The Modeling of a River Impacted with Tailings Mudflows Based on the Differentiation of Spatiotemporal Domains and Assessment of Water–Sediment Interactions Using Machine Learning Approaches
The modeling of metal concentrations in large rivers is complex because the contributing factors are numerous, namely, the variation in metal sources across spatiotemporal domains. By considering both domains, this study modeled metal concentrations derived from the interaction of river water and se...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2024-01-01
|
Series: | Water |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-4441/16/3/379 |
_version_ | 1797318171860926464 |
---|---|
author | João Paulo Moura Fernando António Leal Pacheco Renato Farias do Valle Junior Maytê Maria Abreu Pires de Melo Silva Teresa Cristina Tarlé Pissarra Marília Carvalho de Melo Carlos Alberto Valera Luís Filipe Sanches Fernandes Glauco de Souza Rolim |
author_facet | João Paulo Moura Fernando António Leal Pacheco Renato Farias do Valle Junior Maytê Maria Abreu Pires de Melo Silva Teresa Cristina Tarlé Pissarra Marília Carvalho de Melo Carlos Alberto Valera Luís Filipe Sanches Fernandes Glauco de Souza Rolim |
author_sort | João Paulo Moura |
collection | DOAJ |
description | The modeling of metal concentrations in large rivers is complex because the contributing factors are numerous, namely, the variation in metal sources across spatiotemporal domains. By considering both domains, this study modeled metal concentrations derived from the interaction of river water and sediments of contrasting grain size and chemical composition, in regions of contrasting seasonal precipitation. Statistical methods assessed the processes of metal partitioning and transport, while artificial intelligence methods structured the dataset to predict the evolution of metal concentrations as a function of environmental changes. The methodology was applied to the Paraopeba River (Brazil), divided into sectors of coarse aluminum-rich natural sediments and sectors enriched in fine iron- and manganese-rich mine tailings, after the collapse of the B1 dam in Brumadinho, with 85–90% rainfall occurring from October to March. The prediction capacity of the random forest regressor was large for aluminum, iron and manganese concentrations, with average precision > 90% and accuracy < 0.2. |
first_indexed | 2024-03-08T03:46:41Z |
format | Article |
id | doaj.art-35a1c33997f94b60935c486ea4649743 |
institution | Directory Open Access Journal |
issn | 2073-4441 |
language | English |
last_indexed | 2024-03-08T03:46:41Z |
publishDate | 2024-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Water |
spelling | doaj.art-35a1c33997f94b60935c486ea46497432024-02-09T15:24:20ZengMDPI AGWater2073-44412024-01-0116337910.3390/w16030379The Modeling of a River Impacted with Tailings Mudflows Based on the Differentiation of Spatiotemporal Domains and Assessment of Water–Sediment Interactions Using Machine Learning ApproachesJoão Paulo Moura0Fernando António Leal Pacheco1Renato Farias do Valle Junior2Maytê Maria Abreu Pires de Melo Silva3Teresa Cristina Tarlé Pissarra4Marília Carvalho de Melo5Carlos Alberto Valera6Luís Filipe Sanches Fernandes7Glauco de Souza Rolim8CITAB—Centro de Investigação e Tecnologias Agroambientais e Biológicas, Universidade de Trás-os-Montes e Alto Douro, Ap. 1013, 5001-801 Vila Real, PortugalCQVR—Centro de Química de Vila Real, Universidade de Trás-os-Montes e Alto Douro, Ap. 1013, 5001-801 Vila Real, PortugalInstituto Federal do Triângulo Mineiro, Campus Uberaba, Laboratório de Geoprossessamento, Uberaba 38064-790, MG, BrazilInstituto Federal do Triângulo Mineiro, Campus Uberaba, Laboratório de Geoprossessamento, Uberaba 