Advanced Industrial SCIence (산업과 과학)

Convergence Society for SMB (중소기업융합학회)
권호 표지
DOI QR코드

DOI QR Code

Abnormal Weather Notification Method using SARIMA Model

SARIMA 모델을 사용한 이상기후 알림 방안

  • Shin-Hyeong Choi (Division of Electrical, Control & Instrumentation Engineering, Kangwon National University) ;
  • Choon-Soo Lee (Component Engineering Team, Korea Hydro-Nuclear Power Company)
  • 최신형 (강원대학교 전기제어계측공학부) ;
  • 이춘수 (한국수력원자력(주) 기기엔지니어링부)
  • Received : 2024.12.14
  • Accepted : 2025.01.20
  • Published : 2025.01.30
Download PDF
⟨ Previous Next ⟩

Abstract

Global warming is causing enormous damage to the Earth by causing natural disasters and environmental changes that are different from the past. Among the various factors that threaten human health, smog is a representative example of respiratory disease, and recent news reports show that many people are hospitalized with respiratory diseases due to extreme harmful smog. This study proposes a system that uses the SARIMA(Seasonal ARIMA) model to predict wind speed and direction and detects abnormal weather by comparing the predicted values with past averages. To this end, we collected wind direction and wind speed data for the past 10 years in Region G, and if the predicted values differ significantly from the past, we can use this to reduce casualties and respond by sending warnings to local residents via SNS or emergency disaster text messages.

지구온난화는 과거와 다른 자연재해 및 환경에 변화를 줌으로써 지구상에 막대한 피해를 주고 있다. 이와 같이 인간의 건강을 위협하는 여러 요인중에 호흡기 질환을 일으키는 것으로는 스모그가 대표적인 사례이며, 최근의 뉴스를 살펴보면, 극심한 유해 스모그로 인해 많은 사람이 호흡기 질환으로 입원한다는 보고가 있다. 본 연구는 SARIMA 모델을 사용하여 풍속 및 풍향을 예측하고, 예측된 값과 과거 평균값을 비교하여 이상기후를 감지하는 시스템을 제안한다. 이를 위해 G 지역의 10년간의 풍향, 풍속 데이터를 수집하였고, 예측된 값이 과거와 크게 달라질 경우, 해당 지역 주민들에게 SNS 또는 긴급재난문자를 통해 경고를 발송하여 인명 피해를 줄이고 대응할 수 있는데 활용할 수 있다.

Keywords

References

  1. COP16 Overview: Biodiversity Protection and the Oceans. Name of Site or Board. https://globalgreens.org/kor/cbd-brief-oceans/
  2. Park. H. K. (2018). Air pollution and climate change: Effects on asthmatic patients. Allergy Asthma Respir Dis, 6(2), 79-84. DOI : 10.4168/aard.2018.6.2.79
  3. Jung. Y. J. (2023). A Study on Changes in Disease Patterns and Countermeasures due to Global Warming. Jour. of KoCon.a, 23(8), 426-438. DOI : 10.5392/JKCA.2023.23.08.426
  4. Jang. J. Y. (2009). Climate change, global warming's impact on human health. Horizon of knowledge, 6, 159-175.
  5. Cho H. M. (2012). Climate change and air pollution effect on respiratory and allergic disease in Korea. Korea Centers for Disease Control and Prevention, 1-7.
  6. Erasmo. C. & Wilfrido. R. (2007). Wind speed forecasting in the South Coast of Oaxaca, Mexico. Renewable Energy, 32(12), 2116-2128. DOI : 10.1016/j.renene.2006.10.005
  7. Cadenas, E., Jaramillo, O. A., & Rivera, W. (2010). Analysis and forecasting of wind velocity in chetumal, quintana roo, using the single exponential smoothing method. Renewable Energy, 35(5), 925-930. DOI : 10.1016/j.renene.2009.10.037
  8. Jeong. C. S., Kim. M. M. & Heo. J. H. (2008). Analysis of Climate Change using Stochastical Methods (based on precipitation data). 2008 Korea Water Resources Association, 1001-1006.
  9. Song. K. Y., Bang. C. H., Park. Y. S. & Choi. Y. J. (2012). Research and Analysis for Developing of Evaluation on the Site Selection of Wind Farm. Journal of the Wind Engineering Institute of Korea, 16(1), 3-12.
  10. Saurabh. S. S., Hamidreza. Z., Om. M. & Paras. M. (2010). A review of wind power and wind speed forecasting methods with different time horizons. North American Power Symposium 2010, 1-8. DOI : 10.1109/NAPS.2010.5619586.
  11. Choi. S. H. (2024). A Study on Trend Using Time Series Data. Advanced Industrial SCIence, 3(1). 17-22. DOI : 10.23153/AI-Science.2024.3.1.017
  12. Han, K. H., & Na, W. S. (2024). Forecasting Prices of Major Agricultural Products by Temperature and Precipitation. Journal of Advanced Technology Convergence, 3(2), 17-23. DOI : 10.23152/JATC.2024.03.02.017
  13. Lee, J., Han, H., & Yoon, S. (2020). Air passenger demand forecasting for the Incheon airport using time series models. Journal of Digital Convergence, 18(12), 87-95. DOI : 10.14400/JDC.2020.18.12.087
  14. Choudhary, A., Jain, P., & Prajesh, A. (2023, February). Wind Power Forecasting Using Deep Learning Method: A Review. In 2023 1st International Conference on Intelligent Computing and Research Trends (ICRT) (pp. 1-6). IEEE. DOI : 10.1109/ICRT57042.2023.10146688
  15. Liu, X., Lin, Z., & Feng, Z. (2021). Short-term offshore wind speed forecast by seasonal ARIMA-A comparison against GRU and LSTM. Energy, 227, 120492. DOI : 10.1016/j.energy.2021.120492