Journal of the Korean Society for Aviation and Aeronautics (한국항공운항학회지)

The Korean Society for Aviation and Aeronautics (한국항공운항학회)
권호 표지
DOI QR코드

DOI QR Code

Prediction of Near-Surface Winds on Airport Runways Using Machine Learning

기계학습을 활용한 공항 활주로 지상 바람의 예측

  • Seung-Min Lee ;
  • Seung-Jae Lee ;
  • Harim Kang ;
  • Sook Jung Ham ;
  • Jae Ik Song ;
  • Ki Nam Kim
  • 이승민 (국가농림기상센터 연구개발부) ;
  • 이승재 (국가농림기상센터 연구개발부) ;
  • 강하림 (공군기상단) ;
  • 함숙정 (공군기상단) ;
  • 송재익 (공군기상단) ;
  • 김기남 (공군기상단)
  • Received : 2024.05.13
  • Accepted : 2024.05.30
  • Published : 2024.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

Wind forecast is one of the key meteorological factors required for safe aircraft takeoff and landing. In this study, we developed an artificial intelligence-based wind compensation method by learning the Korea Air Force Weather Research and Forecast (KAF-WRF) forecast data and the Airfield Meteorological Observation System (AMOS) data at five airports using Support Vector Machine (SVM). The SVM wind prediction models were composed of three types according to the learning period (30 days, 40 days, and 60 days) using seven KAF-WRF variables as training data, and the wind prediction performance at the five airports was evaluated using Root Mean Squared Errors (RMSE). According to the results, the SVM wind prediction model trained using U (east-west) and V (north-south) components performed approximately 18% better than the model trained using wind speed and wind direction. The wind correction of KAF-WRF with AMOS observations via SVM outperformed the conventional KAF-WRF wind predictions in eight out of ten cases, capturing abrupt changes in wind direction and speed with a 25% reduction in RMSE.

Keywords

Acknowledgement

본 연구는 공군기상단 연구개발 용역사업 '23-F-AI 기반 비행단 맞춤형 바람예보법 적용 연구'의 지원으로 수행되었습니다.

