Journal of Korea Society of Industrial Information Systems (한국산업정보학회논문지)

Korea Society of Industrial Information Systems (한국산업정보학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on the Real-Time Risk Analysis of Heavy-Snow according to the Characteristics of Traffic and Area

교통과 지역의 특성에 따른 대설의 실시간 피해 위험도 분석 연구

  • KwangRim, Ha ;
  • YongCheol, Jung ;
  • JinYoung, Yoo ;
  • JunHee, Lee
  • 하광림 ((주)씨에스리 AI엔지니어링사업부) ;
  • 정용철 ((주)씨에스리 데이터엔지니어링팀) ;
  • 유진영 ((주)씨에스리 데이터엔지니어링팀) ;
  • 이준희 ((주)씨에스리 데이터엔지니어링팀)
  • Received : 2022.10.14
  • Accepted : 2022.12.21
  • Published : 2022.12.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, we present an algorithm that analyzes the risk by reflecting regional characteristics for factors affected by direct and indirect damage from heavy-snow. Factors affected by heavy-snow damage by 29 regions are selected as influencing variables, and the concept of sensitivity is derived through the relationship with the amount of damage. A snow damage risk prediction model was developed using a machine learning (XGBoost) algorithm by setting weather conditions (snow cover, humidity, temperature) and sensitivity as independent variables, and setting the risk derived according to changes in the independent variables as dependent variables.

본 연구에서 대설의 직접, 간접적인 피해에 영향받는 요소들에 대해 지역적 특성을 반영해 위험도를 분석하는 알고리즘을 제시한다. 229개의 지역별로 대설피해의 영향을 받는 요소들을 영향변수로 선정하고 피해액과의 관계를 통해 민감도라는 개념을 도출한다. 기상 상태(적설량, 습도, 기온)와 민감도를 독립 변수로 설정하고 독립 변수의 변화에 따라 도출된 위험도를 종속변수로 설정해 머신러닝(XGBoost) 알고리즘을 이용한 대설피해 위험도 예측 모델을 개발했다.

Keywords

Acknowledgement

본 연구는 행정안전부 재난 안전 취약핵심역량 도약기술개발사업(2020-MOIS33-006)의 지원을 받아 수행되었음.

References

  1. Cheon (2017). A study on changes of disaster area caused by heavy snowfall and classification of the disaster in South Korea. Thesis, Graduate School of Konkuk University. Seoul, Korea.
  2. Gyeongbuk Male. (2016). Snowbomb Ulleung Mountain Area, Still Isolated, http://www.kbmaeil.com/news/articleView.html?idxno=374114 (Accessed on Jau. 27th, 2016)
  3. Ha. (2021). A Study on the Typhoon Damage Risk Level Prediction Model using Local Sensitivity, Graduate School of Seoul National University of Science and Technology. Seoul, Korea.
  4. Kim et al, (2015). Influence Factors Suggestion and Prediction Model Development of Regional Building Damage Costs according to Typhoon. Journal of the Korea Institute of Building Construction. https://doi.org/10.5345/JKIBC.2015.15.5.515
  5. Kim, et al, (2018). The Study for Damage Effect Factors of Heavy Snowfall Disasters : Focused on Heavy Snowfall Disasters during the Period of 2005 to 2014. Journal of the Korea Academia-Industrial cooperation Society Vol. 19, No. 2 pp. 125-136.
  6. Kwon, et al, (2016). Analysis of Snow Vulnerability and Adaptation Policy for Heavy Snow. J. Korean Soc. Hazard Mitig.Vol. 16, No. 2 (Apr. 2016), pp. 363~368.
  7. Lee & Chung (2018). Measures to Respond to the Cost of Traffic Congestion Caused by Heavy. Thesis, Graduate School of Hoseo University. Asan, Korea.
  8. Moon & Kim. (2018). Economic Loss Assessment caused by Heavy Snowfall, Journal of Korea Planning Association, 53(6), 117-130. https://doi.org/10.17208/jkpa.2018.11.53.6.117
  9. News 1. (2016). "Will the nightmare of heavy snow 11 years ago come back to life?" Gochang-gun is nervous, \https://www.news1.kr/, (Accessed on Jau. 24th, 2016)
  10. Oh. Y. R. (2017). Estimate of Snow Damage using Snow Damage Vulnerability Analysis in South Korea. Thesis, Graduate School of Hoseo University. Asan, Korea.
  11. Oh & Chung (2017). Estimation of Snow Damage and Proposal of Snow Damage Threshold based on Historical Disaster Data, Journal of the Korea Society of Civil Engineers, 37(2), 325-331. https://doi.org/10.12652/Ksce.2017.37.2.0325
  12. YTN (2018). The traffic jam... Accidents everywhere, https://www.ytn.co.kr/, (Accessed on Nov. 24th, 2018)