DOI QR코드

DOI QR Code

소형 자동기상관측장비(Mini-AWS) 기압자료 보정 기법

A Method for Correcting Air-Pressure Data Collected by Mini-AWS

  • Ha, Ji-Hun (Department of Embedded Software Engineering, Kwangwoon University) ;
  • Kim, Yong-Hyuk (Department of Computer Science and Engineering, Kwangwoon University) ;
  • Im, Hyo-Hyuc (Korea Oceanic and Atmospheric System Technology) ;
  • Choi, Deokwhan (Korea Oceanic and Atmospheric System Technology) ;
  • Lee, Yong Hee (National Institute of Meteorological Science)
  • 투고 : 2016.04.28
  • 심사 : 2016.06.21
  • 발행 : 2016.06.25

초록

수치예보모델을 이용한 예보의 정확도를 높이기 위해 관측 간격이 조밀하고 많은 양의 관측자료를 사용하는 방법이 있다. 현재 기상청에서는 자동기상관측장비(Automatic Weather Station, AWS)를 설치하여 관측자료를수 집하고 있지만, 고가의 설치 및 유지보수 비용 등의 경제적인 한계가 있다. 소형 자동기상관측장비(Mini-AWS)는 기온, 습도, 기압을 측정하고 기록할 수 있는 초소형 기상관측장비로 설치 및 유지보수 비용이 저렴하고 설치를 위한 장소 선택의 제약이 크지 않아 필요한 지역에 설치하여 관측자료를 수집하기가 용이하다. 그러나 설치 장소에 따라 외부환경에 영향을 받을 수 있기 때문에 관측자료의 보정이 필요하다. 본 논문에서는 Mini-AWS 기압자료를 기상자료로 활용하기 위한 보정기법을 제안한다. Mini-AWS를 통해 수집된 관측자료는 전처리 과정을 거쳐 주변에서 가장 가까운 AWS 기압 값을 참값으로 기계학습 기법을 이용하여 기압 보정을 수행하였다. 실험결과 기상관측 규정에 따른 허용오차 범위 내에 포함되었으며, 지지벡터 회귀를 적용한 보정기법이 가장 좋은 성능을 보였다.

For high accuracy of forecast using numerical weather prediction models, we need to get weather observation data that are large and high dense. Korea Meteorological Administration (KMA) mantains Automatic Weather Stations (AWSs) to get weather observation data, but their installation and maintenance costs are high. Mini-AWS is a very compact automatic weather station that can measure and record temperature, humidity, and pressure. In contrast to AWS, costs of Mini-AWS's installation and maintenance are low. It also has a little space restraints for installing. So it is easier than AWS to install mini-AWS on places where we want to get weather observation data. But we cannot use the data observed from Mini-AWSs directly, because it can be affected by surrounding. In this paper, we suggest a correcting method for using pressure data observed from Mini-AWS as weather observation data. We carried out preconditioning process on pressure data from Mini-AWS. Then they were corrected by using machine learning methods with the aim of adjusting to pressure data of the AWS closest to them. Our experimental results showed that corrected pressure data are in regulation and our correcting method using SVR showed very good performance.

