{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T11:54:36Z","timestamp":1772452476718,"version":"3.50.1"},"reference-count":59,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T00:00:00Z","timestamp":1772236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Toxics"],"abstract":"<jats:p>Trace metal contamination in lotic freshwater systems exhibits pronounced heterogeneity arising from coupled hydrological connectivity, geochemical partitioning, and anthropogenic forcing, complicating exposure characterization in urban and peri-urban catchments. Addressing this complexity requires integrative analytical approaches capable of deciphering system-level controls, prompting an investigation of the environmental structuring and governing controls of dissolved trace metal signatures in a human-impacted stream using a system-oriented computational framework. To capture temporal variability associated with seasonal hydrological contrasts and heterogeneous pollution inputs, a station-based, season-resolved sampling strategy was implemented during the wet and dry seasons. Physicochemical gradients (pH, temperature, dissolved oxygen, and electrical conductivity), inorganic nitrogen species (NH3, NO2\u2212, and NO3\u2212), and phosphorus fractions (total phosphorus, TP; total orthophosphate, TOP; soluble reactive P, SRP) were jointly analyzed with dissolved concentrations of chromium (Cr), copper (Cu), nickel (Ni), lead (Pb), cadmium (Cd), mercury (Hg), and arsenic (As). Regression-based machine learning models were used to quantify element-specific sensitivities to hydrochemical drivers under wet\u2013dry periods and to identify optimal predictive configurations. Predictive performance was consistently high for trace metals (R2 generally &gt;0.95), with Random Forest providing the best accuracy for Cr, Ni, Pb, Cd, As, and Hg, whereas Cu was most reliably captured by an XGBoost tree ensemble (R2 = 0.994). Explainability analyses revealed heterogeneous, metal-specific control regimes: Cr was primarily driven by temperature, Ni by NO2\u2212 and redox-sensitive conditions, Cd by NH3 and temperature, and As by Hg in combination with phosphorus-related and redox-linked proxies, while Pb showed comparatively lower predictability relative to other metals. Trace metal distributions are therefore structured primarily by differential environmental sensitivity rather than uniform source-driven inputs, reinforcing the need for integrative computational frameworks when interpreting freshwater contamination under intensifying anthropogenic and climatic pressures.<\/jats:p>","DOI":"10.3390\/toxics14030215","type":"journal-article","created":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T10:24:34Z","timestamp":1772447074000},"page":"215","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Environmental Drivers and Explainable Modeling to Resolve Trace Metal Dynamics in a Lotic System"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5229-4181","authenticated-orcid":false,"given":"Akasya","family":"Top\u00e7u","sequence":"first","affiliation":[{"name":"Department of Fisheries and Aquaculture Engineering, Faculty of Agriculture, Ankara University, 06110 Ankara, T\u00fcrkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2705-299X","authenticated-orcid":false,"given":"Dilara","family":"Gerdan Ko\u00e7","sequence":"additional","affiliation":[{"name":"Department of Agricultural Machinery and Technologies Engineering, Graduate School of Applied and Natural Sciences, Ankara University, 06110 Ankara, T\u00fcrkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7404-5680","authenticated-orcid":false,"given":"\u0130lknur","family":"Meri\u00e7 Turgut","sequence":"additional","affiliation":[{"name":"Department of Fisheries and Aquaculture Engineering, Faculty of Agriculture, Ankara University, 06110 Ankara, T\u00fcrkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Serkan","family":"Ta\u015fdemir","sequence":"additional","affiliation":[{"name":"Department of Fisheries and Aquaculture Engineering, Graduate School of Applied and Natural Sciences, Ankara University, 06110 Ankara, T\u00fcrkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,28]]},"reference":[{"key":"ref_1","unstructured":"Intergovernmental Panel on Climate Change (IPCC) (2018). Global Warming of 1.5 \u00b0C, An IPCC Special Report."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"402","DOI":"10.1016\/j.ecolind.2017.12.068","article-title":"Indicators of sustainability to assess aquaculture systems","volume":"88","author":"Valenti","year":"2018","journal-title":"Ecol. Indic."},{"key":"ref_3","unstructured":"(2018). T\u00fcrkiye Y\u00fczeysel Su Kalitesi De\u011ferlendirme Raporu, (In Turkish)."