CART알고리즘과 Landsat-8 위성영상 분석을 통한 계절별 지하수함양량 변화 = Variation of Seasonal Groundwater Recharge Analyzed Using Landsat-8 OLI Data and a CART Algorithm

국문 초록 (Abstract)

지하수함양은 시공간적으로 다양하여 직접적으로 측정하기 어렵기 때문에 함양추정을 위해 수치모델이 널리 사용되고 있다. 이 연구에서는 지하수함양을 추정하기 위한 방법으로 기계학습법의 하나인 분류회귀트리(CART)모형을 적용하기 위해 수정된 수직식생지수(mPVI), 정규식생지수(NDVI), 정규경작지수(NDTI), 정규나지지수(NDRI) 같은 토양-식생관련 지수와 강우, 지형인자(고도, 경사, 경사방향)를 입력하고 김천지역 SWAT-MODFLOW의 함양량 결과를 추출 및 학습하여 함양량을 예측하였다. SWAT-MODFLOW의 함양량 분포에 대한 CART모형의 예측값의 전반적인 정확도는 0.5~0.7, 카파계수는 0.3~0.6으로 나타나 위성영상자료를 통해 토양-식생에 따른 함양량 변화를 합리적으로 예측할 수 있었다.

다국어 초록 (Multilingual Abstract)

Groundwater recharge rates vary widely by location and with time. They are difficult to measure directly and are thus often estimated using simulations. This study employed frequency and regression analysis and a classification and regression tree (CART) algorithm in a machine learning method to estimate groundwater recharge. CART algorithms are considered for the distribution of precipitation by subbasin (PCP), geomorphological data, indices of the relationship between vegetation and landuse, and soil type. The considered geomorphological data were digital elevaion model (DEM), surface slope (SLOP), surface aspect (ASPT), and indices were the perpendicular vegetation index (PVI), normalized difference vegetation index (NDVI), normalized difference tillage index (NDTI), normalized difference residue index (NDRI). The spatio-temperal distribution of groundwater recharge in the SWAT-MODFLOW program, was classified as group 4, run in R, sampled for random and a model trained its groundwater recharge was predicted by CART condidering modified PVI, NDVI, NDTI, NDRI, PCP, and geomorphological data. To assess inter-rater reliability for group 4 groundwater recharge, the Kappa coefficient and overall accuracy and confusion matrix using K-fold cross-validation were calculated. The model obtained a Kappa coefficient of 0.3-0.6 and an overall accuracy of 0.5-0.7, indicating that the proposed model for estimating groundwater recharge with respect to soil type and vegetation cover is quite reliable.

참고문헌 (Reference)

1 정일문, "제주 천미천 유역의 차단량 추정" 대한토목학회 35 (35): 815-820, 2015

2 정일문, "유역 유출과정과 지하수위 변동을 고려한 분포형 지하수 함양량 산정방안" 한국지하수토양환경학회 12 (12): 19-32, 2007

3 van Deventer, A. P., "Using Thematic Mapper data to identify contrasting soil plains and tillage practices" 63 (63): 87-93, 1997

4 Markstrom, S. L., "U.S. Geological Survey Techniques and Methods 6-D1" Geological Survey 254-, 2008

5 MOLIT, "The basic groundwater investigation in Jangseong"

6 Tsutsumi, A., "Surface and subsurface water balance estimation by the groundwater recharge model and a 3-D two-phase flow model" 49 (49): 205-226, 2004

7 Edward A. Sudicky, "Simulating complex flow and transport dynamics in an integrated surfacesubsurface modeling framework" 한국지질과학협의회 12 (12): 107-122, 2008

8 Ghosh, A., "Remote sensing image analysis with R"

9 Memon, B. A., "Quantitative analysis of springs" 26 : 111-120, 1995

10 Mohan, C., "Predicting groundwater recharge for varying land cover and climate conditions-a global meta-study" 22 : 2689-2703, 2018

11 Santos, A., "Package ‘landsat8’"

12 Rouse, J. W., "Monitoring vegetation systems in the great plains with ERTS" I : 309-312, 1973

13 Demattẻ, J. A. M., "Methodolody for bare soil detection and discrimination by Landsat TM image" 2 : 24-35, 2009

14 Sonmez, N. K., "Measuring intensity of tillage and plant residue cover using remote sensing" 49 : 121-135, 2016

15 Koroleva, P., "Location of bare soil surface and soil line on the RED-NIR spectral plane" 50 : 1375-1385, 2017

16 박승혁, "Landsat-8 위성을 통한 토지피복 변화와 지하수 함양량 상관성 고찰" 대한지질공학회 30 (30): 347-378, 2020

17 USGS, "Landsat 8 data users handbook"

18 McHugh, M. L., "Interrater reliability : the kappa statistic" 22 (22): 276-282, 2012

19 Sophocleous, M. A., "Integrated numerical modeling for basin-wide water management : The case of the Rattlesnake Creek basin in south-central Kansas" 214 : 179-196, 1999

20 Scanlon, B. R., "Impact of land use and land cover on groundwater recharge and quality in the southwestern US" 11 : 1577-1593, 2005

21 Perry Jr. C. R., "Functional equivalence of spectral vegetation indices" 14 : 169-182, 1984

22 Healy, R. W., "Estimating groundwater recharge" Cambridge University Press 2010

23 Jinno, K., "Effects of land-use change on groundwater recharge model parameters" 54 (54): 300-315, 2009

24 Serbin, G., "Effect on soil spectral properties on remote sensing of crop residue cover" 73 (73): 1545-1558, 2009

25 Rukundo, E., "Dominant influencing factors of groundwater recharge spatial patterns in Ergene river catchment, Turkey" 11 (11): 1-25, 2019

26 Richardson, A. J., "Distinguishing vegetation from soil background information" 43 : 1541-1552, 1977

27 Kim, N. W., "Development and applications of the integrated SWAT-MODFLOW model" 356 : 1-16, 2008

28 Breiman, L., "Classification and regression trees" Wadworth Books 358-, 1984

29 Goslee, S. C., "Analyzing remote sensing data in R : The landsat package" 43 (43): 1-14, 2011

30 Baret, F., "About the soil line concept in remote sensing" 13 (13): 281-284, 1993

31 Burke, D. G., "A novice experimental with satellite-based classification of agricultural crops and BMPs" Chesapeake Conservancy’s Conservation Innovation Center 6-8, 2014

32 Singhal, V., "A methodology based on spatial distribution of parameters for understanding affect of rainfall and vegetation density on groundwater recharge" 1 (1): 85-96, 2012