Groundwater Level Trend Analysis for Long-term Prediction Basedon Gaussian Process Regression

doi:10.7857/JSGE.2016.21.4.030

All Issue

2016 Vol.21, Issue 4 Preview Page Next Page

Groundwater Level Trend Analysis for Long-term Prediction Basedon Gaussian Process Regression 가우시안 프로세스 회귀분석을 이용한 지하수위 추세분석 및 장기예측 연구: 김효건;박은규;정진아;한원식;김구영;
Kim, Hyo Geon;Park, Eungyu;Jeong, Jina;Han, Weon Shik;Kim, Kue-Young;

31 August 2016. pp. 30 ~ 41

PDF

Abstract

The amount of groundwater related data is drastically increasing domestically from various sources since 2000. To justify the more expansive continuation of the data acquisition and to derive valuable implications from the data, continued employments of sophisticated and state-of-the-arts statistical tools in the analyses and predictions are important issue. In the present study, we employed a well established machine learning technique of Gaussian Process Regression (GPR) model in the trend analyses of groundwater level for the long-term change. The major benefit of GPR model is that the model provide not only the future predictions but also the associated uncertainty. In the study, the long-term predictions of groundwater level from the stations of National Groundwater Monitoring Network located within Han River Basin were exemplified as prediction cases based on the GPR model. In addition, a few types of groundwater change patterns were delineated (i.e., increasing, decreasing, and no trend) on the basis of the statistics acquired from GPR analyses. From the study, it was found that the majority of the monitoring stations has decreasing trend while small portion shows increasing or no trend. To further analyze the causes of the trend, the corresponding precipitation data were jointly analyzed by the same method (i.e., GPR). Based on the analyses, the major cause of decreasing trend of groundwater level is attributed to reduction of precipitation rate whereas a few of the stations show weak relationship between the pattern of groundwater level changes and precipitation.

Keywords

Gaussian process regression (GPR);Machine learning;Groundwater level trend analysis;National Groundwater Monitoring Network (NGMN);Han River basin;

