DOI QR코드

DOI QR Code

베이지안 네트워크 및 의사결정 모형을 이용한 위성 강수자료 기반 기상학적 가뭄 전망

Meteorological drought outlook with satellite precipitation data using Bayesian networks and decision-making model

  • 신지예 (한양대학교 공학대학 건설환경공학과) ;
  • 김지은 (한양대학교 대학원 건설환경시스템공학과) ;
  • 이주헌 (중부대학교 건축토목공학부) ;
  • 김태웅 (한양대학교 공학대학 건설환경공학과)
  • Shin, Ji Yae (Department of Civil and Environmental Engineering, Hanyang University) ;
  • Kim, Ji-Eun (Department of Civil and Environmental System Engineering, Hanyang University) ;
  • Lee, Joo-Heon (Department of Civil Engineering, Joongbu University) ;
  • Kim, Tae-Woong (Department of Civil and Environmental Engineering, Hanyang University)
  • 투고 : 2018.12.29
  • 심사 : 2019.03.15
  • 발행 : 2019.04.30

초록

가뭄재해는 다른 재해와 다르게 광범위한 공간에 걸쳐서 충분한 강우가 발생하기 전까지 오랜 기간 동안 발생되는 특성이 있다. 위성 영상은 시공간적으로 지속적인 강수량 관측을 제공할 수 있다. 본 연구는 위성 영상 기반의 강수자료를 활용하여 기상학적 가뭄 전망 모형을 개발하였다. PERSIANN_CDR, TRMM 3B42와 GPM IMERG 영상을 활용하여 강수 자료를 구축한 뒤, 표준강수지수(SPI)를 기반으로 기상학적 가뭄을 정의하였다. 과거의 가뭄 정보와 물리적 예측 모형 기반의 가뭄 예측 결과를 결합할 수 있는 베이지안 네트워크 기반 가뭄 예측 기법을 이용하여 확률론적 가뭄 예측 결과를 생산하였으며, 가뭄 예측결과를 가뭄 전망 의사결정 모형에 적용하여 가뭄 전망 결과를 도출하였다. 가뭄 전망 정보는 가뭄 발생, 지속, 종결, 가뭄 없음의 4단계로 구분하였다. 본 연구의 가뭄 전망 결과는 ROC 분석을 통하여 물리적 예측 모형인 다중모형 앙상블(MME)을 활용한 가뭄 전망 결과와 전망 성능을 비교하였다. 그 결과, 2~3개월 가뭄 전망에 대한 가뭄 발생 및 지속의 단계에서는 MME 모형보다 높은 전망성능을 보여주었다.

Unlike other natural disasters, drought is a reoccurring and region-wide phenomenon after being triggered by a prolonged precipitation deficiency. Considering that remote sensing products provide consistent temporal and spatial measurements of precipitation, this study developed a remote sensing data-based drought outlook model. The meteorological drought was defined by the Standardized Precipitation Index (SPI) achieved from PERSIANN_CDR, TRMM 3B42 and GPM IMERG images. Bayesian networks were employed in this study to combine the historical drought information and dynamical prediction products in advance of drought outlook. Drought outlook was determined through a decision-making model considering the current drought condition and forecasted condition from the Bayesian networks. Drought outlook condition was classified by four states such as no drought, drought occurrence, drought persistence, and drought removal. The receiver operating characteristics (ROC) curve analysis were employed to measure the relative outlook performance with the dynamical prediction production, Multi-Model Ensemble (MME). The ROC analysis indicated that the proposed outlook model showed better performance than the MME, especially for drought occurrence and persistence of 2- and 3-month outlook.

키워드

SJOHCI_2019_v52n4_279_f0001.png 이미지

Fig. 1. The framework of bayesian networks drought prediction

SJOHCI_2019_v52n4_279_f0002.png 이미지

Fig. 2. Drought outlook decision-making tree

SJOHCI_2019_v52n4_279_f0003.png 이미지

Fig. 3. Results of probabilistic forecast (the current month is January 2009)

SJOHCI_2019_v52n4_279_f0004.png 이미지

Fig. 4. Timeseries of 1-month probabilistic forecasts (the current month is January 2009 in upstream of Namhan River (No. 1001) subbasin)

SJOHCI_2019_v52n4_279_f0005.png 이미지

Fig. 5. Drought outlook map (the current month is January 2009)

SJOHCI_2019_v52n4_279_f0006.png 이미지

Fig. 6. Multi-class ROC confusion matrix

SJOHCI_2019_v52n4_279_f0007.png 이미지

Fig. 7. Spatial distribution of various forecast verification measures for 1-month drought outlook