38064-790, MG, BrazilFaculdade de Ciências Agrárias e Veterinárias, Universidade Estadual Paulista (UNESP), Via de Acesso Prof. Paulo Donato Castellane, s/n, Jaboticabal 14884-900, SP, BrazilSecretaria de Estado de Meio Ambiente e Desenvolvimento Sustentável, Cidade Administrativa do Estado de Minas Gerais, Rodovia João Paulo II, 4143, Bairro Serra Verde, Belo Horizonte 31630-900, MG, BrazilRegional Coordination of Environmental Justice Promoters of the Paranaíba and Baixo Rio Grande River Basins, Rua Coronel Antônio Rios, 951, Uberaba 38061-150, MG, BrazilCITAB—Centro de Investigação e Tecnologias Agroambientais e Biológicas, Universidade de Trás-os-Montes e Alto Douro, Ap. 1013, 5001-801 Vila Real, PortugalFaculdade de Ciências Agrárias e Veterinárias, Universidade Estadual Paulista (UNESP), Via de Acesso Prof. Paulo Donato Castellane, s/n, Jaboticabal 14884-900, SP, BrazilThe modeling of metal concentrations in large rivers is complex because the contributing factors are numerous, namely, the variation in metal sources across spatiotemporal domains. By considering both domains, this study modeled metal concentrations derived from the interaction of river water and sediments of contrasting grain size and chemical composition, in regions of contrasting seasonal precipitation. Statistical methods assessed the processes of metal partitioning and transport, while artificial intelligence methods structured the dataset to predict the evolution of metal concentrations as a function of environmental changes. The methodology was applied to the Paraopeba River (Brazil), divided into sectors of coarse aluminum-rich natural sediments and sectors enriched in fine iron- and manganese-rich mine tailings, after the collapse of the B1 dam in Brumadinho, with 85–90% rainfall occurring from October to March. The prediction capacity of the random forest regressor was large for aluminum, iron and manganese concentrations, with average precision > 90% and accuracy < 0.2.https://www.mdpi.com/2073-4441/16/3/379riverspatiotemporal domainsediment sourcemetalsmachine learning prediction |
spellingShingle | João Paulo Moura Fernando António Leal Pacheco Renato Farias do Valle Junior Maytê Maria Abreu Pires de Melo Silva Teresa Cristina Tarlé Pissarra Marília Carvalho de Melo Carlos Alberto Valera Luís Filipe Sanches Fernandes Glauco de Souza Rolim The Modeling of a River Impacted with Tailings Mudflows Based on the Differentiation of Spatiotemporal Domains and Assessment of Water–Sediment Interactions Using Machine Learning Approaches Water river spatiotemporal domain sediment source metals machine learning prediction |
title | The Modeling of a River Impacted with Tailings Mudflows Based on the Differentiation of Spatiotemporal Domains and Assessment of Water–Sediment Interactions Using Machine Learning Approaches |
title_full | The Modeling of a River Impacted with Tailings Mudflows Based on the Differentiation of Spatiotemporal Domains and Assessment of Water–Sediment Interactions Using Machine Learning Approaches |
title_fullStr | The Modeling of a River Impacted with Tailings Mudflows Based on the Differentiation of Spatiotemporal Domains and Assessment of Water–Sediment Interactions Using Machine Learning Approaches |
title_full_unstemmed | The Modeling of a River Impacted with Tailings Mudflows Based on the Differentiation of Spatiotemporal Domains and Assessment of Water–Sediment Interactions Using Machine Learning Approaches |
title_short | The Modeling of a River Impacted with Tailings Mudflows Based on the Differentiation of Spatiotemporal Domains and Assessment of Water–Sediment Interactions Using Machine Learning Approaches |
