Journal of Korea Water Resources Association (한국수자원학회논문집)

Korea Water Resources Association (한국수자원학회)
권호 표지
DOI QR코드

DOI QR Code

A point-scale gap filling of the flux-tower data using the artificial neural network

인공신경망 기법을 이용한 청미천 유역 Flux tower 결측치 보정

  • Jeon, Hyunho (Civil, Architectural and Environmental System Engineering, Sungkyunkwan University) ;
  • Baik, Jongjin (Center for Built Environment, Sungkyunkwan University) ;
  • Lee, Seulchan (Department of Water Resources, Sungkyunkwan University) ;
  • Choi, Minha (Department of Water Resources, Sungkyunkwan University)
  • 전현호 (성균관대학교 건설환경시스템공학과) ;
  • 백종진 (성균관대학교 건설환경연구소) ;
  • 이슬찬 (성균관대학교 수자원학과) ;
  • 최민하 (성균관대학교 수자원학과)
  • Received : 2020.07.29
  • Accepted : 2020.08.28
  • Published : 2020.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, we estimated missing evapotranspiration (ET) data at a eddy-covariance flux tower in the Cheongmicheon farmland site using the Artificial Neural Network (ANN). The ANN showed excellent performance in numerical analysis and is expanding in various fields. To evaluate the performance the ANN-based gap-filling, ET was calculated using the existing gap-filling methods of Mean Diagnostic Variation (MDV) and Food and Aggregation Organization Penman-Monteith (FAO-PM). Then ET was evaluated by time series method and statistical analysis (coefficient of determination, index of agreement (IOA), root mean squared error (RMSE) and mean absolute error (MAE). For the validation of each gap-filling model, we used 30 minutes of data in 2015. Of the 121 missing values, the ANN method showed the best performance by supplementing 70, 53 and 84 missing values, respectively, in the order of MDV, FAO-PM, and ANN methods. Analysis of the coefficient of determination (MDV, FAO-PM, and ANN methods followed by 0.673, 0.784, and 0.841, respectively.) and the IOA (The MDV, FAO-PM, and ANN methods followed by 0.899, 0.890, and 0.951 respectively.) indicated that, all three methods were highly correlated and considered to be fully utilized, and among them, ANN models showed the highest performance and suitability. Based on this study, it could be used more appropriately in the study of gap-filling method of flux tower data using machine learning method.

본 연구에서는 청미천 유역에서의 플럭스타워에서 산출되는 증발산량의 결측값을 보완하기 위해 인공신경망(Artificial Neural Network, ANN)을 사용하였다. 비교 평가를 위해, Mean Diurnal Variation(MDV), Food and Agriculture Organization Penman-Monteith(FAO-PM) 방법들을 이용하여 증발산량을 산정하였고, ANN 방법을 이용한 결과와 비교하였다. 비교 평가 방법으로 시계열 방법 및 통계 분석(결정계수, IOA, RMSE, MAE)이 사용되었다. 각 gap-filling 모델의 검증을 위해 2015년의 30분 단위 데이터를 이용하였으며, 121개의 결측값 중 MDV, FAO-PM, ANN 방법 순으로 각각 70, 53, 54개의 결측값을 보완하여 모든 데이터가 관측되지 않은 36개의 데이터를 제외하면 각각 82.4%, 62.4%, 63.5%의 성능을 보였다. 결정계수(MDV, FAO-PM, ANN 방법 순으로 각각 0.673, 0.784, 0.841)와 IOA(MDV, FAO-PM, ANN 방법 순으로 각각 0.899, 0.890, 0.951)를 분석한 결과, 3가지 방법 모두 양질의 상관성을 보여 활용성이 충분하다고 판단되며, 이 중 ANN 모델이 가장 높은 적합도와 양질의 성능을 나타내었다. 본 연구를 기반으로 기계학습방법을 이용한 플럭스 타워 자료의 gap-filing 연구에 보다 적절하게 활용될 수 있을 것이다.

