Journal of Digital Convergence (디지털융복합연구)

The Society of Digital Policy and Management (한국디지털정책학회)
권호 표지
DOI QR코드

DOI QR Code

A Study of the Method for Estimating the Missing Data from Weather Measurement Instruments

인공신경망을 이용한 기상관측장비 결측 보완 기술에 관한 연구

  • Min, Jae-Sik (Weather Information Service Engine Institute, Hankuk University of Foreign Studies) ;
  • Lee, Moo-Hun (Weather Information Service Engine Institute, Hankuk University of Foreign Studies) ;
  • Jee, Joon-Bum (Weather Information Service Engine Institute, Hankuk University of Foreign Studies) ;
  • Jang, Min (Weather Information Service Engine Institute, Hankuk University of Foreign Studies)
  • 민재식 (한국외국어대학교 차세대도시농림융합기상사업단) ;
  • 이무훈 (한국외국어대학교 차세대도시농림융합기상사업단) ;
  • 지준범 (한국외국어대학교 차세대도시농림융합기상사업단) ;
  • 장민 (한국외국어대학교 차세대도시농림융합기상사업단)
  • Received : 2016.06.28
  • Accepted : 2016.08.20
  • Published : 2016.08.28
Download PDF
⟨ Previous Next ⟩

Abstract

The purpose of this study is to make up for missing of weather informations from ASOS and AWS using artificial neural networks. We collected temperature, relative humidity and wind velocity for August during 5-yr (2011-2015) and sample designed artificial neural networks, assuming the Seoul weather station was missing. The result of sensitivity study on number of epoch shows that early stopping appeared at 2,000 epochs. Correlation between observation and prediction was higher than 0.6, especially temperature and humidity was higher than 0.9, 0.8 respectively. RMSE decreased gradually and training time increased exponentially with respect to increase of number of epochs. The predictability at 40 epoch was more than 80% effect on of improved results by the time the early stopping. It is expected to make it possible to use more detailed weather information via the rapid missing complemented by quick learning time within 2 seconds.

본 연구는 현재 운영 중인 자동기상관측장비인 ASOS와 AWS의 결측에 대해 안공신경망을 활용하여 주변 관측값을 기반으로 결측을 보완하기 위한 연구이다. 2011년부터 2015년까지 수집된 서울지역 기온, 습도, 풍속을 대상으로 학습데이터를 구성하고 인공신경망을 통해 학습모델을 구축하였으며, 서울관측소를 결측으로 가정하고 학습 모델에 대한 검증을 수행하였다. 학습횟수 증가에 따른 민감도 실험 결과 초기종료는 학습횟수 2,000회에서 나타났다. 관측과 추정치의 상관관계는 모든 기상변수에서 0.6이상이었으며 기온과 습도의 경우 각각 0.9, 0.8 이상의 높은 상관성을 보였다. RMSE는 대부분 기상변수에 대해 학습횟수가 증가함에 따라 꾸준히 감소하지만 풍속의 경우 뚜렷한 증감 경향이 나타나지 않았다. 학습시간은 학습횟수가 증가할수록 지수함수적으로 증가하는 경향을 보였다. 학습 횟수 40회의 ANN 성능은 초기종료 시점까지 향상된 결과에 80%이상의 효과를 볼 수 있으며 2초 내의 빠른 학습시간으로 신속한 결측 보완을 통해 보다 상세한 기상정보의 활용이 가능할 것으로 기대된다.

