Prediction of Heat Wave based on LSTM Considering Urban-social Characteristics of Busan

KangMinHee; Hyungkyoo Kim

doi:10.15793/kspr.2021.109..002

The heat wave, which was first designated as a natural disaster in 2018 and causes casualties and property damage due to temperature rises above a certain standard, is becoming more serious at domestic and abroad. In particular, Busan faces the need to establish strategies to cope with the heat wave for its largest number of thermal disease among all metropolitan areas of the Korean Peninsula. This study aims to provide foundations for establishing heat wave strategies by using LSTM techniques, an artificial intelligence (AI) methodology, to reflect the urban-social characteristics of Busan. LSTM optimization analysis results show higher accuracy than conventional regression models and ensemble models, identified by MAE 0,139 and MSE 0.128. In addition, we perform a feature importance analysis to examine the effects of the utilized variables, and the results showed that the temperature-related variables had the highest impact. Significance of this study is found in predicting heat waves by reflecting the urban-social characteristics of Busan beyond simply utilizing climate data through AI methodology. It is expected that heat waves would be more accurately predicted by supplementing future data, adding variables, and improving models.

Citation status

KCI Citation Counts (2)
열림/닫힘 버튼
REFERENCES (44)
열림/닫힘 버튼
* 2021년 이후 발행 논문의 참고문헌은 현재 구축 중입니다.

[web] / e-나라지표 / http://www.index.go.kr

[confproc] 강미선 / 2018 / 한국주요도시의 폭염에 의한 사망률 평가 / 2018년 한국기상학회 가을학술대회논문집 196

[journal] 강윤희 / 2019 / Spatial-temporal variations in surface ozone concentrations in Busan metropolitan area / 한국환경과학회지 / 한국환경과학회 28(2) : 169~182 / https://doi.org/10.5322/JESI.2019.28.2.169

[other] 광주지방기상청 / 2018 / 1994년과 비교한 2018년 폭염특성 / 보도자료

[journal] 구유성 / 2015 / Study on the Improvement of Adaptation Ability by Vulnerability Analysis of Heat Wave - the Case of Busan Metropolitan City / 한국지역개발학회지 / 한국지역개발학회 27(5) : 331~348

[web] / 국립재난안전연구원 / http://www.ndmi.go.kr

[web] / 국립해양조사원 / http://www.khoa.go.kr

[journal] 권용석 / 2020 / Political Effects of Countermeasures Against Heat Wave Using System Dynamics Method: Case Study in Daegu Metropolitan City / 국토연구 / 국토연구원 106 : 41~64 / 10.15793/kspr.2020.106..003

[web] / 기상청 기상자료개방 포털 / http://data.kma.go.kr

[journal] 김기욱 / 2020 / Assessment of Heat Wave Vulnerability in Busan Using the IPCC Climate Change Vulnerability Assessment Framework / 국토연구 / 국토연구원 104 : 23~38 / 10.15793/kspr.2020.104..002

[journal] 김영인 / 2020 / Prediction of Temperature and Heat Wave Occurrence for Summer Season Using Machine Learning / 한국방재안전학회논문집 / 한국방재안전학회 13(2) : 27~38

[confproc] 김예슬 / 2020 / 인공신경망을 활용한 폭염 취약성 예측 모델 개발: 대구광역시를 사례로 / 한국생태환경건축학회 학술발표대회 논문집 20(1) : 132~133

[journal] 김인겸 / 2020 / Evaluating Economic Value of Heat Wave Watch/Warning Information in Seoul and Busan in 2016: Focused on a Cost of Heat Wave Action Plan and Sample of Patients / 한국콘텐츠학회 논문지 / 한국콘텐츠학회 20(5) : 525~535 / https://doi.org/10.5392/JKCA.2020.20.05.525

[journal] 김효진 / 2019 / 기후변화, 그로인한 도시폭염과 미세먼지에 대응한 안전사회 구축방안 / 법연 / 한국법제연구원 (63)

[journal] 배민기 / 2020 / Analysis on the Spatial Relationship between the Residential Area of the Vulnerable Groups and the Hazardous Area during the Heat Wave / 환경정책 / 한국환경정책학회 28(3) : 243~280 / 10.15301/jepa.2020.28.3.243

[confproc] 서양모 / 2019 / 기상 데이터를 활용한 LSTM 기반 미세먼지 농도 예측 방법 비교 / 2019 한국측량학회 학술대회자료집 : 117~120

[journal] 성지훈 / 2020 / A Study on Identification of the Heat Vulnerability Area Considering Spatial Autocorrelation – Case Study in Daegu / 한국측량학회지 / 한국측량학회 38(4) : 295~304 / https://doi.org/10.7848/ksgpc.2020.38.4.295