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Singh, V., Singh, N., Rai, S.N., Kumar, A., Singh, A.K., Singh, M.P., Sahoo, A., Shekhar, S., Vamanu, E., and Mishra, V. (2023). Heavy metal contamination in the aquatic ecosystem: Toxicity and its remediation using eco-friendly approaches. Toxics, 11.","DOI":"10.3390\/toxics11020147"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1002\/esp.3290120302","article-title":"Copper dispersion in ephemeral stream sediments","volume":"12","author":"Marcus","year":"1987","journal-title":"Earth Surf. Process. Landf."},{"key":"ref_6","unstructured":"Kashefipour, S.M., and Roshanfekr, A. (2012). Numerical modelling of heavy metals transport processes in riverine basins. Numerical Modelling, IntechOpen."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"4071","DOI":"10.1002\/wrcr.20280","article-title":"Scaling and predicting solute transport processes in streams","volume":"49","author":"Haggerty","year":"2013","journal-title":"Water Resour. Res."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"45639","DOI":"10.1007\/s11356-020-10298-x","article-title":"Metal pollution assessment in surface sediments of Namak Lake, Iran","volume":"27","author":"Nodefarahani","year":"2020","journal-title":"Environ. Sci. Pollut. Res."},{"key":"ref_9","first-page":"81","article-title":"Hydro-environmental modelling of riverine basins using dynamic rate and partitioning coefficients","volume":"7","author":"Falconer","year":"2003","journal-title":"Hydrol. Earth Syst. Sci."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"3392","DOI":"10.1016\/j.scitotenv.2009.01.023","article-title":"Environmental modelling in the Gulf of Cadiz: Heavy metal distributions in water and sediments","volume":"407","year":"2009","journal-title":"Sci. Total Environ."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Prajapati, S., Sabokruhie, P., Brinkmann, M., and Lindenschmidt, K.-E. (2023). Modelling Transport and Fate of Copper and Nickel across the South Saskatchewan River Using WASP\u2014TOXI. Water, 15.","DOI":"10.3390\/w15020265"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"435","DOI":"10.1111\/j.1745-6584.2000.tb00230.x","article-title":"How the Kd approach undermines groundwater cleanup","volume":"38","author":"Bethke","year":"2000","journal-title":"Groundwater"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"13439","DOI":"10.1038\/s41598-020-70438-8","article-title":"A comparative analysis of artificial neural networks and wavelet hybrid approaches to long-term toxic heavy metal prediction","volume":"10","author":"Li","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Simionov, I.-A., Cristea, D.S., Petrea, \u0218.-M., Mogodan, A., Jijie, R., Ciornea, E., Nicoar\u0103, M., Turek Rahoveanu, M.M., and Cristea, V. (2021). Predictive Innovative Methods for Aquatic Heavy Metals Pollution Based on Bioindicators in Support of Blue Economy in the Danube River Basin. Sustainability, 13.","DOI":"10.3390\/su13168936"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"06009","DOI":"10.1051\/e3sconf\/202016306009","article-title":"Machine learning approach for simulation of heavy metal concentration in river water: The Crimean Peninsula case study","volume":"163","author":"Malygin","year":"2020","journal-title":"E3S Web Conf."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1188","DOI":"10.2166\/hydro.2023.151","article-title":"Temporal modelling of long-term heavy metal concentrations in aquatic ecosystems","volume":"25","author":"Bushra","year":"2023","journal-title":"J. Hydroinform."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1007\/s10653-024-01885-9","article-title":"Spatiotemporal variations, sources, pollution status and health risk assessment of dissolved trace elements in a major Arabian Sea draining river: Insights from multivariate statistical and machine learning approaches","volume":"46","author":"Singh","year":"2024","journal-title":"Environ. Geochem. Health"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"125148","DOI":"10.1016\/j.watres.2025.125148","article-title":"Using machine learning to predict heavy metal concentrations and induced health risks in drinking water distribution systems from key cities in China","volume":"291","author":"Zhang","year":"2025","journal-title":"Water Res."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"45333","DOI":"10.1038\/s41598-025-29598-8","article-title":"Explainable machine learning framework for assessing groundwater quality and trace element contamination in Eastern Saudi Arabia","volume":"15","author":"Aldrees","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"125367","DOI":"10.1016\/j.watres.2026.125367","article-title":"Linking hypolimnion to epilimnion in a stratified Arctic lake: Machine learning-based estimation of hypolimnetic water quality from epilimnetic measurements","volume":"231","author":"Mahdian","year":"2026","journal-title":"Water Res."},{"key":"ref_21","first-page":"134323","article-title":"Evolution of eutrophication in boreal lakes: Results from a half-century of in-situ measurements","volume":"612","author":"Noori","year":"2025","journal-title":"J. Hydrol."