Novel hybrid methods applied for spatial prediction of mercury and variable selection of trace elements in coastal areas of USA.

This study was concerned with spatial analysis of mercury (Hg) in sediment samples of the USA coastal areas using more accurate and stable hybrid approaches compared to the conventional methods. An ensemble of simulated annealing along with least angle regression (SA-LAR) was applied for selection of predictors in spatial analysis. The latest algorithm was efficient with resultant RMSE and R2 of 0.066 and 0.705 compared to 0.099 and 0.571 for the traditional method of recursive feature elimination (RFE) approach. Using Cu, Pb and As as selected variables, it was tried to improve the spatial forecasting of Hg with either a hybrid of generalized boosted regression and ordinary kriging (GBROK) or inverse distance weighting (GBRIDW). According to the results, the variance explained by cross validation (VECV) was improved from 7.52% and 9.76% for IDW and OK to 40.41% and 41.94% for the GBRIDW and GBROK methods, respectively.

[1]  S. Chrétien,et al.  Dendrochemical assessment of mercury releases from a pond and dredged-sediment landfill impacted by a chlor-alkali plant. , 2016, Environmental research.

[2]  S. Lacorte,et al.  Temporal and Spatial Distribution of Mercury in Gulls Eggs from the Iberian Peninsula , 2018, Archives of Environmental Contamination and Toxicology.

[3]  WANGKe,et al.  Neural Network Ensemble Residual Kriging Application for Spatial Variability of Soil Properties , 2004 .

[4]  J. Diamond,et al.  Use of man-made impoundment in mitigating acid mine drainage in the North Branch Potomac River , 1993 .

[5]  Clayton V. Deutsch,et al.  Collocated Cokriging Based on Merged Secondary Attributes , 2009 .

[6]  Guijian Liu,et al.  Geochemical normalization and assessment of heavy metals (Cu, Pb, Zn, and Ni) in sediments from the Huaihe River, Anhui, China , 2015 .

[7]  C. Vane,et al.  PAH, PCB, TPH and mercury in surface sediments of the Delaware River Estuary and Delmarva Peninsula, USA. , 2017, Marine pollution bulletin.

[8]  J. A. Mueller,et al.  Contaminant inputs to the Hudson-Raritan estuary , 1982 .

[9]  Daizhou Zhang,et al.  Spatial distribution characteristics of mercury in the soils and native earthworms (Bimastos parvus) of the leachate-contaminated zone around a traditional landfill. , 2018, The Science of the total environment.

[10]  Luca Montanarella,et al.  Prediction of Soil Organic Carbon at the European Scale by Visible and Near InfraRed Reflectance Spectroscopy , 2013, PloS one.

[11]  Timothy C. Coburn,et al.  Geostatistics for Natural Resources Evaluation , 2000, Technometrics.

[12]  N. Chandrasekar,et al.  Geospatial risk assessment and trace element concentration in reef associated sediments, northern part of Gulf of Mannar biosphere reserve, Southeast Coast of India. , 2017, Marine pollution bulletin.

[13]  Jin Li,et al.  Application of machine learning methods to spatial interpolation of environmental variables , 2011, Environ. Model. Softw..

[14]  Yong Yang,et al.  Spatiotemporal modeling and prediction of soil heavy metals based on spatiotemporal cokriging , 2017, Scientific Reports.

[15]  G. Quaranta,et al.  Heavy metal contamination of coastal lagoon sediments by anthropogenic activities: the case of Nador (East Morocco) , 2009 .

[16]  Omar Assobhei,et al.  Environmental and ecological risk assessment of heavy metals in sediments of Nador lagoon, Morocco , 2015 .

[17]  D. Myers.  Matrix formulation of co-kriging , 1982 .

[18]  Kabindra Adhikari,et al.  Role of environmental variables in the spatial distribution of soil carbon (C), nitrogen (N), and C:N ratio from the northeastern coastal agroecosystems in China , 2018 .

[19]  Xian-liang Wang,et al.  Heavy metals in soils from a typical county in Shanxi Province, China: Levels, sources and spatial distribution. , 2016, Chemosphere.

[20]  Majdi M. Mafarja,et al.  Hybrid Whale Optimization Algorithm with simulated annealing for feature selection , 2017, Neurocomputing.

[21]  V. Rodriguez-Galiano,et al.  Predictive modeling of groundwater nitrate pollution using Random Forest and multisource variables related to intrinsic and specific vulnerability: a case study in an agricultural setting (Southern Spain). , 2014, The Science of the total environment.

