Preprint Article Version 1 This version not peer reviewed

Assessment of Building Damage Risk by Natural Disasters in South Korea Using Decision Tree Analysis

Version 1 : Received: 12 February 2018 / Approved: 12 February 2018 / Online: 12 February 2018 (11:13:37 CET)

How to cite: Kim, K.; Yoon, S. Assessment of Building Damage Risk by Natural Disasters in South Korea Using Decision Tree Analysis. Preprints 2018, 2018020087 (doi: 10.20944/preprints201802.0087.v1). Kim, K.; Yoon, S. Assessment of Building Damage Risk by Natural Disasters in South Korea Using Decision Tree Analysis. Preprints 2018, 2018020087 (doi: 10.20944/preprints201802.0087.v1).

Abstract

Changes in extreme weather patterns are expected under climate change. In this study, a risk assessment was conducted using 4 building damage history datasets and 33 weather datasets (precipitation, wind speed, snow, and temperature) from 230 regions in South Korea to quantitatively analyze and predict building damage caused by potential future natural disasters. Decision tree analysis was used to evaluate building damage risk in 230 regions. The decision tree model to determine the risk of flood, gale, and typhoon was generated, which excluded gales, with less damage. The weight (variable importance) and limit value (damage limit) of the weather variables ware derived using the decision tree model. Using these two factors, we assessed the building damage risk in 230 regions in South Korea until 2100. The number of regions at risk of flood damage increased by more than 30% in average. Conversely, regions at risk of snowfall damage decreased by more than 90%. The regions at risk of typhoons decreased by 57.5% on average, and the number of regions at high risk of typhoon damage increased by up to 62.5% in RCP 8.5. These results can be used as objective data to minimize future building damage throughout South Korea, representing the first step towards sustainable development in the region with respect to disaster response.

Subject Areas

building damage; climate change scenarios; decision tree analysis; limit value; natural disaster; random forest; risk assessment process; South Korea

Readers' Comments and Ratings (0)

Leave a public comment
Send a private comment to the author(s)
Rate this article
Views 0
Downloads 0
Comments 0
Metrics 0
Leave a public comment

×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.