References

Bazi, Y., Alajlan, N., and Melgani, F., 2012, Improved estimation of water chlorophyll concentration with semisupervised gaussian process regression, IEEE Transactions on Geoscience and Remote Sensing, 50(7), 2733-2743.10.1109/TGRS.2011.2174246
Cha, K., Cheong, T.S., and Ko, I., 2007, Validation of the surface-ground waters interaction and water supplying to upper region of geum river basin by optimal method for drought season, J. Korean Soc. Civil Eng. B, 27(5B), 507-513.
Evans, James D., 1996, Straightforward statistics for the behavioral sciences, Brooks/Cole, 600 p.
GIMS (National Groundwater Information Management and Service Center), 2015, available at http://www.gims.go.kr.
Grbić, R., Kurtagić , D., and Slišković, D., 2013, Stream water temperature prediction based on Gaussian process regression Expert Systems with Applications, 40(18), 7407-7414.10.1016/j.eswa.2013.06.077
Jang, S., Hamm, S.Y., Yoon, H., Kim, G.B., Park, J.H., and Kim, M.S., 2015, Predicting long-term change of groundwater level with regional climate model in South Korea, Geosci. J., 19(3), 503-513.10.1007/s12303-015-0002-9
Jeong, J.M., Park, Y.C., Jo, Y.J., and Lee, J.Y., 2010, Time series analysis of groundwater level fluctuation data in Cheonjeonri, Chuncheon, Gangwon-do, J. Geol. Soc. Korea, 46(2), 171-176.
Kim, B.S., Kwon, H.H., and Kim, H.S., 2011, Impact assessment of climate change on drought risk, J. Wetlands Res., 13(1), 1-11.
Kim, C.R., Kim, Y.O., Seo, S.B., and Choi, S.W., 2013, Water balance projection using climate change scenarios in the Korean Peninsula, J. Korea Water Resources Association, 46(8), 807-819.10.3741/JKWRA.2013.46.8.807
Kim, G., Choi, D., and Shin, S., 2011, Characteristics of groundwater levels fluctuation and quality in Ddan-sum area, J. Korean Geoenviron. Soc., 12(2), 35-43.
Kim, G.B. and Lee, S.H., 2012, Applicability of logistic regression model of groundwater levels to drought forecast, J. Geological Soc., 48(3), 275-284.
Kim, G.B. and Yum, B.W., 2007, Classification and characterization for water level time series of shallow wells at the national groundwater monitoring stations, J. Soil Groundw. Environ., 12(5), 86-97.
Kim, G.B., Yun, H.H., and Kim, D.H., 2006, Relationship between standardized precipitation index and groundwater levels: A proposal for establishment of drought index wells, J. Soil Groundw. Environ., 11(3), 31-42.
Kim, T.W. and Park, D.H., 2015, Extreme drought response and improvement - Focusing on 2015 drought, J. Korean Soc. Civil Eng., 63(9), 25-35.
Kim, Y.K., Yoo, J.A., and Chung, E.S., 2012, Water management vulnerability assessment considering climate change in Korea, J. Clim. Change Res., 3(1), 1-12.
KMA (Korea Meteorological Administration), 2015, available at http://www.kma.go.kr.
Kwon, H.J. and Kim, S.J., 2007, Methodology of drought assessment using national groundwater monitoring network data, J. Korean Soc. Civil Eng. B, 27(2B), 193-199.
Lee, B., Hamm, S.Y., Jang, S., Cheong, J.Y., and Kim, G.B., 2014, Relationship between groundwater and climate change in South Korea, Geosci. J., 18(2), 209-218.10.1007/s12303-013-0062-7
Lee, B.S., Kim, Y.I., Choi, K.J., Song, S.H., Kim, J.H., Woo, D.K., Seol, M.K., and Park, K.Y., 2014, Rural groundwater monitoring network in Korea, J. Soil Ground. Environ., 19(4), 1-11.
Lee, J.Y., Yi, M.J., Lee, J.M., Ahn, K.H., Won, J.H., Moon, S.H., and Cho, M., 2006, Parametric and non-parametric trend analysis of groundwater data obtained from national groundwater monitoring stations, J. Soil Groundw. Environ., 11(2), 56-67.
MOLIT (Ministry of Land, Infrastructure and Transport), 2011, Analysis report for long-term measured data from the national groundwater monitoring network in the Yeongsan and Seomjin River Basins, 211 p.
MOLIT (Ministry of Land, Infrastructure and Transport), 2014, Annual report for national groundwater monitoring network in Korea, 738 p.
Park, E., 2012, Delineation of recharge rate from a hybrid water table fluctuation method, Water Resources Research, 48(7), W07503.
Park, E. and Parker, J.C., 2008, A simple model for water table fluctuations in response to precipitation, J. Hydrol., 365(3-4), 344-349.
Park, J.Y., Yoo, J.Y., Lee, M., and Kim, T.W., 2012, Assessment of drought risk in Korea: Focused on data-based drought risk map, J. Korean Soc. Civil Eng. B, 32(4B), 203-211.10.12652/Ksce.2012.32.4B.203
Rasmussen, C.E., 2004, Gaussian processes in machine learning. In: Bousquet, O., von Luxburg, U. and Ratsch, G. (eds.), Adv. Lect. Mach. Learn., Springer, Berlin, p. 63-71.
Rasmussen, C.E. and Williams, C.K.I., 2006, Gaussian Processes for Machine Learning, The MIT Press, Cambridge, 266 p.
Sun, A.Y., Wang, D., and Xu, X., 2014, Monthly streamflow forecasting using Gaussian Process Regression, J. Hydrol., 511, 72-81.10.1016/j.jhydrol.2014.01.023
Yang, J.S., Park, J.H., and Kim, N.K., 2012, Development of drought vulnerability index using trend analysis, J. Korean Soc. Civil Eng. B, 32(3), 185-192.10.12652/Ksce.2012.32.5C.185
Yi, M.J., Kim, G.B., Sohn, Y.C., Lee, J.Y., and Lee, K.K., 2004, Time series analysis of groundwater level data obtained from national groundwater monitoring stations, J. Geol. Soc. Korea, 40(3), 305-329.

Information

Publisher :The Korean Society of Soil and Groundwater Environment
Publisher(Ko) :한국지하수토양환경학회
Journal Title :Journal of Soil and Groundwater Environment
Journal Title(Ko) :지하수토양환경
Volume : 21
No :4
Pages :30 ~ 41
DOI :https://doi.org/10.7857/JSGE.2016.21.4.030

[1] Bazi, Y., Alajlan, N., and Melgani, F., 2012, Improved estimation of water chlorophyll concentration with semisupervised gaussian process regression, IEEE Transactions on Geoscience and Remote Sensing, 50(7), 2733-2743.10.1109/TGRS.2011.2174246

[2] Cha, K., Cheong, T.S., and Ko, I., 2007, Validation of the surface-ground waters interaction and water supplying to upper region of geum river basin by optimal method for drought season, J. Korean Soc. Civil Eng. B, 27(5B), 507-513.

[3] Evans, James D., 1996, Straightforward statistics for the behavioral sciences, Brooks/Cole, 600 p.

[4] GIMS (National Groundwater Information Management and Service Center), 2015, available at http://www.gims.go.kr.

[5] Grbić, R., Kurtagić , D., and Slišković, D., 2013, Stream water temperature prediction based on Gaussian process regression Expert Systems with Applications, 40(18), 7407-7414.10.1016/j.eswa.2013.06.077

[6] Jang, S., Hamm, S.Y., Yoon, H., Kim, G.B., Park, J.H., and Kim, M.S., 2015, Predicting long-term change of groundwater level with regional climate model in South Korea, Geosci. J., 19(3), 503-513.10.1007/s12303-015-0002-9

[7] Jeong, J.M., Park, Y.C., Jo, Y.J., and Lee, J.Y., 2010, Time series analysis of groundwater level fluctuation data in Cheonjeonri, Chuncheon, Gangwon-do, J. Geol. Soc. Korea, 46(2), 171-176.