Keywords

References

  1. Ji-Ae Park, Jang-Mook Kim, Ho-Sung Lee, He-Jin Lee, “Big data study about the effects of weather factors on food poisoning incidence,” Journal of Digital Convergence, Vol. 14, No. 3, pp. 319-327, 2016. https://doi.org/10.14400/JDC.2016.14.3.319
  2. Jang-Mook Kim, Jung-Hwan Cho, Byul Kim, “Correlation between meteorological factors and hospital power consumption,” Journal of Digital Convergence, Vol. 14, No. 6, pp. 457-466, 2016. https://doi.org/10.14400/JDC.2016.14.6.457
  3. Moo-Hun Lee, Min-Gyu Kim, “Meteorological information analysis algorithm based on weight for outdoor activity decision-making,” Journal of Digital Convergence, Vol. 14, No. 3, pp. 209-217, 2016. https://doi.org/10.14400/JDC.2016.14.3.209
  4. Young-Suk Chung, Rack-Koo Park, Jin-Mook Kim, “Study on predictive modeling of incidence of traffic accidents caused by weather conditions,” Journal of the Korea Convergence Society, Vol. 5, No. 1, pp. 9-15, 2014. https://doi.org/10.15207/JKCS.2014.5.1.009
  5. WMO, "Guidelines on quality control procedures for data from automatic weather stations," CIMO/OPAGSURFACE/ETST&MT-1/Doc. 6.1(2), pp. 10, 2004.
  6. M. A. Shafer, C. A. Fiebrich, D. S. Arndt, S. E. Fredrickson, and T. W. Hughes, "Quality assurance procedures in the Oklahoma Mesonetwork". J. Atmos. Oceanic Technol., Vol. 17, pp. 474-494, 2000. https://doi.org/10.1175/1520-0426(2000)017<0474:QAPITO>2.0.CO;2
  7. KMA, "Real-time quality control system for meteorological observation data (I) Application," 11-1360000-000206-01 (Tech. Note 2006-2), pp. 157, 2006.
  8. Jung-Hoon. Chae, Moon-Soo Park, Young-Jean Choi, "The WISE Quality control system for integrated meteorological sensor data", Atmosphere, Vol. 24, No. 3, pp. 445-456, 2014. https://doi.org/10.14191/Atmos.2014.24.3.445
  9. Yu-Mi Cha, Joong-Bae Ahn, “Evaluation of artificial neural network correction skill on dynamically downscaled summer rainfall over South Korea,” Asia-Pac. J. Atmos. Sci., Vol. 41, No. 6, pp. 1125-1135, 2005.
  10. Joong-Bae Ahn, Yu-Mi Cha, “A comparison study of corrections using artificial neural network and multiple linear regression for dynamically downscaled winter temperature over South Korea,” Asia-Pac. J. Atmos. Sci., Vol. 41, No. 3, pp. 401-413, 2005.
  11. R. J. Kuligowski, A. P. Barros, “Localized precipitation forecasts from a numerical weather prediction model using artificial neural networks,” Weather and Forecasting, Vol. 13, No. 4, pp. 1194-1204, 1998. https://doi.org/10.1175/1520-0434(1998)013<1194:LPFFAN>2.0.CO;2
  12. M. C. V. Ramirez, H. F. C. Velho, N. J. Ferreira, "Artificial neural network technique for rainfall forecasting applied to the Sao Paulo region," Journal of Hydrology, Vol. 301, Nos. 1-4, pp. 146-162, 2005. https://doi.org/10.1016/j.jhydrol.2004.06.028
  13. Ju-Young Shin, Gian Choi, Chang-Sam Jeong, Jun-Haeng Heo, "Improving accuracy of RDAPS prediction precipitation using artificial neural networks," KWRA, In procceedings of KWRA 2008 conference, pp. 1013-1017. 2008.
  14. Boosik Kang, Bongki Lee, "Predicting probability of precipitation using artificial neural network and mesoscale numerical weather prediction," KSCE, Vol. 28, No. 5B, pp. 485-493. 2008.
  15. Ji-Hun Ha, Lee, Y.-H. Kim, “Forecasting the precipitation of the next day using deep learning,” JKIIS, Vol. 26, No. 2, pp. 93-98, 2016. https://doi.org/10.5391/JKIIS.2016.26.2.093
  16. S. Samarasinghe, "Neural Networks for Applied Sciences and Engineering: From Fundamentals to Complex Pattern Recognition," CRC Press, 2006.
  17. Y. Yuan, L. Rosasco, A. Caponnetto, "On Early Stopping in Gradient Descent Learning," Constr Approx Constructive Approximation, Vol. 26, No. 2. pp. 289-315, 2007. https://doi.org/10.1007/s00365-006-0663-2
  18. Seong-Eun Lee, Sun-Hee Shin, Kyung-Ja Ha, “The assessment of the spatial variation of the wind field using the meso-velocity scale and its contributing factors,” Atmosphere, Vol. 20, No. 3, pp. 343-353, 2010.

Cited by

  1. A Missing Value Replacement Method for Agricultural Meteorological Data Using Bayesian Spatio–Temporal Model vol.27, pp.7, 2018, https://doi.org/10.5322/JESI.2018.27.7.499