Mobina Mousapour Mamoudan , Ali Jafari , Zahra Mohammadnazari , Mohammad Mahdi Nasiri , Maziar Yazdani
{"title":"缺水条件下可持续农业食品生产和供应链规划的混合机器学习元启发式模型","authors":"Mobina Mousapour Mamoudan , Ali Jafari , Zahra Mohammadnazari , Mohammad Mahdi Nasiri , Maziar Yazdani","doi":"10.1016/j.resenv.2023.100133","DOIUrl":null,"url":null,"abstract":"<div><p>Agriculture is of great importance in all societies, serving as the fundamental basis for producing food and ensuring the survival of human populations. The process of agricultural production and the associated logistical elements face numerous difficulties, which are further intensified by the worldwide water scarcity resulting from climate change. Nevertheless, the existing body of literature has not sufficiently addressed the consequences of water scarcity on agri-food supply chains. To bridge this research gap and contribute to mitigating the global water crisis induced by climate change, this study proposes a hybrid model that combines optimized neural networks based on meta-heuristic algorithms and mathematical optimization for a sustainable agricultural supply chain. The proposed model integrates particle swarm optimization (PSO) for feature selection and a hybrid convolutional neural network (CNN)-gated recurrent unit (GRU) with a genetic algorithm (GA) optimized structure to predict water consumption. Leveraging the model’s results, a multi-objective sustainable agriculture supply chain model is developed to optimize supply chain profitability while simultaneously addressing environmental pollutants, production waste, food waste, water usage, and manufacturing costs and time. To evaluate the effectiveness of the proposed approach, a real case study in Iran is employed, providing both theoretical and practical insights into the design of agriculture supply chain optimization that incorporates sustainability factors and effectively tackles the growing challenge of water scarcity. The findings of this study hold implications for managers and policymakers in countries where the importance of sustainability is growing. By integrating advanced optimization techniques and predictive models, this research offers a novel framework for enhancing the sustainability of agricultural supply chains and addressing the pressing issues of water scarcity induced by climate change.</p></div>","PeriodicalId":34479,"journal":{"name":"Resources Environment and Sustainability","volume":null,"pages":null},"PeriodicalIF":12.4000,"publicationDate":"2023-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Hybrid machine learning-metaheuristic model for sustainable agri-food production and supply chain planning under water scarcity\",\"authors\":\"Mobina Mousapour Mamoudan , Ali Jafari , Zahra Mohammadnazari , Mohammad Mahdi Nasiri , Maziar Yazdani\",\"doi\":\"10.1016/j.resenv.2023.100133\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Agriculture is of great importance in all societies, serving as the fundamental basis for producing food and ensuring the survival of human populations. The process of agricultural production and the associated logistical elements face numerous difficulties, which are further intensified by the worldwide water scarcity resulting from climate change. Nevertheless, the existing body of literature has not sufficiently addressed the consequences of water scarcity on agri-food supply chains. To bridge this research gap and contribute to mitigating the global water crisis induced by climate change, this study proposes a hybrid model that combines optimized neural networks based on meta-heuristic algorithms and mathematical optimization for a sustainable agricultural supply chain. The proposed model integrates particle swarm optimization (PSO) for feature selection and a hybrid convolutional neural network (CNN)-gated recurrent unit (GRU) with a genetic algorithm (GA) optimized structure to predict water consumption. Leveraging the model’s results, a multi-objective sustainable agriculture supply chain model is developed to optimize supply chain profitability while simultaneously addressing environmental pollutants, production waste, food waste, water usage, and manufacturing costs and time. To evaluate the effectiveness of the proposed approach, a real case study in Iran is employed, providing both theoretical and practical insights into the design of agriculture supply chain optimization that incorporates sustainability factors and effectively tackles the growing challenge of water scarcity. The findings of this study hold implications for managers and policymakers in countries where the importance of sustainability is growing. By integrating advanced optimization techniques and predictive models, this research offers a novel framework for enhancing the sustainability of agricultural supply chains and addressing the pressing issues of water scarcity induced by climate change.</p></div>\",\"PeriodicalId\":34479,\"journal\":{\"name\":\"Resources Environment and Sustainability\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":12.4000,\"publicationDate\":\"2023-08-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Resources Environment and Sustainability\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2666916123000269\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENVIRONMENTAL SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Resources Environment and Sustainability","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2666916123000269","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
Hybrid machine learning-metaheuristic model for sustainable agri-food production and supply chain planning under water scarcity
Agriculture is of great importance in all societies, serving as the fundamental basis for producing food and ensuring the survival of human populations. The process of agricultural production and the associated logistical elements face numerous difficulties, which are further intensified by the worldwide water scarcity resulting from climate change. Nevertheless, the existing body of literature has not sufficiently addressed the consequences of water scarcity on agri-food supply chains. To bridge this research gap and contribute to mitigating the global water crisis induced by climate change, this study proposes a hybrid model that combines optimized neural networks based on meta-heuristic algorithms and mathematical optimization for a sustainable agricultural supply chain. The proposed model integrates particle swarm optimization (PSO) for feature selection and a hybrid convolutional neural network (CNN)-gated recurrent unit (GRU) with a genetic algorithm (GA) optimized structure to predict water consumption. Leveraging the model’s results, a multi-objective sustainable agriculture supply chain model is developed to optimize supply chain profitability while simultaneously addressing environmental pollutants, production waste, food waste, water usage, and manufacturing costs and time. To evaluate the effectiveness of the proposed approach, a real case study in Iran is employed, providing both theoretical and practical insights into the design of agriculture supply chain optimization that incorporates sustainability factors and effectively tackles the growing challenge of water scarcity. The findings of this study hold implications for managers and policymakers in countries where the importance of sustainability is growing. By integrating advanced optimization techniques and predictive models, this research offers a novel framework for enhancing the sustainability of agricultural supply chains and addressing the pressing issues of water scarcity induced by climate change.