analysis that looks into 11 ground‐motion validation metrics using semisupervised and supervised machine learning techniques. These techniques help label and classify goodness‐of‐fit results with the objective of prioritizing and narrowing the choice of these metrics. This work provides an objective framework for selecting the most informative validation metrics in earthquake ground motion simulation.

Key Contributions

• Objective Metric Selection: First systematic approach to prioritize ground-motion validation metrics using machine learning
• Machine Learning Framework: Application of both semisupervised and supervised learning techniques to seismological validation
• Comprehensive Analysis: Evaluation of 11 different ground-motion validation metrics
• Practical Guidelines: Provides simulators with focused set of metrics for model improvement
• Goodness-of-Fit Classification: Systematic labeling and classification of simulation quality

Methodology and Innovation

The research addresses a fundamental challenge in computational seismology by:

• Removing Subjectivity: Eliminates personal preference and application-specific bias in metric selection
• Machine Learning Integration: Applies advanced ML techniques to traditional seismological problems
• Systematic Validation: Provides framework for consistent evaluation across different simulation studies
• Model Improvement Guidance: Helps simulators identify specific areas needing improvement

Impact on Earthquake Engineering

This work has significant implications for:

• Simulation Quality Assessment: Standardized approach for evaluating ground motion simulations
• Model Development: Focused improvement strategies based on prioritized metrics
• Research Efficiency: Reduced computational and analytical burden through metric prioritization
• Community Standards: Foundation for establishing consensus validation protocols

Applications

The methodology enables:

• More efficient validation of physics-based ground motion simulations
• Objective comparison of different simulation approaches
• Focused development of improved seismic modeling techniques
• Enhanced reliability of earthquake hazard assessments

This interdisciplinary approach bridges machine learning, seismology, and earthquake engineering, contributing to more reliable and efficient earthquake ground motion simulation practices.

Recommended citation: Khoshnevis, N., & Taborda, R. (2018). Prioritizing ground‐motion validation metrics using semisupervised and supervised learning. Bulletin of the Seismological Society of America, 108(4), 2248-2264. https://doi.org/10.1785/0120180043
Download Paper