References

  1. Chaloulos, G., and Lygeros, J., "Effect of wind correlation on aircraft conflict probability", Journal of Guidance, Control, and Dynamics, 30(6), 2007, pp.1742-1752.
  2. Kim, S., "The impact of extreme weather events on flight delays & cancellations with a focus on Gimpo-Jeju air route", M.S. Thesis, Seoul National University, Seoul, 2021.
  3. El-Fouly, T. H. M., El-Saadany, E. F., and Salama, M. M. A., "One day ahead prediction of wind speed using annual trends", IEEE Power Engineering Society General Meeting, 2006, pp.1-7.
  4. Lei, M., Shiyan, L., Chuanwen, J., Hongling, L., and Yan, Z., "A review on the forecasting of wind speed and generated power", Renewable and Sustainable Energy Reviews, 13(4), 2009, pp.915-920.
  5. Santhosh, M., Venkaiah, C., and Vinod Kumar, D. M., "Current advances and approaches in wind speed and wind power forecasting for improved renewable energy integration: A review", Engineering Reports, 2(6), 2020, e12178.
  6. Wu, Z., Luo, G., Yang, Z., Guo, Y., Li, K., and Xue, Y., "A comprehensive review on deep learning approaches in wind forecasting applications", CAAI Transactions on Intelligence Technology, 7(2), 2022, pp.129-143.
  7. Kalnay, E., "Atmospheric modeling, data assimilation and predictability", Cambridge University Press, 2003, pp.18-19.
  8. Shukur, O. B., and Lee, M. H., "Daily wind speed forecasting through hybrid KF-ANN model based on ARIMA", Renewable Energy, 76, 2015, pp.637-647.
  9. Lydia, M., Kumar, S. S., Selvakumar, A. I., and Kumar, G. E. P., "Linear and non-linear autoregressive models for short-term wind speed forecasting", Energy Conversion and Management, 112, 2016, pp.115-124.
  10. Jeong, J., and Lee, S. J., "A statistical parameter correction technique for WRF mediumrange prediction of near-surface temperature and wind speed using generalized linear model", Atmosphere, 9(8), 2018, pp.291.
  11. Singh, S. N., and Mohapatra, A., "Repeated wavelet transform based ARIMA model for very short-term wind speed forecasting", Renewable Energy, 136, 2019, pp.758-768.
  12. Fattaheian-Dehkordi, S., Fereidunian, A., Gholami-Dehkordi, H., and Lesani, H., "Hour ahead demand forecasting in smart grid using support vector regression (SVR)", International Transactions on Electrical Energy Systems, 24(12), 2014, pp.1650-1663.
  13. Ali, M., Khan, A., and Rehman, N. U., "Hybrid multiscale wind speed forecasting based on variational mode decomposition", International Transactions on Electrical Energy Systems, 28(1), 2018, e2466.
  14. Kwon, S. Y., Lee, S. J., and Kim, M. I., "A Statistical correction of point time series data of the NCAM-LAMP medium-range prediction system using support vector machine", Korean Journal of Agricultural and Forest Meteorology, 23(4), 2021, pp.415-423.
  15. Shin, J. Y., Min, B., and Kim, K. R., "High-resolution wind speed forecast system coupling numerical weather prediction and machine learning for agricultural studies a case study from South Korea", International Journal of Biometeorology, 66(7), 2022, pp.1429-1443.
  16. Hu, Q., Zhang, R., and Zhou, Y., "Transfer learning for short-term wind speed prediction with deep neural networks", Renewable Energy, 85, 2016, pp.83-95.
  17. Araya, I. A., Valle, C., and Allende, H., "Lstm-based multi-scale model for wind speed forecasting", In Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications: 23rd Iberoamerican Congress, CIARP 2018, Madrid, Spain, 2019, Proceedings 23, pp.38-45.
  18. Yin, H., Ou, Z., Huang, S., and Meng, A., "A cascaded deep learning wind power prediction approach based on a two-layer of mode decomposition", Energy, 189, 2019, pp.116316.
  19. Xu, W., Liu, P., Cheng, L., Zhou, Y., Xia, Q., Gong, Y., and Liu, Y., "Multi-step wind speed prediction by combining a WRF simulation and an error correction strategy", Renewable Energy, 163, 2021, pp.772-782.
  20. Jung, J., and Broadwater, R. P., "Current status and future advances for wind speed and power forecasting", Renewable and Sustainable Energy Reviews, 31, 2014, pp.762-777.
  21. Bao, L., Gneiting, T., Grimit, E. P., Guttorp, P., and Raftery, A. E., "Bias correction and Bayesian model averaging for ensemble forecasts of surface wind direction", Monthly Weather Review, 138(5), 2010, pp.1811-1821.
