Predicting carbon footprint in stochastic dynamic routing using Bayesian Markov random fields

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade de São Paulo (USP)-
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.creatorDesuó Neto, Luiz-
Autor(es): dc.creatorCaetano, Henrique de Oliveira-
Autor(es): dc.creatorFogliatto, Matheus de Souza Sant'Anna-
Autor(es): dc.creatorMaciel, Carlos Dias-
Data de aceite: dc.date.accessioned2025-08-21T17:35:05Z-
Data de disponibilização: dc.date.available2025-08-21T17:35:05Z-
Data de envio: dc.date.issued2025-04-29-
Data de envio: dc.date.issued2025-06-01-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1016/j.eswa.2025.127137-
Fonte completa do material: dc.identifierhttps://hdl.handle.net/11449/304499-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/304499-
Descrição: dc.descriptionEvaluating carbon emissions in last-mile logistics is critical for achieving climate goals, yet current models lack integration of spatiotemporal traffic dynamics and climate factors. This study aims to (1) develop a Bayesian Markov random field model integrating spatiotemporal traffic data and speed scenarios influenced by precipitation, (2) quantify carbon dioxide emissions from last-mile logistics illustrated by maintenance dispatches in power distribution systems using a widely recognized traffic speed to CO2 conversion method, and (3) provide actionable strategies for reducing emissions in last-mile logistics. Achieving a traffic speed prediction accuracy with an approximate error of 2%, the proposed model quantified carbon emissions under dynamic routing conditions. Simulation results from maintenance dispatches in power distribution systems indicate that, under average failure conditions, the annual carbon emissions from two teams operating in São Paulo are equivalent to the carbon dioxide absorbed by approximately five hectares of trees. These findings underscore the critical importance of incorporating environmental considerations into reliability assessments. While the study focuses on power distribution systems, the proposed framework is broadly applicable to any last-mile logistics problem, offering actionable insights—such as optimizing dispatch frequencies—to minimize emissions. By addressing the cumulative environmental impact of routine operations, this research supports the transition to carbon-neutral last-mile services and promotes responsible logistics practices across industries worldwide.-
Descrição: dc.descriptionCoordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)-
Descrição: dc.descriptionFundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)-
Descrição: dc.descriptionInternational Business Machines Corporation-
Descrição: dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)-
Descrição: dc.descriptionDepartment of Electrical and Computer Engineering University of São Paulo (USP), 400 Trabalhador São Carlense Ave., SP-
Descrição: dc.descriptionDepartment of Electrical Engineering São Paulo State University (UNESP), 333 Ariberto Pereira da Cunha Ave., SP-
Descrição: dc.descriptionDepartment of Electrical Engineering São Paulo State University (UNESP), 333 Ariberto Pereira da Cunha Ave., SP-
Descrição: dc.descriptionFAPESP: 2014/50851-0-
Descrição: dc.descriptionCNPq: 2018/19150-6-
Descrição: dc.descriptionFAPESP: 2019/07665-4-
Descrição: dc.descriptionCNPq: 465755/2014-3-
Idioma: dc.languageen-
Relação: dc.relationExpert Systems with Applications-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectBayesian Markov random fields-
Palavras-chave: dc.subjectCarbon footprint prediction-
Palavras-chave: dc.subjectLast-mile logistics-
Palavras-chave: dc.subjectMulti-layer systems-
Palavras-chave: dc.subjectStochastic dynamic routing-
Título: dc.titlePredicting carbon footprint in stochastic dynamic routing using Bayesian Markov random fields-
Tipo de arquivo: dc.typelivro digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.