SJOHCI_2019_v52n4_279_f0008.png 이미지

Fig. 8. ROC curves for drought outlook

Table 1. Data periods of precipitation data

SJOHCI_2019_v52n4_279_t0001.png 이미지

Table 2. Drought condition decision table

SJOHCI_2019_v52n4_279_t0002.png 이미지

Table 3. ROC scores for drought outlook

SJOHCI_2019_v52n4_279_t0003.png 이미지

참고문헌

  1. AghaKouchak, A., Farahmand, A., Melton, F. S., Teixeira, J., Anderson, M. C., Wardlow, B. D., and Hain, C. R. (2015). "Remote sensing of drought: progress, challenges and opportunities." Reviews of Geophysics, Vol. 53, No. 2, pp. 452-480. https://doi.org/10.1002/2014RG000456
  2. Aviles, A., Celleri, R., Solera, A., and Paredes, J. (2016). "Probabilistic forecasting of drought events using markov chain-and bayesian network-based models: a case study of an andean regulated river basin." Water, Vol. 8, No. 2, pp. 1-37.
  3. De Jesus, A., Brena-Naranjo, J. A., Pedrozo-Acuna, A., and Yamanaka, V. H. A. (2016). "The use of TRMM 3B42 product for drought monitoring in Mexico." Water, Vol. 8, No. 8, pp. 325. https://doi.org/10.3390/w8080325
  4. De Linage, C., Famiglietti, J. S., and Randerson, J. T. (2014). "Statistical prediction of terrestrial water storage changes in the Amazon Basin using tropical Pacific and North Atlantic sea surface temperature anomalies." Hydrology and Earth System Sciences, Vol. 18, No. 6, pp. 2089-2102. https://doi.org/10.5194/hess-18-2089-2014
  5. Hao, Z., Singh, V. P., and Xia, Y. (2018). "Seasonal drought prediction: advances, challenges, and future prospects." Reviews of Geophysics, Vol. 56, No. 1, pp. 108-141. https://doi.org/10.1002/2016RG000549
  6. Jang, S., Rhee, J., Yoon, S., Lee, T., and Park, K. (2017). "Evaluation of GPM IMERG applicability using SPI based satellite precipitation." Journal of the Korean Society of Agricultural Engineer, Vol. 59, No. 3, pp. 29-39. https://doi.org/10.5389/KSAE.2017.59.3.029
  7. Jang, S., Yoon, S., Lee, S., Lee, T., and Park, K. (2018). "Evaluation of drought monitoring using satellite precipitation for un-gaged basins." Journal of the Korean Society of Agricultural Engineer, Vol. 60, No. 2, pp. 55-63. https://doi.org/10.5389/KSAE.2018.60.2.055
  8. Jeong, M.-S., Kim, J.-S., Jang, H.-W., and Lee, J.-H. (2016). "ROC evaluation for MLP ANN drought forecasting model." Journal of Korea Water Association, Vol. 49, No. 10, pp. 877-885.
  9. Kim, T. W., and Valdes, J. B. (2003). "Nonlinear model for drought forecasting based on a conjunction of wavelet transforms and neural networks." Journal of Hydrologic Engineering, Vol. 8, No. 6, pp. 319-328. https://doi.org/10.1061/(ASCE)1084-0699(2003)8:6(319)
  10. Lee, J. H., Jeong, S. M., Kim, J. H., and Ko, Y. S. (2006). "Development of drought monitoring system: II. Quantitative drought monitoring and drought outlook methodology." Journal of Korea Water Resources Association, Vol. 39, No. 9, pp. 801-812. https://doi.org/10.3741/JKWRA.2006.39.9.801
  11. Liu, W., and Juarez, R. N. (2001). "ENSO drought onset prediction in northeast Brazil using NDVI." International Journal of Remote Sensing, Vol. 22, No. 17, pp. 3483-3501. https://doi.org/10.1080/01431160010006430
  12. Lui, Z., Lu, G., He, H., Wu, Z., and He, J. (2018). "A conceptual prediction model for seasonal drought processes using atmospheric and oceanic standardized anomalies: application to regional drought processes in China." Hydrology and Earth System Sciences, Vol. 22, No. 1, pp. 529-546. https://doi.org/10.5194/hess-22-529-2018
  13. Madadgar, S., AghaKouchak, A., Shukla, S., Wood, A. W., Cheng, L., Hsu, K. L., and Svoboda, M. (2016). "A hybrid statistical dynamical framework for meteorological drought prediction: application to the southwestern United States." Water Resources Research, Vol. 52, No. 7, pp. 5095-5110. https://doi.org/10.1002/2015WR018547
  14. Madadgar, S., and Moradkhani, H. (2014). "Spatio-temporal drought forecasting within Bayesian networks." Journal of Hydrology, Vol. 512, pp. 134-146. https://doi.org/10.1016/j.jhydrol.2014.02.039
  15. Milly, P. C. D., Betancourt, J., Falkenmark, M., Hirsch, R. M., Kundzewicz, Z. W., Lettenmaier, D. P., and Stouffer, R. J. (2008). "Stationarity is dead: whither water management?" Science, Vol. 319, No. 5863, pp. 573-574. https://doi.org/10.1126/science.1151915
  16. Mishra, A. K., and Desai, V. R. (2005). "Drought forecasting using stochastic models." Stochastic Environmental Research and Risk Assessment, Vol. 19, No. 5, pp. 326-339. https://doi.org/10.1007/s00477-005-0238-4