  22. Lee, S. J., and Kim, Y. C., "A numerical forecast and verification of the aircraft turbulence observed over South Korea", Journal of Korean Meteorological Society, 38(5), 2002, pp.493-507.
  23. Min, B., Kim, Y. H., Choi, H. W., Jeong, H. S., Kim, K. R., and Kim, S., "Low-level wind shear (LLWS) forecasts at Jeju International Airport using the KMAPP", Atmosphere, 30(3), 2020, pp.277-291.
  24. Kim, G. H., Choi, H. W., Seok, J. H., and Kim, Y. H., "Prediction of low level wind shear using high resolution numerical weather prediction model at the Jeju International Airport, Korea", Journal of the Korean Society for Aviation and Aeronautics, 29(4), 2021, pp.88-95.
  25. Kim, G. H., Choi, H. W., Seok, J. H., Lee, S. S., and Lee Y. H., "Low level wind shear characteristics and predictability at the Jeju International Airport", Journal of the Korean Society for Aviation and Aeronautics, 31, 2023, pp.55-58.
  26. Seok, J. H., Choi, H. W., Kim, Y. H. and Lee, S. S., "Diagnosis of low-level aviation turbulence using the Korea meteorological administration post processing (KMAPP)", Journal of the Korean Society for Aviation and Aeronautics, 28(4), 2020, pp.1-11.
  27. Yun, J., Kim, Y. H., and Choi, H. W., "Analyses of the meteorological characteristics over South Korea for wind power applications using KMAPP", Atmosphere, 31(1), 2021, pp.1-15.
  28. Keum, W. H., Lee, S. H., Lee, D. I., Lee, S. S., and Kim, Y. H., "Evaluation and improvement of the KMAPP surface wind speed prediction over complex terrain areas", Atmosphere, 31(1), 2021, pp.85-100.
  29. Seok, J. H., Choi, H. W., Kim, G. H., Lee, S. S., and Lee, Y. H., "Verification of low-level wind shear prediction system using aircraft meteorological data relay (AMDAR)", Journal of the Korean Society for Aviation and Aeronautics, 31(3), 2023, pp.59-70.
  30. Wang, J., Song, Y., Liu, F., and Hou, R., "Analysis and application of forecasting models in wind power integration: A review of multi-step-ahead wind speed forecasting models", Renewable and Sustainable Energy Reviews, 60, 2016, pp.960-981.
  31. Hyundai E&C, "Secrets of airports shared by Hyundai E&C's Airport Experts", Hyundai E&C Newsroom, 2024, Available from: https://en.hdec.kr/en/newsroom/news_view.aspx?NewsSeq=780&NewsType=FUTURE&NewsListType=news_clist
  32. Hwang, H., Eun, S. H., Kim, B. G., Park, S. J., and Park, G. M., "Occurrence characteristics of sea breeze in the gangneung region for 2009 2018", Atmosphere, 30(3), 2020, pp.221-236.
  33. An, E. J., and Kim, H. D., "Characteristics of mountain and valley winds observed at Palgongsan Mountain and their effects on reducing high temperatures in summer", Quantitative Bio-Science, 40(2), 2021, pp.77-82.
  34. Byun, U. Y., Hong, S. Y., Shin, H., Lee, J. W., Song, J. I., Hahm, S. J. Kim, J. K., Kim, H. W., and Kim, J. S., "WRF-based short-range forecast system of the Korea Air Force: Verification of prediction skill in 2009 summer", Atmosphere, 21(2), 2011, pp.197-208.
  35. Byun, U. Y., Hong, J., Hong, S. Y., and Shin, H. H., "Numerical simulations of heavy rainfall over central Korea on 21 September 2010 using the WRF model", Advances in Atmospheric Sciences, 32, 2015, pp.855-869.
  36. Lee, S. J., Lee, J., Greybush, S. J., Kang, M., and Kim, J., "Spatial and temporal variation in PBL height over the Korean peninsula in the KMA operational regional model", Advances in Meteorology, 2013, pp.1-16.
  37. Cortes, C., and Vapnik, V., "Support-vector networks", Machine Learning, 20, 1995, pp.273-297.
  38. Drucker, H., Burges, C. J., Kaufman, L., Smola, A., and Vapnik, V., "Support vector regression machines", Advances in Neural Information Processing Systems, 1996, pp.9.
  39. Smola, A. J., and Scholkopf, B., "A tutorial on support vector regression", Statistics and Computing, 14, 2004, pp.199-222.
  40. Rickard, G. J., Lunnon, R. W., and Tenenbaum, J., "The met office upper air winds: Prediction and verification in the context of commercial aviation data", Meteorological Applications, 8(3), 2001, pp.351-360.
  41. Lee, S. J., Parrish, D. F., Park, S. Y., Wu, W. S., Greybush, S. J., Lee, W. J., and Lord, S. J., "Effects of 2-m air temperature assimilation and a new near-surface observation operator on the NCEP Gridpoint Statistical-Interpolation system", Asia-Pacific Journal of Atmospheric Sciences, 47, 2011, pp.353-376.