[22]  João Felipe C. L. Costa,et al.  Uncertainty Estimate in Resources Assessment: A Geostatistical Contribution , 2004 .

[23]  B. Schröder,et al.  Estimation of suspended sediment concentration and yield using linear models, random forests and quantile regression forests , 2008 .

[24]  Jianming Xu,et al.  Characterizing the risk assessment of heavy metals and sampling uncertainty analysis in paddy field by geostatistics and GIS. , 2006, Environmental pollution.

[25]  Gangcai Liu,et al.  Spatial prediction of soil organic matter content integrating artificial neural network and ordinary kriging in Tibetan Plateau , 2014 .

[26]  S. Vincenzi,et al.  Application of a Random Forest algorithm to predict spatial distribution of the potential yield of Ruditapes philippinarum in the Venice lagoon, Italy , 2011 .

[27]  Gabor Kereszturi,et al.  Integrating Airborne Hyperspectral, Topographic, and Soil Data for Estimating Pasture Quality Using Recursive Feature Elimination with Random Forest Regression , 2018, Remote. Sens..

[28]  Fred D. Calder,et al.  Natural trace metal concentrations in estuarine and coastal marine sediments of the southeastern United States , 1989 .

[29]  J. Friedman.  Stochastic gradient boosting , 2002 .

[30]  Bhanu Pandey,et al.  Ecological risk assessment of soil contamination by trace elements around coal mining area , 2015, Journal of Soils and Sediments.

[31]  D. Bui,et al.  A comparative assessment of support vector regression, artificial neural networks, and random forests for predicting and mapping soil organic carbon stocks across an Afromontane landscape. , 2015 .

[32]  Ling Chen,et al.  An extended study on historical mercury accumulation in lake sediment of Shanghai: The contribution of socioeconomic driver. , 2016, Environmental pollution.

[33]  Annamaria Castrignanò,et al.  Assessing heavy metal contamination in soils of the Zagreb region (Northwest Croatia) using multivariate geostatistics , 2010 .

[34]  M. Söderström,et al.  Cokriging of Heavy Metals as an Aid to Biogeochemical Mapping , 1996 .

[35]  J. Burger,et al.  Lead (Pb) in Biota and Perceptions of Pb Exposure at a Recently Designated Superfund Beach Site in New Jersey , 2012, Journal of toxicology and environmental health. Part A.

[36]  B. Pradhan,et al.  A comparative study of logistic model tree, random forest, and classification and regression tree models for spatial prediction of landslide susceptibility , 2017 .

[37]  D. Loring.  Normalization of heavy-metal data from estuarine and coastal sediments , 1991 .

[38]  Z. Szabó,et al.  An assessment of mercury in estuarine sediment and tissue in Southern New Jersey using public domain data. , 2016, Marine pollution bulletin.

[39]  Michael Edward Hohn,et al.  An Introduction to Applied Geostatistics: by Edward H. Isaaks and R. Mohan Srivastava, 1989, Oxford University Press, New York, 561 p., ISBN 0-19-505012-6, ISBN 0-19-505013-4 (paperback), $55.00 cloth, $35.00 paper (US) , 1991 .

[40]  Tomislav Hengl,et al.  Improving performance of spatio-temporal machine learning models using forward feature selection and target-oriented validation , 2018, Environ. Model. Softw..

[41]  Jin Li,et al.  Assessing spatial predictive models in the environmental sciences: Accuracy measures, data variation and variance explained , 2016, Environ. Model. Softw..

[42]  Simon X. Yang,et al.  A comparative study for least angle regression on NIR spectra analysis to determine internal qualities of navel oranges , 2015, Expert Syst. Appl..

[43]  Melissa M. Hughes,et al.  Six decades of change in pollution and benthic invertebrate biodiversity in a southern New England estuary. , 2018, Marine pollution bulletin.

[44]  A. Potter,et al.  Can we improve the spatial predictions of seabed sediments? A case study of spatial interpolation of mud content across the southwest Australian margin , 2011 .

[45]  P. Roy,et al.  Metals and their ecological impact on beach sediments near the marine protected sites of Sodwana Bay and St. Lucia, South Africa. , 2018, Marine pollution bulletin.

[46]  Bin Dai,et al.  Identifying the origins and spatial distributions of heavy metals in soils of Ju country (Eastern China) using multivariate and geostatistical approach , 2014, Journal of Soils and Sediments.

