기계학습과 시스템 다이내믹스를 이용한 재난예측 및 대응정책효과 시뮬레이션: 경기도 단기가뭄을 사례로 = Disaster Prediction and Policy Simulation for Evaluating Mitigation Effects Using Machine Learning and System Dynamics: Case Study of Seasonal Drought in Gyeonggi Province

다국어 초록 (Multilingual Abstract)

Korea has had fewer droughts than floods; thus, its drought mitigation policies are insufficient. Typically, it takes a long time to confirm the effects of any policy and frequent revisions to a policy can cause social disruption. Therefore, a new method is needed, with which we can simulate policies in advance based on drought situation forecasts. This study deals with policy evaluation, using machine learning and system dynamics, by forecasting agricultural drought trends and simulating the effects of drought mitigation policies. The study area was the southern part of Gyeonggi Province. As a result, the soil moisture map predicted by machine learning for a time after three months of no rainfall clearly showed the resultant agricultural drought distribution. Also, the water price increase policy was simulated using system dynamics and found to be ineffective for drought mitigation because of insufficient water security measures.

국문 초록 (Abstract)

우리나라는 홍수에 비해 가뭄에 대한 경험이 부족해 관련 정책이 미흡하다. 일반적으로 정책은 실행 후 효과가 확인되기까지 긴 시일이 걸릴 뿐만 아니라 빈번하게 수정되면 사회적 혼란이 야기되므로 이를 사전에 모의할 수 있는 새로운 방법이 필요하다. 본 연구는 기계학습과 시스템 다이내믹스를 이용하여 농업적 가뭄의 진행양상을 예측하고 이를 토대로 가상의 가뭄대응정책의 효과를 시뮬레이션 하는 전 과정을 다루었다. 연구 대상지는 경기도 남부이며, 연구 결과에 의하면 기계학습에 의해 예측된 3 개월간의 가뭄 후의 토양 수분지도는 농업적 가뭄 분포 패턴을 보여 주었다. 그리고 이 지도로부터 확인된 가뭄우심지역과 동일 취수원을 사용하는 모든 지자체를 대상으로 시스템 다이내믹스를 이용하여 가상의 수도가격 인상정책을 모의하였더니 확보 가능한 수자원양이 미미하여 가뭄완화에 거의 실효성이 없는 것으로 나타났다.

참고문헌 (Reference)

1 김형건, "패널 분위수회귀 모형을 사용한 우리나라 지방 상수도 생활용수 수요의 가격탄력성 추정" 한국환경경제학회 27 (27): 195-214, 2018

2 Owen, D., "Water and taxes" 50 : 1559-1617, 2017

3 Kwon, H. D., "Water & climate change" Pieona 2016

4 Wilhite, D., "Understanding: the drought phenomenon: The role of definitions" 10 (10): 111-120, 1985

5 Raduła, M. W., "Topographic wetness index explains soil moisture better than bioindication with Ellenberg's indicator values" 85 : 172-179, 2018

6 Landsat Science, "Thermal Infrared Sensor"

7 "Statistics Korea"

8 Hao, Z., "Seasonal drought prediction: Advances, challenges, and future prospects" 56 (56): 108-141, 2018

9 Tucker, C. J., "Red and photographic infrared linear combinations for monitoring vegetation" 8 (8): 127-150, 1979

10 Breiman, L., "Random forests" 45 (45): 5-32, 2001

11 U.S. Geological Survey, "Product guide:Landsat surface reflectance-derived spectral indices" 2017

12 National Drought Mitigation Center, "Predicting drought"

13 McDonnell, T., "Paying for water:Equity, efficiency and sustainability" Think-tank for Action on Social Change 2013

14 Huete, A., "Overview of the radiometric and biophysical performance of the MODIS vegetation indices" 83 (83): 195-213, 2002

15 "My Water"

16 Rhee, J., "Meteorological drought forecasting for ungauged areas based on machine learning: Using long-range climate forecast and remote sensing data" 237-238 : 105-122, 2017

17 "Korean Statistical Information Service"

18 Seo, S.K, "K-Water tried to raise water tax during drought" News1 News

19 World Meteorologcal Organizatio, "Handbook of drought indicators and indices" Integrated Drought Management Programme 2016

20 "Gyeonggi Province Statistics"

21 Van Leeuwen, B, "GIS workflow for continuous soil moisture estimation based on medium resolution satellite data" 2015

22 Weng, Q., "Estimation of land surface temperature-vegetation abundance relationship for urban heat island studies" 89 (89): 467-483, 2004

23 Wichman, C.J, "Enduring effects of changes in billing frequency: Evidence from urban water use" 2017

24 "Earth Explorer"

25 Nataraj, S., "Do residential water consumers react to price increases? Evidence from a natural experiment in Santa Cruz" 10 (10): 9-11, 2007

26 Kim, Y. P., "Development of simulation system for financial investment impact assessment and set-up of national development index (I)" Korea Research Institute for Human Settlements 2007

27 Grafton, R. Q., "Determinants of residential water consumption:Evidence and analysis from a 10-country household survey" 47 (47): W08537-, 2011

28 Barros, V. R., "Climate change 2014: Impacts, adaptation, and vulnerability - Part B: Regional aspects" Intergovernmental Panel on Climate Change, Cambridge University Press 2014

29 Union of Concerned Scientists, "Causes of drought: What's the climate connection?" 2018

30 Public Policy Institute of California (PPIC) Water Policy Center, "California' s water"

31 Sruthi, S., "Agricultural drought analysis using the NDVI and land surface temperature data; A case study of Raichur District" 4 : 1258-1264, 2015

32 Korea Rural Community Corporation, "Agricultural Drought Management System"

33 Huete, A., "A soil-adjusted vegetation index (SAVI)" 25 (25): 295-309, 1988

34 Sandholt, I., "A simple interpretation of the surface temperature/vegetation index space for assessment of surface moisture status" 79 (79): 213-224, 2002

35 Qi, J., "A modified soil adjusted vegetation index" 48 (48): 119-126, 1994