title_sort | modeling of a river impacted with tailings mudflows based on the differentiation of spatiotemporal domains and assessment of water sediment interactions using machine learning approaches |
topic | river spatiotemporal domain sediment source metals machine learning prediction |
url | https://www.mdpi.com/2073-4441/16/3/379 |
work_keys_str_mv | AT joaopaulomoura themodelingofariverimpactedwithtailingsmudflowsbasedonthedifferentiationofspatiotemporaldomainsandassessmentofwatersedimentinteractionsusingmachinelearningapproaches AT fernandoantoniolealpacheco themodelingofariverimpactedwithtailingsmudflowsbasedonthedifferentiationofspatiotemporaldomainsandassessmentofwatersedimentinteractionsusingmachinelearningapproaches AT renatofariasdovallejunior themodelingofariverimpactedwithtailingsmudflowsbasedonthedifferentiationofspatiotemporaldomainsandassessmentofwatersedimentinteractionsusingmachinelearningapproaches AT maytemariaabreupiresdemelosilva themodelingofariverimpactedwithtailingsmudflowsbasedonthedifferentiationofspatiotemporaldomainsandassessmentofwatersedimentinteractionsusingmachinelearningapproaches AT teresacristinatarlepissarra themodelingofariverimpactedwithtailingsmudflowsbasedonthedifferentiationofspatiotemporaldomainsandassessmentofwatersedimentinteractionsusingmachinelearningapproaches AT mariliacarvalhodemelo themodelingofariverimpactedwithtailingsmudflowsbasedonthedifferentiationofspatiotemporaldomainsandassessmentofwatersedimentinteractionsusingmachinelearningapproaches AT carlosalbertovalera themodelingofariverimpactedwithtailingsmudflowsbasedonthedifferentiationofspatiotemporaldomainsandassessmentofwatersedimentinteractionsusingmachinelearningapproaches AT luisfilipesanchesfernandes themodelingofariverimpactedwithtailingsmudflowsbasedonthedifferentiationofspatiotemporaldomainsandassessmentofwatersedimentinteractionsusingmachinelearningapproaches AT glaucodesouzarolim themodelingofariverimpactedwithtailingsmudflowsbasedonthedifferentiationofspatiotemporaldomainsandassessmentofwatersedimentinteractionsusingmachinelearningapproaches AT joaopaulomoura modelingofariverimpactedwithtailingsmudflowsbasedonthedifferentiationofspatiotemporaldomainsandassessmentofwatersedimentinteractionsusingmachinelearningapproaches AT fernandoantoniolealpacheco modelingofariverimpactedwithtailingsmudflowsbasedonthedifferentiationofspatiotemporaldomainsandassessmentofwatersedimentinteractionsusingmachinelearningapproaches AT renatofariasdovallejunior modelingofariverimpactedwithtailingsmudflowsbasedonthedifferentiationofspatiotemporaldomainsandassessmentofwatersedimentinteractionsusingmachinelearningapproaches AT maytemariaabreupiresdemelosilva modelingofariverimpactedwithtailingsmudflowsbasedonthedifferentiationofspatiotemporaldomainsandassessmentofwatersedimentinteractionsusingmachinelearningapproaches AT teresacristinatarlepissarra modelingofariverimpactedwithtailingsmudflowsbasedonthedifferentiationofspatiotemporaldomainsandassessmentofwatersedimentinteractionsusingmachinelearningapproaches AT mariliacarvalhodemelo modelingofariverimpactedwithtailingsmudflowsbasedonthedifferentiationofspatiotemporaldomainsandassessmentofwatersedimentinteractionsusingmachinelearningapproaches AT carlosalbertovalera modelingofariverimpactedwithtailingsmudflowsbasedonthedifferentiationofspatiotemporaldomainsandassessmentofwatersedimentinteractionsusingmachinelearningapproaches AT luisfilipesanchesfernandes modelingofariverimpactedwithtailingsmudflowsbasedonthedifferentiationofspatiotemporaldomainsandassessmentofwatersedimentinteractionsusingmachinelearningapproaches AT glaucodesouzarolim modelingofariverimpactedwithtailingsmudflowsbasedonthedifferentiationofspatiotemporaldomainsandassessmentofwatersedimentinteractionsusingmachinelearningapproaches |