[report] 송교욱 / 2012 / 기후변화 본격화로 폭염· 폭우· 폭풍에 대한적응 필요 / 부산발전연구원

[web] / 에어코리아 / http://www.airkorea.or.kr

[journal] 오규식 / 2005 / The Relationship between Urban Spatial Elements and the Urban Heat Island Effect / 도시설계 / 한국도시설계학회 6(1) : 47~63

[journal] 이수미 / 2019 / A Study on the Influence of Urban Environment on the Generation of Thermal Diseases / 한국콘텐츠학회 논문지 / 한국콘텐츠학회 19(12) : 84~92 / https://doi.org/10.5392/JKCA.2019.19.12.084

[journal] 이홍석 / 2020 / A Deep Learning LSTM Framework for Urban Traffic Flow and Fine Dust Prediction / 정보과학회논문지 / 한국정보과학회 47(3) : 292~297 / https://doi.org/10.5626/JOK.2020.47.3.292

[journal] 이희동 / 2020 / Characteristics and Comparison of 2016 and 2018 Heat Wave in Korea / 대기 / 한국기상학회 30(1) : 1~15 / 10.14191/Atmos.2020.30.1.001

[journal] 제민희 / 2018 / Urban Heat Island Intensity Analysis by Landuse Types / 한국콘텐츠학회 논문지 / 한국콘텐츠학회 18(11) : 1~12 / https://doi.org/10.5392/JKCA.2018.18.11.001

[report] 조진희 / 2018 / 미시적 도시공간의 폭염취약지역분석을 통한 정책적 대응방안 / 충북연구원

[journal] 조희선 / 2014 / Effects of the Urban Spatial Characteristics on Urban Heat Island / 환경정책 / 한국환경정책학회 22(2) : 27~43 / http://dx.doi.org/10.15301/jepa.2014.22.2.27

[web] / 질병관리청 / http://www.kdca.go.kr

[web] / 통계청 / http://kostat.go.kr

[report] 한국환경정책·평가연구원 기후변화리스크연구단 / 2020 / 2020 폭염영향 보고서 / 한국환경정책‧평가연구원

[confproc] 함유근 / 2016 / 폭염과 여름철 한반도 연근해 해수면변동간의 관련성 연구 / 2016 한국기상학회 가을학술대회 논문집 : 433~434

[journal] 허솔잎 / 2019 / An Assessment of Applicability of Heat Waves Using Extreme Forecast Index in KMA Climate Prediction System (GloSea5) / 대기 / 한국기상학회 29(3) : 257~267 / 10.14191/Atmos.2019.29.3.257

[journal] Coutts, A. M. / 2008 / Investigating the climatic impact of urban planning strategies through the use of regional climate modeling / International Journal of Climatology 28(14) : 1943~1957 / 10.1002/joc.1680

[journal] Bauer, P. / 2015 / The quiet revolution of numerical weather prediction / Nature 525(7567) : 47~55

[other] Kingma, D. P / 2014 / Adam: A method for stochastic optimization / arXiv preprint arXiv:1412.6980

[journal] Dodla, V. B. / 2017 / Analysis and prediction of a catastrophic Indian coastal heat wave of 2015 / Natural Hazards 87(1) : 395~414

[journal] Hajat, S / 2010 / Heat-related mortality: a review and exploration of heterogeneity / Journal of Epidemiology & Community Health 64(9) : 753~760 / 10.1136/jech.2009.087999

[journal] Hochreiter, S / 1997 / Long short-term memory / Neural Computation 9(8) : 1735~1780

[journal] Khan, N. / 2019 / Prediction of heat waves in Pakistan using quantile regression forests / Atmospheric Research 221 : 1~11 / https://doi.org/10.1016/j.atmosres.2019.01.024

[journal] Kim Do-Woo / 2019 / Weekly heat wave death prediction model using zero-inflated regression approach / Theoretical and Applied Climatology 137(1-2) : 823~838

[journal] Mandal, R. / 2019 / Real time extended range prediction of heat waves over India / Scientific Reports 9(1) : 1~11

[confproc] Nair, V / 2010 / Rectified linear units improve restricted boltzmann machi / Proceedings of the 27th International Conference on Machine Learning (ICML-10) : 807~814

[journal] Park Minsoo / 2020 / Heatwave damage prediction using random forest model in Korea / Applied Sciences 10(22) : 8237~ / 10.3390/app10228237

[journal] Singh, H. / 2017 / Verification of pre-monsoon temperature forecasts over India during 2016 with a focus on heatwave prediction / Natural Hazards & Earth System Sciences 17(9) : 1469~1485 / 10.5194/nhess-17-1469-2017

[report] World Economic Forum / 2020 / The Global Risks Report / World Economic Forum

KJC Korea
Journal Central

Statistics

Tools

Sharing

Issue List

Citation status