Browse > Article
http://dx.doi.org/10.7857/JSGE.2016.21.6.067

Applications of Gaussian Process Regression to Groundwater Quality Data  

Koo, Min-Ho (Department of Geoenvironmental Sciences, Kongju National University)
Park, Eungyu (Department of Geology, Kyungpook National University)
Jeong, Jina (Department of Geology, Kyungpook National University)
Lee, Heonmin (Department of Geology, Kyungpook National University)
Kim, Hyo Geon (Byucksan Engineering)
Kwon, Mijin (Korea Radioactive Waste Agency)
Kim, Yongsung (GeoGreen21 Co. Ltd.)
Nam, Sungwoo (GeoGreen21 Co. Ltd.)
Ko, Jun Young (Dohwa Engineering)
Choi, Jung Hoon (GeoInnovation)
Kim, Deog-Geun (Korea Water Resources Corporation)
Jo, Si-Beom (Korea Rural Community Corporation)
Publication Information
Journal of Soil and Groundwater Environment / v.21, no.6, 2016 , pp. 67-79 More about this Journal
Abstract
Gaussian process regression (GPR) is proposed as a tool of long-term groundwater quality predictions. The major advantage of GPR is that both prediction and the prediction related uncertainty are provided simultaneously. To demonstrate the applicability of the proposed tool, GPR and a conventional non-parametric trend analysis tool are comparatively applied to synthetic examples. From the application, it has been found that GPR shows better performance compared to the conventional method, especially when the groundwater quality data shows typical non-linear trend. The GPR model is further employed to the long-term groundwater quality predictions based on the data from two domestically operated groundwater monitoring stations. From the applications, it has been shown that the model can make reasonable predictions for the majority of the linear trend cases with a few exceptions of severely non-Gaussian data. Furthermore, for the data shows non-linear trend, GPR with mean of second order equation is successfully applied.
Keywords
Groundwater quality; Trend analysis; Gaussian process regression; Theil-Sen estimator; Groundwater quality monitoring network;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 Kim, G.B., Choi, D.H., Yoon, P.S., and Kim, K.Y., 2010, Trends of groundwater quality in the areas with a high possibility of pollution, J. Korean Geo-Environ. Soc., 11(3), 5-16.
2 Ministry of Environment (Korea), National Institute of Environmental Research (Korea), 2007-2013, National Groundwater Quality Monitoring Network Annual Report.
3 Bazi, Y., Alajlan, N., and Melgani, F., 2012, Improved Estimation of Water Chlorophyll Concentration With Semisupervised Gaussian Process Regression, IEEE Trans. Geosci. Remote Sensing, 50(7), 2733-2743.   DOI
4 Chapman, D., 1996, Water quality assessments: a guide to the use of biota, sediments, and water in environmental monitoring, UNESCO/WHO/UNEP, 22 p.
5 Grbi, R., Kurtagi, D., and Sli kovi, D., 2013, Stream water temperature prediction based on Gaussian process regression, Expert Sys. Applic., 40(18), 7407-7414.   DOI
6 Helsel, D.R. and Hirsch, R.M., 1988, Applicability of the t-Test for Detecting Trends in Water Quality Variables, J. American Water Resour. Assoc., 24(1), 201-204.   DOI
7 Helsel, D.R. and Hirsch, R.M., 2002, Statistical methods in water resources: US Geological Survey Techniques of Water Resources Investigations, book 4, chap. A3, U.S. Geological Survey.
8 Murphy, K.P., 2012, Machine Learning: a Probabilistic Perspective, The MIT Press, Cambridge, 1067 p.
9 Hirsch, R.M., Alexander, R.B., and Smith, R.A., 1991, Selection of methods for the detection and estimation of trends in water quality, Water Resour. Res., 27(5), 803-813.   DOI
10 Jarque, Carlos M., Bera, Anil K., 1987, A test for normality of observations and regression residuals, Int. Stat. Rev., 55(2), 163-172.   DOI
11 Sun, A.Y., Wang, D., and Xu, X., 2014, Monthly streamflow forecasting using Gaussian Process Regression, J. Hydro., 511, 72-81.   DOI
12 Hirsch, R.M., Slack, J.R., and Smith, R.A., 1982, Techniques of trend analysis for monthly water-quality data, Water Resour. Res., 18, 107-121.   DOI