학술논문
Earthquake Damage Report Interactive Dashboard Using Bayesian Structural Time Series and Value-Suppressing Uncertainty Palettes
Document Type
Conference
Author
Source
2019 IEEE Conference on Visual Analytics Science and Technology (VAST) Visual Analytics Science and Technology (VAST), 2019 IEEE Conference on. :106-107 Oct, 2019
Subject
Language
Abstract
Earthquake Damage Report Interactive Dashboard addresses Mini Challenge 1 of VAST Challenge 2019. The project uses interactive visual analytics to report and summarize crowd-sourced damage reports temporally and spatially. We modelled the reports with Bayesian structural time series (BSTS) and encoded uncertainties in the reports visually with value-suppressing uncertainty palettes (VSUPs). The interactive visualization was developed with Vega and VueJS. We performed further analyses in Tableau. The dashboard and the challenge submission package can be found at https://vast2019.maxnadul.com.