Keywords

References

  1. Allen, R.G., Tasumi, M., and Trezza, R. (2007). "Satellite-based energy balance for mapping evapotranspiration with internalized calibration (METRIC)-Model." Journal of Irrigation and Drainage Engineering, Vol. 133, No. 4, pp. 380-394. https://doi.org/10.1061/(ASCE)0733-9437(2007)133:4(380)
  2. Ambas, V.T., and Baltas, E. (2012). "Sensitivity analysis of different evapotranspiration methods using a new sensitivity coefficient." Global NEST Journal, Vol. 14, No. 3, pp. 335-343. https://doi.org/10.30955/gnj.000882
  3. Atkinson, P.M., and Tatnall, A.R. (1997). "Introduction neural networks in remote sensing." International Journal of remote sensing, Vol. 18, No. 4, pp. 699-709. https://doi.org/10.1080/014311697218700
  4. Baldocchi, D., Falge, E., Gu, L., Olson, R., Hollinger, D., Running, S., Anthoni, P., Bernhofer, C., Davis, K., Evans, R., Fuentes, J., Goldstein, A., Katul, G., Law, B., Lee, X., Malhi, Y., Meyers, T., Munger, W., Oechel, W., Paw, K. T., Pilegaard, K., Schmid, H.P., Valentini, R., Verma, S., Vesala, T., Wilson, K., and Wofsy, S. (2001). "FLUXNET: A new tool to study the temporal and spatial variability of ecosystem-scale carbon dioxide, water vapor, and energy flux densities." Bulletin of the American Meteorological Society, Vol. 82, No. 11, pp. 2415-2434. https://doi.org/10.1175/1520-0477(2001)082<2415:FANTTS>2.3.CO;2
  5. Chen, B., Black, T.A., Coops, N.C., Hilker, T., Trofymow, J.T., and Morgenstern, K. (2009). "Assessing tower flux footprint climatology and scaling between remotely sensed and eddy covariance measurements." Boundary-Layer Meteorology, Vol. 130, No. 2, pp. 137-167. https://doi.org/10.1007/s10546-008-9339-1
  6. Choi, B., Lee, J.H., and Kim, D.H. (2008). "Solving local minima problem with large number of hidden nodes on two-layered feed-forward artificial neural networks." Neurocomputing, Vol. 71, No. 16-18, pp. 3640-3643. https://doi.org/10.1016/j.neucom.2008.04.004
  7. Gao, H., Struble, T.J., Coley, C.W., Wang, Y., Green, W.H., and Jensen, K.F. (2018). "Using machine learning to predict suitable conditions for organic reactions." ACS central science, Vol. 4, No. 11, pp. 1465-1476. https://doi.org/10.1021/acscentsci.8b00357
  8. Heo, S., Kim, J., and Moon, T. (2018). "Predicting crime risky area using machine learning." Journal of the Korean Association of Geographic Information Studies, Vol. 21, No. 4, pp. 64-80. https://doi.org/10.11108/KAGIS.2018.21.4.064
  9. Hong, J.K., Kwon, H.J., Lim, J.H., Byun, Y.H., Lee, J.H., and Kim, J. (2009). "Standardization of KoFlux eddy-covariance data processing." Korean Journal of Agricultural and Forest Meteorology, Vol. 11, No. 1, pp. 19-26. https://doi.org/10.5532/KJAFM.2009.11.1.019
  10. Hunter, D., Yu, H., Pukish III, M.S., Kolbusz, J., and Wilamowski, B.M. (2012). "Selection of proper neural network sizes and architectures-A comparative study." IEEE Transactions on Industrial Informatics, Vol. 8, No. 2, pp. 228-240. https://doi.org/10.1109/TII.2012.2187914
  11. Jean, N., Burke, M., Xie, M., Davis, W.M., Lobell, D.B., and Ermon, S. (2016). "Combining satellite imagery and machine learning to predict poverty." Science, Vol. 353, No. 6301, pp. 790-794. https://doi.org/10.1126/science.aaf7894
  12. Jensen, J.R., Qiu, F., and Ji, M. (1999). "Predictive modelling of coniferous forest age using statistical and artificial neural network approaches applied to remote sensor data." International Journal of Remote Sensing, Vol. 20, No. 14, pp. 2805-2822. https://doi.org/10.1080/014311699211804
  13. Jeong, D., and Kang, J. (2009). "An analysis of changes in pan evaporation and climate values related to actual evaporation." Journal of Korea Water Resources Association, Vol. 42, No. 2, pp. 117-129. https://doi.org/10.3741/JKWRA.2009.42.2.117
  14. Kang, M., Kwon, H., Kim, J., Kim, H.S., Ryu, Y., Lee, S.J., and Choi, T. (2018). "Korean flux monitoring network's past, present, and future." Korean Journal of Agricultural and Forest Meteorology, Vol. 20, No. 1, pp. 1-4. https://doi.org/10.5532/KJAFM.2018.20.1.1
  15. Kendale, S., Kulkarni, P., Rosenberg, A.D., and Wang, J. (2018). "Supervised machine-learning predictive analytics for prediction of postinduction hypotension." Anesthesiology, Vol. 129, No. 4, pp. 675-688. https://doi.org/10.1097/ALN.0000000000002374