키워드

참고문헌

  1. P. Bauer, A. Thorpe, G. Brunet, "The quiet revolution of numerical weather prediction," Nature, Vol. 525, issue. 7567, pp. 47-55, 2015. https://doi.org/10.1038/nature14956
  2. J. M. Straka, E. N. Rasamussen, S. E. Fredrickson, “A mobile mesonet for finescale meteorological observations,” American Meteorological Society, Vol. 13, No. 5, pp. 921-936, 1996.
  3. J. J. Cassano, “Weather bike: a bicycle-based weather station for observing local temperature variations,” American Meteorological Society, Vol. 95, No. 2, pp. 205-209, 2014. https://doi.org/10.1175/BAMS-D-13-00044.1
  4. W. P. Mahoney III, J. M. O'Sullivan, "Realizing the potential of vehicle-based observations," Bulletin of the American Meteorological Society, Vol. 94, No. 2, pp. 1007-1018, 2013. https://doi.org/10.1175/BAMS-D-12-00044.1
  5. C. L. Muller, L. Chapman, S. Johnston, C. Kidd, S. Illingworth, G. Foody, A. Overeem, R. R. Leigh, "Crowdsourcing for climate and atmospheric sciences: current status and future potential," International Journal of Climatology, Vol. 35, pp. 3185-3203, 2015. https://doi.org/10.1002/joc.4210
  6. N.-Y. Kim, Y.-H. Kim, Y. Yoon, H.-H. Im, Reno K. Y. Choi, Y. H. Lee, "Correcting air-pressure data collected by MEMS sensors in smartphones," Journal of Sensors, Vol. 2015, article ID. 245498, pp. 10
  7. F. Persson, T. Svahn, Mobile Meteorological Measurements, Department of Electrical and Information Technology, Lund University, 2011.
  8. J.-H. Ha, Y.-H. Kim, Y. H. Lee, “Forecasting the precipitation of the next day using deep learning,” Journal of Korean Institute of Intelligent Systems, Vol. 26, No. 2, pp. 93-98, 2016. https://doi.org/10.5391/JKIIS.2016.26.2.093
  9. D. Kim, K. Seo, “Comparison of linear and nonlinear regression and elements analysis for wind speed prediction,” Journal of Korean Institute of Intelligent Systems, Vol. 25, No. 5, pp. 477-482, 2015. https://doi.org/10.5391/JKIIS.2015.25.5.477
  10. J.-S. Bae, C.-S. Song, S.-K. Oh, “Design of meteorological radar echo classifier based on RBFNN using radial velocity,” Journal of Korean Institute of Intelligent Systems, Vol. 25, No. 3, pp. 242-247, 2015. https://doi.org/10.5391/JKIIS.2015.25.3.242
  11. B. Hyoen, K. Seo, Y. H. Lee, "Two evolutionary algorithms based compensation techniques for short-term temperature prediction," Proceeding of KIIS Spring Conference, Vol. 23, no. 1, pp. 38-39, 2013.
  12. S.-J. Lim, H.-K. Kim, S.-K. Oh, "Design of regression model based on feature selection for quality control with correction of error on AWS observation data," Proceeding of KIIS Autumn Conference, Vol. 25, No. 2, pp. 17-18, 2015.
  13. M. W. Gardner, S. R. Dorling, "Artificial neural networks (the multilayer perceptron)-a review of applications in the atmospheric sciences," Atmospheric Environment, Vol. 32, no. 14-15, pp. 2627-2636, 1998. https://doi.org/10.1016/S1352-2310(97)00447-0
  14. A. Smola, V. Vapnik, "Support vector regression machines," Advances in Neural Information Processing Systems, Vol. 9, pp. 155-161, 1997.
  15. A. Smola, B. Schoelkopf, "A tutorial on support vector regression," Statistics and Computing, Vol. 14, pp. 199-222, 2004. https://doi.org/10.1023/B:STCO.0000035301.49549.88
  16. S. K. Shevade, S. S. Keerthi, C. Bhattacharyya, K. R. K. Murthy, "Improvements to the SMO algorithm for SVM regression," IEEE Transactions on Neural Networks, Vol. 11, Issue 5, pp. 1188-1193, 2000. https://doi.org/10.1109/72.870050
  17. D. Frank, The Expectation Maximization Algorithm, Georgia Institute of Technology, 2002
  18. BIZ-GIS, biz-gis.com/GISDB:DEM.
  19. M. Jarraud, "Guide to meteorological instrument and methods of observation (WMO-No. 8)," World Meteorological Organization, 2008
  20. M. Hall, E. Frank, I. H. Witten, Data Mining :Practical Machine Learining Tool and Techniques, Morgan Kaufmann, 2011.
  21. J.-H. Ha, Y.-H. Kim, N.-Y. Kim, H.-H. Im, S. Sim, R. K. Y. Choi, "Improved correction of air-pressure data corrected by smartphones using support vector regression," Proceeding of KIIS Autumn Conference, Vol. 25, No. 2, pp. 171-172, 2015.