기계학습을 이용한 제주국제공항 저층 윈드시어 예측
Prediction of Low Level Wind Shear of Jeju International Airport using Machine Learning Methods
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Low-Level Wind Shear (LLWS), one of the aviation hazard, is a sudden change in wind speed or direction within 2000ft above the ground. If this event occurs during an aircraft take-off and landing, it may interfere with the normal altitude change of the aircraft and leads to not only delay of the aircraft but also human casualty. In this study, we used seven machine learning methods to predict low-level wind shear of Jeju International Airport (JIA) and compared its prediction skills to the ensemble mean. The machine learning methods used in this study are as follows: multiple linear regression, k-nearest neighbor, regression tree, random forest, support vector machine, artificial neural networks and Long-Short Term Memory (LSTM). Thirteen LLWS ensemble member forecasts derived from a Limited area ENsemble prediction System (LENS) were obtained between 1 December 2018 and 28 February 2020, and 3-h LLWS forecasts for lead times up to 24h. The machine learning methods were applied to the LLWS forecasts and we found that seven machine learning methods showed better prediction skills than ensemble mean and LSTM exhibited best prediction skill among the mentioned seven methods.
Abstract
Low-Level Wind Shear (LLWS), one of the aviation hazard, is a sudden change in wind speed or direction within 2000ft above the ground. If this event occurs during an aircraft take-off and landing, it may interfere with the normal altitude change of the aircraft and leads to not only delay of the aircraft but also human casualty. In this study, we used seven machine learning methods to predict low-level wind shear of Jeju International Airport (JIA) and compared its prediction skills to the ensemble mean. The machine learning methods used in this study are as follows: multiple linear regression, k-nearest neighbor, regression tree, random forest, support vector machine, artificial neural networks and Long-Short Term Memory (LSTM). Thirteen LLWS ensemble member forecasts derived from a Limited area ENsemble prediction System (LENS) were obtained between 1 December 2018 and 28 February 2020, and 3-h LLWS forecasts for lead times up to 24h. The machine learning methods were applied to the LLWS forecasts and we found that seven machine learning methods showed better prediction skills than ensemble mean and LSTM exhibited best prediction skill among the mentioned seven methods.
참고문헌 (16)
- Breiman, L. R, "Random forests", Machine Learning, 45, pp.5~32 (2001)
- 조휘연, "심층 신경망을 이용한 윈드시어 경보 사전 예측", 예술인문사회 융합 멀티미디어 논문지, 8(7), pp.749~757 (2018), 사단법인 인문사회과학기술융합학회[DOI]
- Choi, H.-W, "Probabilistic foreast of low level wind shear of Gimpo, Gimhae, Incheon and Jeju international airports using ensemble model output statistics", 12(12), pp.1643~ (2021)
- Cristianini, N, "An Introduction to Support Vector Machine and Other Kernel- based Learning Methods" (2000)
- Hahn, K. U, "Effect of wind shear on flight safety", Progress in Aerospace Sciences, 26(3), pp.225~259 (1989)
- Hamil, T. M, "Interpretation of rank histograms for verifying ensemble forecasts", Monthly Weather Review, 129(3), pp.550~560 (2001)
- Hochreiter, S, "Long short-term memory", Neural Computation, 9(8), pp.1735~1780 (1997)
- Hon, K. K, "Predicting low-level wind shear using 200-m-resolution NWP at the Hong Kong international airport", Journal of Applied Meteorology and Climatology, 59(2), pp.193~206 (2020)
- 김찬수, "순환신경망을 이용한 제주지역 겨울철 저층윈드시어 예측", 기후연구, 14(3), pp.199~208 (2019), 기후연구소[DOI]
- Lee, Y. G, "Probabilistic forecast of low-level wind shear over Jeju international airport using non-homogeneous regression model", The International Journal of Electrical Engineering & Education, pp.1177~ (2021)[DOI]
- Li, Y. X, "Wind-shear prediction with airport LIDAR data", 2012 IEEE International Geoscience and Remote Sensing Symposium, pp.3704~3707 (2012)
- 민병훈, "고해상도 KMAPP 자료를 활용한 제주국제공항에서 저층 윈드시어 예측", 대기, 30(3), pp.277~291 (2020), 한국기상학회[DOI]
- Minsky, M, "Perceptrons: An Introduction to Computational Geometry" (1988), MIT press
- Rosenblatt, F, "The perceptron: a probabilistic model for information storage and organization in the brain", Psychological Review, 65(6), pp.386~ (1958)
- 석재혁, "고해상도 규모상세화 수치자료 산출체계(KMAPP)를 이용한 저고도 항공난류 진단", 한국항공운항학회지, 28(4), pp.1~11 (2020), 한국항공운항학회[DOI]
- Wong, M. H, "Wind shear forecasting by Chaotic Oscillatory-based Neural Networks (CONN) with Lee Oscillator (retrograde signalling) model", 2008 IEEE International Joint Conference on Neural Networks, pp.2040~2047 (2008)