  16. Kim, K., Baik, J., Lee, J., Lee, Y., Jung, S., and Choi, M. (2016). "An assessment and analysis of the gap-filling techniques for revising missing data of flux tower based evapotranspiration-FAO-PM, MDV, and Kalman filter." Journal of the Korean Society of Hazard Mitigation, Vol. 16, No. 6, pp. 95-107. https://doi.org/10.9798/KOSHAM.2016.16.6.95
  17. Kwon, H.J., Park, S.B., Kang, M.S., Yoo, J.I., Yuan, R., and Kim, J. (2007). "Quality control and assurance of eddy covariance data at the two KoFlux sites." Korean Journal of Agricultural and Forest Meteorology, Vol. 9, No. 4, pp. 260-267. https://doi.org/10.5532/KJAFM.2007.9.4.260
  18. Langley, P., and Simon H. (1995). "Applications of machine learning and rule induction." Communications of the ACM, Vol. 38, No. 11, pp. 54-64. https://doi.org/10.1145/219717.219768
  19. Marin, F.R., Angelocci, L.R., Nassif, D.S., Costa, L.G., Vianna, M. S., and Carvalho, K.S. (2016). "Crop coefficient changes with reference evapotranspiration for highly canopy-atmosphere coupled crops." Agricultural Water Management, Vol. 163, pp. 139-145. https://doi.org/10.1016/j.agwat.2015.09.010
  20. Mitchell, T.M. (1997). Machine learning. The McGraw-Hill Companies Inc., Boston, U.S., pp. 52-78.
  21. Panchal, G., Ganatra, A., Kosta, Y.P., and Panchal, D. (2011). "Behaviour analysis of multilayer perceptrons with multiple hidden neurons and hidden layers." International Journal of Computer Theory and Engineering, Vol. 3, No. 2, pp. 332-337.
  22. Papale, D., Reichstein, M., Aubinet, M., Canfora, E., Bernhofer, C., Kutsch, W., Longdoz, B., Rambal, S., Valentini, R., Vesala, T., and Yakir, D. (2006). "Towards a standardized processing of net ecosystem exchange measured with eddy covariance technique: Algorithms and uncertainty estimation." Biogeosciences, Vol. 3, No. 4, pp. 571-583. https://doi.org/10.5194/bg-3-571-2006
  23. Park, J., Baik, J., and Choi, M. (2017). "Satellite-based crop coefficient and evapotranspiration using surface soil moisture and vegetation indices in Northeast Asia." Catena, Vol. 156, pp. 305-314. https://doi.org/10.1016/j.catena.2017.04.013
  24. Park, J., Byun, K., Choi, M., Jang, E., Lee, J., Lee, Y., and Jung, S. (2015). "Evaluation of statistical gap fillings for continuous energy flux (evapotranspiration) measurements for two different land cover types." Stochastic Environmental Research And Risk Assessment, Vol. 29, No. 8, pp. 2021-2035. https://doi.org/10.1007/s00477-015-1101-x
  25. Peterson, T.C., Golubev, V.S., and Groisman, P.Y. (1995). "Evaporation losing its strength." Nature, Vol. 377, No. 6551, pp. 687-688.
  26. Post, H., Franssen, H.H., Graf, A., Schmidt, M., and Vereecken, H. (2015). "Uncertainty analysis of eddy covariance CO2 flux measurements for different EC tower distances using an extended two-tower approach." Biogeosciences, Vol. 12, No. 4, p. 1205. https://doi.org/10.5194/bg-12-1205-2015
  27. Roderick, M.L., and Farquhar, G.D. (2004). "Changes in Australian pan evaporation from 1970 to 2002." International Journal of Climatology, Vol. 24, No. 9, pp. 1077-1090. https://doi.org/10.1002/joc.1061
  28. Sartori, M.A., and Antsaklis, P.J. (1991). "A simple method to derive bounds on the size and to train multilayer neural networks." IEEE transactions on neural networks, Vol. 2, No. 4, pp. 467-471. https://doi.org/10.1109/72.88168
  29. Sheela, K.G., and Deepa, S.N. (2013). "Review on methods to fix number of hidden neurons in neural networks." Mathematical Problems in Engineering, 2013, Article 425740.
  30. Tamura, S.I., and Tateishi, M. (1997). "Capabilities of a four-layered feedforward neural network: Four layers versus three." IEEE Transactions on Neural Networks, Vol. 8, No. 2, pp. 251-255. https://doi.org/10.1109/72.557662
  31. Yuan, R., Kang, M.S., Park, S.B., Hong, J.K., Lee, D.H., and Kim, J. (2007). "The effect of coordinate rotation on the eddy covariance flux estimation in a hilly KoFlux forest catchment." Korean Journal of Agricultural and Forest Meteorology, Vol. 9, No. 2, pp. 100-108. https://doi.org/10.5532/KJAFM.2007.9.2.100