  17. Mishra, A. K., and Singh, V. P. (2011). "Drought modeling: a review." Journal of Hydrology, Vol. 403, No. 1-2, pp. 157-175. https://doi.org/10.1016/j.jhydrol.2011.03.049
  18. Mishra, A., Desai, V., and Singh, V. (2007). "Drought forecasting using a hybrid stochastic and neural network model." Journal of Hydrologic Engineering, Vol. 12, No. 6, pp. 626-638. https://doi.org/10.1061/(ASCE)1084-0699(2007)12:6(626)
  19. Morid, S., Smakhtin, V., and Bagherzadeh, K. (2007). "Drought forecasting using artificial neural networks and time series of drought indices." International Journal of Climatology, Vol. 27, No. 15, pp. 2103-2111. https://doi.org/10.1002/joc.1498
  20. Mwangi, E., Wetterhall, F., Dutra, E., Di Giuseppe, F., and Pappenberger, F. (2014). "Forecasting droughts in East Africa." Hydrology and Earth System Sciences, Vol. 18, No. 2, pp. 611-620. https://doi.org/10.5194/hess-18-611-2014
  21. Nam, W.-H., Tadesse, T., Wardlow, B. D., Jang, M.-W., and Hong, S.-Y. (2015). "Satellite-based hybrid drought assessment using vegetation drought response index in South Korea (VegDRISKorea)." Journal of the Korean Society of Agricultural Engineers, Vol. 57, No. 4, pp. 1-9. https://doi.org/10.5389/KSAE.2015.57.4.001
  22. Pathiraja, S., Marshall, L., Sharma, A., and Moradkhani, H. (2016). "Detecting non-stationary hydrologic model parameters in a paired catchment system using data assimilation." Advances in Water Resources, Vol. 94, pp. 103-119. https://doi.org/10.1016/j.advwatres.2016.04.021
  23. Rhee, J., Im, J., and Kim, J. (2014). "Hydrological drought assessment and monitoring based on remote sensing for ungauged area." Korean Journal of Remote Sensing, Vol. 30, No. 4, pp. 525-536. https://doi.org/10.7780/kjrs.2014.30.4.10
  24. Russell, S. and Norvig, P. (1995). Artificial intelligence: a modern approach. Englewood Cliff, Prentice Hall.
  25. Shin, J. Y., Ajmal, M., Yoo, J., and Kim, T.-W. (2016). "A Bayesian network-based probabilistic framework for drought forecasting and outlook." Advances in Meteorology, Vol. 2016, No. 9472605, pp. 1-10.
  26. Shin, J. Y., Kwon, H.-H., Lee, J.-H., and Kim, T.-W. (2017). "Bayesian networks-based probabilistic forecasting of hydrological drought considering drought propagation." Journal of Korea Water Resources Association, Vol. 50, No. 11, pp. 769-779. https://doi.org/10.3741/JKWRA.2017.50.11.769
  27. Sohn, S. J., Ahn, J. B., and Tam, C. Y. (2013a). "Six month-lead downscaling prediction of winter to spring drought in South Korea based on a multimodel ensemble." Geophysical Research Letters, Vol. 40, No. 3, pp. 579-583. https://doi.org/10.1002/grl.50133
  28. Sohn, S. J., Min, Y. M., Lee, J. Y., Tam, C. Y., Kang, I. S., Wang, B., Ahn, J. B., and Yamagata, T. (2012). "Assessment of the long-lead probabilistic prediction for the Asian summer monsoon precipitation (1983-2011) based on the APCC multimodel system and a statistical model." Journal of Geophysical Research, Vol. 117, No. D4, pp. 1-12.
  29. Sohn, S. J., Tam, C. Y., and Ahn, J. B. (2013b). "Development of a multimodel-based seasonal prediction system for extreme droughts and floods: a case study for South Korea." International Journal of Climatology, Vol. 33, No. 4, pp. 793-805. https://doi.org/10.1002/joc.3464
  30. Son, K.-H., Bae, D.-H., and Cheong, H.-S. (2015). "Construction & evaluation of GloSea5-based hydrological drought outlook system." Atmosphere, Vol. 25, No. 2, pp. 271-281. https://doi.org/10.14191/Atmos.2015.25.2.271
  31. Tadesse, T., Demisse, G. B., Zaitchik, B., and Dinku, T. (2014). "Satellite-based hybrid drought monitoring tool for prediction of vegetation condition in eastern Africa: a case study for Ethiopia." Water Resources Research, Vol. 50, No. 3, pp. 2176-2190. https://doi.org/10.1002/2013WR014281
  32. Yan, H., Moradkhani, H., and Zarekarizi, M. (2017). "A probabilistic drought forecasting framework: a combined dynamical and statistical approach." Journal of Hydrology, Vol. 548, pp. 291-304. https://doi.org/10.1016/j.jhydrol.2017.03.004
  33. Yoon, J. H., Mo, K., and Wood, E. F. (2012). "Dynamic-modelbased seasonal prediction of meteorological drought over the contiguous United States." Journal of Hydrometeorology, Vol. 13, No. 2, pp. 463-482. https://doi.org/10.1175/JHM-D-11-038.1