{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T10:18:06Z","timestamp":1782209886000,"version":"3.54.5"},"reference-count":31,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T00:00:00Z","timestamp":1756944000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JTAER"],"abstract":"<jats:p>This study explores how the integration of generative artificial intelligence, multi-objective evolutionary optimization, and reinforcement learning can enable sustainable and cost-effective decision-making in supply chain strategy. Using real-world retail demand data enriched with synthetic sustainability attributes, we trained a Variational Autoencoder (VAE) to generate plausible future demand scenarios. These were used to seed a Non-Dominated Sorting Genetic Algorithm (NSGA-II) aimed at identifying Pareto-optimal sourcing strategies that balance delivery cost and CO2 emissions. The resulting Pareto frontier revealed favorable trade-offs, enabling up to 50% emission reductions for only a 10\u201315% cost increase. We further deployed a deep Q-learning (DQN) agent to dynamically manage weekly shipments under a selected balanced strategy. The reinforcement learning policy achieved an additional 10% emission reduction by adaptively switching between green and conventional transport modes in response to demand and carbon pricing. Importantly, the agent also demonstrated resilience during simulated supply disruptions by rerouting decisions in real time. This research contributes a novel AI-based decision architecture that combines generative modeling, evolutionary search, and adaptive control to support sustainability in complex and uncertain supply chains.<\/jats:p>","DOI":"10.3390\/jtaer20030240","type":"journal-article","created":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T08:08:46Z","timestamp":1756973326000},"page":"240","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Generative and Adaptive AI for Sustainable Supply Chain Design"],"prefix":"10.3390","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6912-2450","authenticated-orcid":false,"given":"Sabina-Cristiana","family":"Necula","sequence":"first","affiliation":[{"name":"Department of Accounting, Business Informatics and Statistics, Alexandru Ioan Cuza University of Iasi, 700506 Iasi, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emanuel","family":"Rieder","sequence":"additional","affiliation":[{"name":"Doctoral School of Economics and Business Administration, Alexandru Ioan Cuza University of Iasi, 700506 Iasi, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,4]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Zou, Y., Gao, Q., Wu, H., and Liu, N. (2024). Carbon-Efficient Scheduling in Fresh Food Supply Chains with a Time-Window-Constrained Deep Reinforcement Learning Model. Sensors, 24.","DOI":"10.3390\/s24237461"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"598","DOI":"10.1016\/j.ifacol.2024.08.402","article-title":"Leveraging reinforcement learning and evolutionary strategies for dynamic multi objective decision making in supply chain management","volume":"58","author":"Qiu","year":"2024","journal-title":"IFAC-PapersOnLine"},{"key":"ref_3","unstructured":"Jensen, T.C. (2025, August 14). How Gen AI Is Transforming Sustainable Supply Chains, Deloitte. Available online: https:\/\/www.deloitte.com\/dk\/en\/blogs\/cxo-board\/blog-tore-how-gen-ai-is-transforming-sustainable-supply-chains.html."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"101922","DOI":"10.1016\/j.tre.2020.101922","article-title":"Predicting the impacts of epidemic outbreaks on global supply chains: A simulation-based analysis on the coronavirus outbreak (COVID-19\/SARS-CoV-2) case","volume":"136","author":"Ivanov","year":"2020","journal-title":"Transp. Res. Part E Logist. Transp. Rev."},{"key":"ref_5","unstructured":"Rodrigo, J.A., and Ortiz, J.E. (2025, August 14). The M5 Accuracy Competition: The Success of Global Forecasting Models. Available online: https:\/\/cienciadedatos.net\/documentos\/py61-m5-forecasting-competition.html."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1109\/4235.996017","article-title":"A fast and elitist multiobjective genetic algorithm: NSGA-II","volume":"6","author":"Deb","year":"2002","journal-title":"IEEE Trans. Evol. Comput."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"7151","DOI":"10.1080\/00207543.2022.2140221","article-title":"A review on reinforcement learning algorithms and applications in supply chain management","volume":"61","author":"Rolf","year":"2023","journal-title":"Int. J. Prod. Res."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1007\/s10458-024-09669-2","article-title":"Carbon trading supply chain management based on constrained deep reinforcement learning","volume":"38","author":"Wang","year":"2024","journal-title":"Auton. Agents Multi-Agent Syst."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1007\/978-3-031-14714-2_26","article-title":"Evolving Through the Looking Glass: Learning Improved Search Spaces with Variational Autoencoders","volume":"Volume 13398","author":"Rudolph","year":"2022","journal-title":"Parallel Problem Solving from Nature\u2013PPSN XVII"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Jayarathna, C.P., Agdas, D., Dawes, L., and Yigitcanlar, T. (2021). Multi-Objective Optimization for Sustainable Supply Chain and Logistics: A Review. Sustainability, 13.","DOI":"10.3390\/su132413617"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Pakdel, G.H., He, Y., and Pakdel, S.H. (2024). Multi-Objective Green Closed-Loop Supply Chain Management with Bundling Strategy, Perishable Products, and Quality Deterioration. Mathematics, 12.","DOI":"10.3390\/math12050737"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"13478","DOI":"10.1007\/s10489-021-02944-9","article-title":"A closed-loop supply chain configuration considering environmental impacts: A self-adaptive NSGA-II algorithm","volume":"52","author":"Babaeinesami","year":"2022","journal-title":"Appl. Intell."