Post-Event GM Estimation Using GNNs - Data

Relevant data for the journal paper "Post-Event Ground Motion Estimation Using Graph Neural Networks"<b>Paper Abstract</b>Accurate ground motion estimates are essential for forensic analysis of structural damage following major earthquakes when direct recordings at the location(s) of interest are unavailable. Contemporary post-event ground motion estimation methods often leverage nearby observations to constrain estimates of intensity measures (IMs); however, existing approaches rely on empirical ground-motion models with well-known limitations in capturing spatial dependencies. This study introduces a graph neural network (GNN) approach for estimating ground-motion IMs, leveraging a graph-based representation to naturally encode spatial dependencies and allow for different observation types. Applied to a New Zealand case study, the GNN achieves performance comparable to the established multivariate normal conditional IM method, while learning spatial correlations directly from the data. Athough the proof-of-concept illustration does not yet surpass existing methods, the results demonstrate the viability of GNNs for post-event GM estimation. Continued improvements in model architecture and increased data availability are expected to further enhance performance and applicability.

期刊论文《基于图神经网络的震后地震动估算》的相关数据**论文摘要**：当目标地点无法获取直接地震观测记录时，精准的地震动估算结果对于大地震后结构损伤的溯源分析至关重要。当前主流的震后地震动估算方法通常借助邻近台站的观测数据来约束强度度量（Intensity Measures, IM）的估算结果，但现有方法依赖经验地震动模型，这类模型在捕捉空间相关性方面存在公认的局限性。本研究提出了一种用于估算地震动强度度量的图神经网络（Graph Neural Network, GNN）方法，该方法通过基于图的表征方式自然编码空间相关性，同时支持兼容多种观测数据类型。在新西兰的案例研究中，该图神经网络的估算性能与成熟的多元正态条件强度度量方法相当，且可直接从数据中学习空间相关性。尽管本研究的概念验证示例尚未超越现有方法，但实验结果证明了图神经网络用于震后地震动估算的可行性。未来通过持续优化模型架构、扩充数据储备，有望进一步提升该方法的性能与应用范围。