[8] Kim, B.S., Kwon, H.H., and Kim, H.S., 2011, Impact assessment of climate change on drought risk, J. Wetlands Res., 13(1), 1-11.

[9] Kim, C.R., Kim, Y.O., Seo, S.B., and Choi, S.W., 2013, Water balance projection using climate change scenarios in the Korean Peninsula, J. Korea Water Resources Association, 46(8), 807-819.10.3741/JKWRA.2013.46.8.807

[10] Kim, G., Choi, D., and Shin, S., 2011, Characteristics of groundwater levels fluctuation and quality in Ddan-sum area, J. Korean Geoenviron. Soc., 12(2), 35-43.

[11] Kim, G.B. and Lee, S.H., 2012, Applicability of logistic regression model of groundwater levels to drought forecast, J. Geological Soc., 48(3), 275-284.

[12] Kim, G.B. and Yum, B.W., 2007, Classification and characterization for water level time series of shallow wells at the national groundwater monitoring stations, J. Soil Groundw. Environ., 12(5), 86-97.

[13] Kim, G.B., Yun, H.H., and Kim, D.H., 2006, Relationship between standardized precipitation index and groundwater levels: A proposal for establishment of drought index wells, J. Soil Groundw. Environ., 11(3), 31-42.

[14] Kim, T.W. and Park, D.H., 2015, Extreme drought response and improvement - Focusing on 2015 drought, J. Korean Soc. Civil Eng., 63(9), 25-35.

[15] Kim, Y.K., Yoo, J.A., and Chung, E.S., 2012, Water management vulnerability assessment considering climate change in Korea, J. Clim. Change Res., 3(1), 1-12.

[16] KMA (Korea Meteorological Administration), 2015, available at http://www.kma.go.kr.

[17] Kwon, H.J. and Kim, S.J., 2007, Methodology of drought assessment using national groundwater monitoring network data, J. Korean Soc. Civil Eng. B, 27(2B), 193-199.

[18] Lee, B., Hamm, S.Y., Jang, S., Cheong, J.Y., and Kim, G.B., 2014, Relationship between groundwater and climate change in South Korea, Geosci. J., 18(2), 209-218.10.1007/s12303-013-0062-7

[19] Lee, B.S., Kim, Y.I., Choi, K.J., Song, S.H., Kim, J.H., Woo, D.K., Seol, M.K., and Park, K.Y., 2014, Rural groundwater monitoring network in Korea, J. Soil Ground. Environ., 19(4), 1-11.

[20] Lee, J.Y., Yi, M.J., Lee, J.M., Ahn, K.H., Won, J.H., Moon, S.H., and Cho, M., 2006, Parametric and non-parametric trend analysis of groundwater data obtained from national groundwater monitoring stations, J. Soil Groundw. Environ., 11(2), 56-67.

[21] MOLIT (Ministry of Land, Infrastructure and Transport), 2011, Analysis report for long-term measured data from the national groundwater monitoring network in the Yeongsan and Seomjin River Basins, 211 p.

[22] MOLIT (Ministry of Land, Infrastructure and Transport), 2014, Annual report for national groundwater monitoring network in Korea, 738 p.

[23] Park, E., 2012, Delineation of recharge rate from a hybrid water table fluctuation method, Water Resources Research, 48(7), W07503.

[24] Park, E. and Parker, J.C., 2008, A simple model for water table fluctuations in response to precipitation, J. Hydrol., 365(3-4), 344-349.

[25] Park, J.Y., Yoo, J.Y., Lee, M., and Kim, T.W., 2012, Assessment of drought risk in Korea: Focused on data-based drought risk map, J. Korean Soc. Civil Eng. B, 32(4B), 203-211.10.12652/Ksce.2012.32.4B.203

[26] Rasmussen, C.E., 2004, Gaussian processes in machine learning. In: Bousquet, O., von Luxburg, U. and Ratsch, G. (eds.), Adv. Lect. Mach. Learn., Springer, Berlin, p. 63-71.

[27] Rasmussen, C.E. and Williams, C.K.I., 2006, Gaussian Processes for Machine Learning, The MIT Press, Cambridge, 266 p.

[28] Sun, A.Y., Wang, D., and Xu, X., 2014, Monthly streamflow forecasting using Gaussian Process Regression, J. Hydrol., 511, 72-81.10.1016/j.jhydrol.2014.01.023

[29] Yang, J.S., Park, J.H., and Kim, N.K., 2012, Development of drought vulnerability index using trend analysis, J. Korean Soc. Civil Eng. B, 32(3), 185-192.10.12652/Ksce.2012.32.5C.185

[30] Yi, M.J., Kim, G.B., Sohn, Y.C., Lee, J.Y., and Lee, K.K., 2004, Time series analysis of groundwater level data obtained from national groundwater monitoring stations, J. Geol. Soc. Korea, 40(3), 305-329.

Journal of Soil and Groundwater Environment ISSN:1598-6438(Print) 2287-8831(Online) 지하수토양환경

All Issue