2025 – Artificial intelligence-based optimization of the WEEE reverse chain in São Paulo − Brazil to promote economic, environmental and social benefits
Documento
Informações
Título
2025 - Artificial intelligence-based optimization of the WEEE reverse chain in São Paulo − Brazil to promote economic, environmental and social benefits
Título (EN)
2025 - Artificial intelligence-based optimization of the WEEE reverse chain in São Paulo − Brazil to promote economic, environmental and social benefits
Autor(es)
Geraldo C.de Oliveira Neto | Rodrigo Neri Bueno da Silva | Gustavo Araújo Lima | Sidnei Alves de Araújo | Peterson Adriano Belan | Denilson Carvalho | Cecília M.V.B. Almeida
Instituição
Universidade Paulista
Tipo
Artigo
Tipo de Mídia
Revista
Resumo (EN)
The rapid growth in electronic production has intensified e-waste generation, underscoring the need for efficient Waste Electrical and Electronic Equipment (WEEE) reverse logistics systems coordinated by manufacturers, retailers, and public agencies. However, in some parts of the world, such as in S˜ ao Paulo–Brazil, these systems still face substantial inefficiencies, resulting in increased environmental and social costs. This study focuses on applying artificial intelligence (AI) techniques to optimize the WEEE reverse logistics chain in Sao ˜ Paulo–Brazil,
aiming to generate economic, environmental, and social benefits. The proposed approach integrates genetic algorithms, greedy local search and tabu search techniques, to reorganize recyclers, redistribute collection points, and enhance vehicle routing, thereby reducing travel distances, collection times, and environmental impacts. Data were collected from manufacturers, recyclers, and waste management companies to develop AIbased strategies that improve operational practices. Environmental impact was assessed using the Material In
tensity Factor (MIF), revealing reductions in fuel consumption and greenhouse gas emissions, alongside societal benefits such as increased employment opportunities and improved occupational safety. The integration of AI with spatial data provides a practical tool for decision-makers, as evidenced by computational experiments
showing approximately a 30 % reduction in travel distances and a 20 % decrease in collection times. These improvements lead to lower operational costs and significant environmental benefits, including the mitigation of over 4.5 million tons per year in combined impacts related to resource use, water consumption, and atmospheric emissions. These outcomes underscore the broader economic, environmental, and social benefits of WEEE management, fully aligned with the United Nations Sustainable Development Goals.
Resumo
The rapid growth in electronic production has intensified e-waste generation, underscoring the need for efficient Waste Electrical and Electronic Equipment (WEEE) reverse logistics systems coordinated by manufacturers, retailers, and public agencies. However, in some parts of the world, such as in S˜ ao Paulo–Brazil, these systems still face substantial inefficiencies, resulting in increased environmental and social costs. This study focuses on applying artificial intelligence (AI) techniques to optimize the WEEE reverse logistics chain in Sao ˜ Paulo–Brazil,
aiming to generate economic, environmental, and social benefits. The proposed approach integrates genetic algorithms, greedy local search and tabu search techniques, to reorganize recyclers, redistribute collection points, and enhance vehicle routing, thereby reducing travel distances, collection times, and environmental impacts. Data were collected from manufacturers, recyclers, and waste management companies to develop AIbased strategies that improve operational practices. Environmental impact was assessed using the Material In
tensity Factor (MIF), revealing reductions in fuel consumption and greenhouse gas emissions, alongside societal benefits such as increased employment opportunities and improved occupational safety. The integration of AI with spatial data provides a practical tool for decision-makers, as evidenced by computational experiments
showing approximately a 30 % reduction in travel distances and a 20 % decrease in collection times. These improvements lead to lower operational costs and significant environmental benefits, including the mitigation of over 4.5 million tons per year in combined impacts related to resource use, water consumption, and atmospheric emissions. These outcomes underscore the broader economic, environmental, and social benefits of WEEE management, fully aligned with the United Nations Sustainable Development Goals.
Palavras-chave
Reverse logistic, WEEE Optimization, Artificial intelligence, Environmental assessment, Economic assessment, Social benefits
Direito de Acesso
Acesso restrito
Financiamento
FAPESP/CNPq