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Barrio-Parra, F., Izquierdo-D\u00edaz, M., Fern\u00e1ndez-Guti\u00e9rrez del \u00c1lamo, L.J., Biosca, B., and De Miguel, E. (2020). Modelling the transference of trace elements between environmental compartments in abandoned mining areas. Int. J. Environ. Res. Public Health, 17.","DOI":"10.3390\/ijerph17145117"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.26480\/wcm.02.2023.122.127","article-title":"Development of trace metal concentration model for rivers using PCA and artificial neural networks","volume":"7","author":"Faudzi","year":"2023","journal-title":"Water Conserv. Manag."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"012107","DOI":"10.1088\/1742-6596\/1899\/1\/012107","article-title":"Dynamical spatial model of heavy metals in Kendari bay using Bayesian geographical weighted regression","volume":"1899","author":"Mukhsar","year":"2021","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"163087","DOI":"10.1016\/j.scitotenv.2023.163087","article-title":"Modelling transport and fate of heavy metals at the watershed scale: State-of-the-art and future directions","volume":"878","author":"Zhou","year":"2023","journal-title":"Sci. Total Environ."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"242","DOI":"10.3846\/jeelm.2010.28","article-title":"Investigation into heavy metals in storm wastewater from Vilnius \u017dirm\u016bnai district and pollutantits spread model in Neris river","volume":"18","year":"2010","journal-title":"J. Environ. Eng. Landsc. Manag."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/s11270-017-3261-4","article-title":"The impact of climate change on metal transport in a lowland catchment","volume":"228","author":"Wijngaard","year":"2017","journal-title":"Water Air Soil Pollut."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1185","DOI":"10.1007\/s12237-019-00544-y","article-title":"A model-based analysis of metal fate in the Thames Estuary","volume":"42","author":"Premier","year":"2019","journal-title":"Estuaries Coasts"},{"key":"ref_29","first-page":"7","article-title":"A process for developing and evaluating design options for large-scale watershed remediation","volume":"23","author":"Ziemkiewicz","year":"2004","journal-title":"Mine Water Environ."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1007\/s10651-006-0022-8","article-title":"Spatial statistical models that use flow and stream distance","volume":"13","author":"Hoef","year":"2006","journal-title":"Environ. Ecol. Stat."},{"key":"ref_31","first-page":"177","article-title":"Spatial representation of surface water monitoring using geostatistical and non-geostatistical techniques in GIS","volume":"45","author":"Maliqi","year":"2019","journal-title":"Geod. Cartogr."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"032100","DOI":"10.1088\/1742-6596\/1015\/3\/032100","article-title":"Mathematical modelling for distribution of heavy metals in estuary area of Red River (Vietnam)","volume":"1015","author":"Volkova","year":"2018","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Mouazen, A., Nyarko, F., Qaswar, M., T\u00f3th, G., Gobin, A., and Moshou, D. (2021). Spatiotemporal prediction and mapping of heavy metals at regional scale using regression methods and remote sensing. Remote Sens., 13.","DOI":"10.3390\/rs13224615"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Fant, S., and Dortch, M. (2007). Documentation of A One-Dimensional, Time-Varying Contaminant Transport and Fate Model for Streams.","DOI":"10.21236\/ADA460827"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"49","DOI":"10.5194\/hess-5-49-2001","article-title":"A hydrochemical modelling framework for combined assessment of spatial and temporal variability in stream chemistry","volume":"5","author":"Foster","year":"2001","journal-title":"Hydrol. Earth Syst. Sci."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Motovilov, Y.G., and Fashchevskaya, T. (2021). Modeling management and climate change impacts on water pollution by heavy metals in a river watershed. Water, 13.","DOI":"10.3390\/w13223214"},{"key":"ref_37","first-page":"195","article-title":"Modelling the seasonal dynamics of heavy metal pollution of water bodies within a mining area","volume":"40","author":"Popovych","year":"2025","journal-title":"Rud. Geol. Naft. Zb."},{"key":"ref_38","first-page":"65","article-title":"Use of innovative and advanced computer simulations of chemical speciation of heavy metals in soils and environmental samples","volume":"65","author":"Jeske","year":"2014","journal-title":"Environ. Earth Sci."},{"key":"ref_39","first-page":"83","article-title":"Distribution of Oligochaeta species as bioindicators of organic pollution in Ankara Stream and their use in biomonitoring","volume":"22","author":"Girgin","year":"1998","journal-title":"Turk. J. Zool."},{"key":"ref_40","unstructured":"APHA (2012). Standard Methods for the Examination of Water and Wastewater, American Public Health Association, American Water Works Association, Water Environment Federation. [22nd ed.]."