DOI QR코드

DOI QR Code

심층신경망을 활용한 풍속 예측 개선 모델 개발

Development for Estimation Improvement Model of Wind Velocity using Deep Neural Network

  • 투고 : 2019.11.20
  • 심사 : 2019.12.21
  • 발행 : 2019.12.30

초록

인공신경망은 뇌의 뉴런들에서 상호 작용과 경험을 통해 학습해 나가는 것을 모사해 만든 알고리즘으로, 데이터의 특성이 반영된 학습을 통하여 정확한 결과를 산출하는데 사용할 수 있는 방법이다. 본 연구에서 기상 역학 모델에서 예측된 풍속 값의 개선을 위하여 심층신경망을 이용한 모델을 제시하였다. 연구에서 제시한 심층신경망을 이용한 풍속 예측 개선 모델은 기상 역학 모델의 예측 값을 재 보정하는 모델을 구축하고 이에 대한 검증과 시험 과정 후 별도의 데이터를 통한 예측의 정확도를 높일 수 있는 것을 확인하였다. 풍속 예측의 개선을 위하여 예측 시간, 온도, 기압, 습도, 대기상태변수, 풍속 등과 같은 일반적 기상 현상 자료의 예측 값을 활용한 심층신경망을 구축하였고, 전체 데이터 중 일부 데이터는 모델의 적정성 확인용 데이터로 구분하여, 모델 구축 및 학습에 사용하지 않고 별도의 정확도를 확인하여 연구에서 제시한 방법의 적합성을 확인하였다.

Artificial neural networks are algorithms that simulate learning through interaction and experience in neurons in the brain and that are a method that can be used to produce accurate results through learning that reflects the characteristics of data. In this study, a model using deep neural network was presented to improve the predicted wind speed values in the meteorological dynamic model. The wind speed prediction improvement model using the deep neural network presented in the study constructed a model to recalibrate the predicted values of the meteorological dynamics model and carried out the verification and testing process and Separate data confirm that the accuracy of the predictions can be increased. In order to improve the prediction of wind speed, an in-depth neural network was established using the predicted values of general weather data such as time, temperature, air pressure, humidity, atmospheric conditions, and wind speed. Some of the data in the entire data were divided into data for checking the adequacy of the model, and the separate accuracy was checked rather than being used for model building and learning to confirm the suitability of the methods presented in the study.

키워드

참고문헌

  1. G. S. Ban, "Weather factor for aircraft operation safety," Civil Aviation Development, Vol. 28, pp. 225-257, Oct. 2002.
  2. FAA, AC00-45H, Aviation weather services, Federal Aviation Administration, Sep. 2016.
  3. S. K. Ku and S. M. Hong, "Development for estimation model of runway visual range using deep neural network," Journal of Advanced Navigation Technology, Vol. 21, No. 4, pp. 435-442, Oct, 2017
  4. R. Frank, The perceptron a perceiving and recognizing automaton, Technical Report 85-460-1, 1957.
  5. W. P. John, Beyond regression: New tools for prediction and analysis in the behavioral sciences, Doctoral Dissertation, Applied Mathematics, Harvard University, Boston, MA, 1974.
  6. G. E. Hinton, S. Osindero, and Y.. W. Teh "A fast learning algorithm for deep belief nets," Neural Computation, Vol. 18, No. 7, pp. 1527-1554. 2006. https://doi.org/10.1162/neco.2006.18.7.1527
  7. J. S. Lee, "Development process and understanding of Deep Neural Networks", Information and Communications Magazine, Vol 33 , No.10, pp. 40-48, Sep, 2016.
  8. S. H. Choo, Y. H. Lee, K. D. Ahn and K. Y. Chung, "Development of wind forecast model over korean peninsula using harmony search algorithm," in Korean Institute of Intelligent Systems 2013 Spring Conference, Daegu: Korea, pp. 198-199, Apr, 2013
  9. S. J. Lee and Y. C. Kim, "A numerical forecast and verification of the aircraft turbulence observed over South Korea," Asia-Pacific Journal of Atmospheric Sciences, Vol. 38, No. 5, pp. 493-507, Oct. 2002
  10. J. I. Kwon, H. S. Lee and K, Y, Kim "Low altitude wind prediction using the atmospheric model" in The Korean Society for Aviation and Aeronautics 2018 Fall Conference, Seoul: Korea, pp. 141-146, Nov, 2018.