STFT-LDA: An Algorithm to Facilitate the Visual Analysis of Building Seismic Responses

TL;DR

This paper introduces STFT-LDA, a novel method using topic modeling to analyze and compare complex seismic response time series from building simulations, aiding civil engineers in understanding structural failures.

Contribution

The paper presents a new technique that transforms seismic response data into interpretable topics, facilitating multiscale analysis and visual comparison of building responses to earthquakes.

Findings

Enables easier identification of recurring seismic patterns.

Supports querying and comparing earthquake responses across time scales.

Improves visual analysis through an integrated prototype system.

Abstract

Civil engineers use numerical simulations of a building's responses to seismic forces to understand the nature of building failures, the limitations of building codes, and how to determine the latter to prevent the former. Such simulations generate large ensembles of multivariate, multiattribute time series. Comprehensive understanding of this data requires techniques that support the multivariate nature of the time series and can compare behaviors that are both periodic and non-periodic across multiple time scales and multiple time series themselves. In this paper, we present a novel technique to extract such patterns from time series generated from simulations of seismic responses. The core of our approach is the use of topic modeling, where topics correspond to interpretable and discriminative features of the earthquakes. We transform the raw time series data into a time series of topics, and use this visual summary to compare temporal patterns in earthquakes, query earthquakes via the topics across arbitrary time scales, and enable details on demand by linking the topic visualization with the original earthquake data. We show, through a surrogate task and an expert study, that this technique allows analysts to more easily identify recurring patterns in such time series. By integrating this technique in a prototype system, we show how it enables novel forms of visual interaction.