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Abir, A.S., Bhuiyan, I.A., Arani, M., and Billal, M. (2020, January 26\u201327). Multi-Objective Optimization for Sustainable Closed-Loop Supply Chain Network Under Demand Uncertainty: A Genetic Algorithm. Proceedings of the 2020 International Conference on Data Analytics for Business and Industry: Way Towards a Sustainable Economy (ICDABI), Sakheer, Bahrain.","DOI":"10.1109\/ICDABI51230.2020.9325648"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Sun, W., and Su, Y. (2020). Analysing Green Forward\u2013Reverse Logistics with NSGA-II. Sustainability, 12.","DOI":"10.3390\/su12156082"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1016\/j.susoc.2021.07.006","article-title":"Green supply chain network design with emphasis on inventory decisions","volume":"2","author":"Mahjoob","year":"2021","journal-title":"Sustain. Oper. Comput."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Acerce, A., and Denizhan, B. (2025). Application of the Non-Dominated Sorting Genetic Algorithm II (NSGA-II) in a Two-Echelon Cold Supply Chain. Systems, 13.","DOI":"10.3390\/systems13030206"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Islam, H.M.M., Vo, H.Q.N., and Ramanan, P. (2024, January 15\u201318). SplitVAEs: Decentralized scenario generation from siloed data for stochastic optimization problems. Proceedings of the 2024 IEEE International Conference on Big Data (BigData), Washington, DC, USA.","DOI":"10.1109\/BigData62323.2024.10826070"},{"key":"ref_19","first-page":"222","article-title":"NSGA-II-based study of carbon emissions in service-based manufacturing supply chains","volume":"10","author":"Wang","year":"2024","journal-title":"Int. J. Internet Manuf. Serv."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Zhang, Y., He, L., and Zheng, J. (2024). A Deep Reinforcement Learning-Based Dynamic Replenishment Approach for Multi-Echelon Inventory Considering Cost Optimization. Electronics, 14.","DOI":"10.3390\/electronics14010066"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Kim, T., Bilsel, R.U., and Kumara, S.R.T. (2007, January 27\u201329). A Reinforcement Learning Approach for Dynamic Supplier Selection. Proceedings of the 2007 IEEE International Conference on Service Operations and Logistics, and Informatics, Philadelphia, PA, USA.","DOI":"10.1109\/SOLI.2007.4383959"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"6639","DOI":"10.24294\/jipd.v8i8.6639","article-title":"Leveraging variational autoencoders and recurrent neural networks for demand forecasting in supply chain management: A case study","volume":"8","author":"Khlie","year":"2024","journal-title":"J. Infrastruct. Policy Dev."},{"key":"ref_23","unstructured":"Oroojlooyjadid, A., Nazari, M., Snyder, L., and Tak\u00e1\u010d, M. (2020). A Deep Q-Network for the Beer Game: A Deep Reinforcement Learning algorithm to Solve Inventory Optimization Problems. arXiv."},{"key":"ref_24","unstructured":"Sultana, N.N., Meisheri, H., Baniwal, V., Nath, S., Ravindran, B., and Khadilkar, H. (2020). Reinforcement Learning for Multi-Product Multi-Node Inventory Management in Supply Chains. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Qian, W., Xu, H., Chen, H., Yang, L., Lin, Y., Xu, R., Yang, M., and Liao, M. (2024). A Synergistic MOEA Algorithm with GANs for Complex Data Analysis. Mathematics, 12.","DOI":"10.3390\/math12020175"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Simchi-Levi, D., Mellou, K., Menache, I., and Pathuri, J. (2025). Large Language Models for Supply Chain Decisions. arXiv.","DOI":"10.2139\/ssrn.5370043"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Martins, M., Rocha, M., and Pereira, V. (2022, January 18\u201323). Variational Autoencoders and Evolutionary Algorithms for Targeted Novel Enzyme Design. Proceedings of the 2022 IEEE Congress on Evolutionary Computation (CEC), Padua, Italy.","DOI":"10.1109\/CEC55065.2022.9870421"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/j.ejor.2025.01.026","article-title":"Deep Controlled Learning for Inventory Control","volume":"324","author":"Imdahl","year":"2025","journal-title":"Eur. J. Oper. Res."},{"key":"ref_29","unstructured":"Pathak, P.P. (2025, August 14). Future Supply Chain Systems with Autonomous, Adaptive, and Self-Learning AI Agents, Linkedin AI Supply Chain Frontiers. Available online: https:\/\/www.linkedin.com\/pulse\/future-supply-chain-systems-autonomous-adaptive-ai-agents-pathak-lxijc\/."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1613\/jair.3987","article-title":"A Survey of Multi-Objective Sequential Decision-Making","volume":"48","author":"Roijers","year":"2013","journal-title":"J. Artif. Intell. Res."},{"key":"ref_31","unstructured":"Lundberg, S., and Lee, S.-I. (2017). A Unified Approach to Interpreting Model Predictions. arXiv."}],"container-title":["Journal of Theoretical and Applied Electronic Commerce Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/0718-1876\/20\/3\/240\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:39:09Z","timestamp":1760035149000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/0718-1876\/20\/3\/240"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,4]]},"references-count":31,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["jtaer20030240"],"URL":"https:\/\/doi.org\/10.3390\/jtaer20030240","relation":{},"ISSN":["0718-1876"],"issn-type":[{"value":"0718-1876","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,4]]}}}