},{"key":"ref_41","unstructured":"APHA (1995). Standard Methods for the Examination of Water and Wastewater, American Public Health Association, American Water Works Association, Water Environment Federation. [19th ed.]."},{"key":"ref_42","unstructured":"(2002). Water Quality\u2014Digestion for the Determination of Selected Elements in Water\u2014Part 1: Aqua Regia Digestion. Standard No. TS EN ISO 15587-1:2002. Available online: https:\/\/www.tse.org.tr."},{"key":"ref_43","unstructured":"(2002). Water Quality\u2014Digestion for the Determination of Selected Elements in Water\u2014Part 2: Hydrochloric Acid Digestion. Standard No. TS EN ISO 15587-2:2002. Available online: https:\/\/www.tse.org.tr."},{"key":"ref_44","unstructured":"(2024). Water Quality\u2014Application of Inductively Coupled Plasma Mass Spectrometry (ICP-MS)\u2014Part 1: General Requirements. Standard No. TS EN ISO 17294-1:2024. Available online: https:\/\/www.tse.org.tr."},{"key":"ref_45","unstructured":"(2024). Water Quality\u2014Application of Inductively Coupled Plasma Mass Spectrometry (ICP-MS)\u2014Part 2: Determination of Selected Elements Including Protocol Details. Standard No. TS EN ISO 17294-2:2024. Available online: https:\/\/www.tse.org.tr."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 13\u201317 August 2016, Association for Computing Machinery.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_48","first-page":"321","article-title":"Multivariable functional interpolation and adaptive networks","volume":"2","author":"Broomhead","year":"1988","journal-title":"Complex Syst."},{"key":"ref_49","unstructured":"Haykin, S. (1999). Neural Networks: A Comprehensive Foundation, Prentice Hall. [2nd ed.]."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Draper, N.R., and Smith, H. (1998). Applied Regression Analysis, Wiley. [3rd ed.].","DOI":"10.1002\/9781118625590"},{"key":"ref_51","unstructured":"Montgomery, D.C., Peck, E.A., and Vining, G.G. (2012). Introduction to Linear Regression Analysis, Wiley. [5th ed.]."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Torres-Bejarano, F., Ram\u00edrez-Le\u00f3n, H., Rodr\u00edguez-Cuevas, C., Herrera-D\u00edaz, I.E., Hern\u00e1ndez-G\u00f3mez, J.J., Barrios-Pi\u00f1a, H., and Couder-Casta\u00f1eda, C. (2018). Modelling, Transport and Assessment of Aquatic Toxic Metals in Coastal Ecosystems. arXiv.","DOI":"10.20944\/preprints201804.0024.v1"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"158","DOI":"10.11113\/aej.v11.17052","article-title":"Application of Coupled HEC-HMS and US EPA WASP for Transport Modelling of Mercury in the Mining-Impacted Ambalanga River","volume":"11","author":"Macasieb","year":"2021","journal-title":"ASEAN Eng. J."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1007\/s10651-007-0015-2","article-title":"Model-Based Combination of Spatial Information for Stream Networks","volume":"14","author":"Handcock","year":"2007","journal-title":"Environ. Ecol. Stat."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1007\/s10661-024-12730-y","article-title":"A case study of using artificial neural networks to predict heavy metal pollution in Lake \u0130znik","volume":"196","author":"Mert","year":"2024","journal-title":"Environ. Monit. Assess."},{"key":"ref_56","first-page":"597","article-title":"Modeling the spatial distribution of soil heavy metals using Random Forest model\u2014A case study of Nairobi and Thirirka Rivers\u2019 confluence","volume":"12","author":"Omondi","year":"2020","journal-title":"J. Geogr. Inf. Syst."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/j.jhydrol.2012.12.004","article-title":"Performance evaluation of hydrological models: Statistical significance for reducing subjectivity in goodness-of-fit assessments","volume":"480","author":"Ritter","year":"2013","journal-title":"J. Hydrol."},{"key":"ref_58","first-page":"2162","article-title":"Machine learning-based analysis of trace metal contamination of Nwaniba river: Assessing the interplay between water and sediment","volume":"16","author":"Obadimu","year":"2025","journal-title":"J. Mater. Environ. Sci."},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1080\/26395940.2021.1978868","article-title":"Alarming carcinogenic and non-carcinogenic risk of heavy metals in Sabalan dam reservoir, Northwest of Iran","volume":"33","author":"Aradpour","year":"2021","journal-title":"Environ. Pollut. Bioavailab."}],"container-title":["Toxics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2305-6304\/14\/3\/215\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T10:58:11Z","timestamp":1772449091000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2305-6304\/14\/3\/215"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,28]]},"references-count":59,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["toxics14030215"],"URL":"https:\/\/doi.org\/10.3390\/toxics14030215","relation":{},"ISSN":["2305-6304"],"issn-type":[{"value":"2305-6304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,28]]}}}