[47]  R. Greig,et al.  Trace metals in sediments of Raritan bay , 1977 .

[48]  L. Håkanson.  An ecological risk index for aquatic pollution control.a sedimentological approach , 1980 .

[49]  P. Goovaerts.  Ordinary Cokriging Revisited , 1998 .

[50]  Alistair Grinham,et al.  Random forest algorithm yields accurate quantitative prediction models of benthic light at intertidal sites affected by toxic Lyngbya majuscula blooms , 2012 .

[51]  Alex B. McBratney,et al.  An overview of pedometric techniques for use in soil survey , 2000 .

[52]  T. G. Orton,et al.  Evaluation of modelling approaches for predicting the spatial distribution of soil organic carbon stocks at the national scale , 2014, 1502.02513.

[53]  Feng Liu,et al.  Comparison of boosted regression tree and random forest models for mapping topsoil organic carbon concentration in an alpine ecosystem , 2016 .

[54]  R. Tucker,et al.  Lead and copper in the waters of Raritan and Lower New York Bays , 1978 .

[55]  Martial Bernoux,et al.  Mapping organic carbon stocks in eucalyptus plantations of the central highlands of Madagascar: A multiple regression approach , 2011 .

[56]  Monitoring changes in salinity and metal concentrations in New Jersey (USA) coastal ecosystems Post-Hurricane Sandy , 2015, Environmental Earth Sciences.

[57]  M. Thies,et al.  A comparison of factors affecting the small-scale distribution of mercury from artisanal small-scale gold mining in a Zimbabwean stream system. , 2019, The Science of the total environment.

[58]  Jacob Zahavi,et al.  Using simulated annealing to optimize the feature selection problem in marketing applications , 2006, Eur. J. Oper. Res..

[59]  B. Huwe,et al.  Uncertainty in the spatial prediction of soil texture: Comparison of regression tree and Random Forest models , 2012 .

[60]  C. Douvris,et al.  Investigation of the metal content of sediments around the historically polluted Potomac River basin in Washington D.C., United States by inductively coupled plasma-optical emission spectroscopy (ICP-OES) , 2018, Microchemical Journal.

[61]  Yu Zhao,et al.  Comprehensive analysis of mercury pollution in the surface riverine sediments in the Haihe Basin, China , 2017, Environmental Science and Pollution Research.

[62]  D. Colby,et al.  Assessment of elemental contamination in estuarine and coastal environments based on geochemical and statistical modeling of sediments , 1993 .

[63]  Zne-Jung Lee,et al.  Parameter determination of support vector machine and feature selection using simulated annealing approach , 2008, Appl. Soft Comput..

[64]  Seyed Amir Naghibi,et al.  GIS-based groundwater potential mapping using boosted regression tree, classification and regression tree, and random forest machine learning models in Iran , 2015, Environmental Monitoring and Assessment.

[65]  J. Yamamoto.  Correcting the Smoothing Effect of Ordinary Kriging Estimates , 2005 .

[66]  P. Martín‐Ramos,et al.  Evolution of mercury content in agricultural soils due to the application of organic and mineral fertilizers , 2017, Journal of Soils and Sediments.

[67]  K. Thomas,et al.  A review of factors affecting the release and bioavailability of contaminants during sediment disturbance events. , 2004, Environment international.

[68]  J. Corella,et al.  700 years reconstruction of mercury and lead atmospheric deposition in the Pyrenees (NE Spain) , 2017 .

[69]  Max Kuhn,et al.  The caret Package , 2007 .

[70]  R. Macdonald,et al.  Spatiotemporal patterns of mercury accumulation in lake sediments of western North America. , 2016, The Science of the total environment.

[71]  J. Clevers,et al.  Identification of soil heavy metal sources and improvement in spatial mapping based on soil spectral information: A case study in northwest China. , 2016, The Science of the total environment.

[72]  P. Goovaerts.  Factorial kriging analysis: a useful tool for exploring the structure of multivariate spatial soil information , 1992 .

[73]  E. Zhang,et al.  Spatial distribution, contamination and ecological risk assessment of heavy metals in surface sediments of Erhai Lake, a large eutrophic plateau lake in southwest China , 2016 .

[74]  Hao Xu,et al.  Spatial distribution, risk assessment and source identification of heavy metals in sediments of the Yangtze River Estuary, China. , 2017, Marine pollution bulletin.