Modeling groundwater nitrate concentrations in private wells in Iowa

被引:116
作者
Wheeler, David C. [1 ]
Nolan, Bernard T. [2 ]
Flory, Abigail R. [3 ]
DellaValle, Curt T. [4 ]
Ward, Mary H. [4 ]
机构
[1] Virginia Commonwealth Univ, Dept Biostat, Richmond, VA 23298 USA
[2] US Geol Survey, Reston, VA 22092 USA
[3] Westat Corp, Rockville, MD USA
[4] NCI, Occupat & Environm Epidemiol Branch, Div Canc Epidemiol & Genet, Rockville, MD USA
关键词
Nitrate; Groundwater contamination; Random forest; UNITED-STATES; VULNERABILITY; WATER; POLLUTION; DRAINAGE;
D O I
10.1016/j.scitotenv.2015.07.080
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Contamination of drinking water by nitrate is a growing problem in many agricultural areas of the country. Ingested nitrate can lead to the endogenous formation of N-nitroso compounds, potent carcinogens. We developed a predictive model for nitrate concentrations in private wells in Iowa. Using 34,084 measurements of nitrate in private wells, we trained and tested random forest models to predict log nitrate levels by systematically assessing the predictive performance of 179 variables in 36 thematic groups (well depth, distance to sinkholes, location, land use, soil characteristics, nitrogen inputs, meteorology, and other factors). The final model contained 66 variables in 17 groups. Some of the most important variables were well depth, slope length within 1 km of the well, year of sample, and distance to nearest animal feeding operation. The correlation between observed and estimated nitrate concentrations was excellent in the training set (r-square = 0.77) and was acceptable in the testing set (r-square = 0.38). The random forest model had substantially better predictive performance than a traditional linear regressionmodel or a regression tree. Our model will be used to investigate the association between nitrate levels in drinking water and cancer risk in the Iowa participants of the Agricultural Health Study cohort. (C) 2015 Elsevier B.V. All rights reserved.
引用
收藏
页码:481 / 488
页数:8
相关论文
共 55 条
[31]   ESTIMATION OF NONPOINT SOURCE NITRATE CONCENTRATIONS IN INDIANA RIVERS BASED ON AGRICULTURAL DRAINAGE IN THE WATERSHED [J].
Jiang, Yan ;
Frankenberger, Jane R. ;
Sui, Yinghui ;
Bowling, Laura C. .
JOURNAL OF THE AMERICAN WATER RESOURCES ASSOCIATION, 2014, 50 (06) :1501-1514
[32]   Assigning land use to supply wells for the statistical characterization of regional groundwater quality: Correlating urban land use and VOC occurrence [J].
Johnson, Tyler D. ;
Belitz, Kenneth .
JOURNAL OF HYDROLOGY, 2009, 370 (1-4) :100-108
[33]  
Kross B., 1990, IOWA STATE WIDE RURA
[34]  
Landon MK, 2010, HYDROGEOL J, V18, P577, DOI 10.1007/s10040-009-0531-2
[35]  
Li Yong, 2006, Aquatic Ecosystem Health & Management, V9, P27, DOI 10.1080/14634980600559379
[36]   Epidemiologic evaluation of measurement data in the presence of detection limits [J].
Lubin, JH ;
Colt, JS ;
Camann, D ;
Davis, S ;
Cerhan, JR ;
Severson, RK ;
Bernstein, L ;
Hartge, P .
ENVIRONMENTAL HEALTH PERSPECTIVES, 2004, 112 (17) :1691-1696
[37]  
Mallarino A.P., 2006, Proceedings of the Integrated Crop Management Conference, Ames, V5, P198
[38]   Soil-Test N Recommendations Augmented with PEST-Optimized RZWQM Simulations [J].
Malone, R. W. ;
Jaynes, D. B. ;
Ma, L. ;
Nolan, B. T. ;
Meek, D. W. ;
Karlen, D. L. .
JOURNAL OF ENVIRONMENTAL QUALITY, 2010, 39 (05) :1711-1723
[39]   Nitrate Variability in Groundwater of North Carolina using Monitoring and Private Well Data Models [J].
Messier, Kyle P. ;
Kane, Evan ;
Bolich, Rick ;
Serre, Marc L. .
ENVIRONMENTAL SCIENCE & TECHNOLOGY, 2014, 48 (18) :10804-10812
[40]   Machine learning techniques to examine large patient databases [J].
Meyfroidt, Geert ;
Guiza, Fabian ;
Ramon, Jan ;
Bruynooghe, Maurice .
BEST PRACTICE & RESEARCH-CLINICAL ANAESTHESIOLOGY, 2009, 23 (01) :127-143