An adaptive supply chain stress testing framework with deep learning
| dc.contributor.author | Ozturk, Cemalettin | en |
| dc.contributor.author | O'Sullivan, Barry | en |
| dc.contributor.funder | Science Foundation Ireland | en |
| dc.date.accessioned | 2025-10-15T10:37:03Z | |
| dc.date.available | 2025-10-15T10:37:03Z | |
| dc.date.issued | 2025-10-04 | en |
| dc.description.abstract | Since the COVID-19 pandemic, supply chain disruptions have become the biggest risk to the continuity and stability of the global economy. Therefore, assessing the vulnerability of supply chains and developing the best mitigation plans for high-impact disruptions to enhance supply chain resilience is crucial to the survival of public and private organizations. In this paper, we propose a conceptual framework for diagnosing the vulnerability of suppliers, logistic providers, and commodities for any size of multi-tier supply chain networks for private and public bodies. The framework is based on a supply chain digital twin that will be formed with the industrial Internet of Things technology for accessing field data, machine learning models for disruption prediction, simulation methods for disruption scenario analysis, and optimization methods for developing mitigation plans to minimize the impact of anticipated disruptions. The framework also exploits a deep learning-based surrogate model of the digital supply chain twin | en |
| dc.description.status | Peer reviewed | en |
| dc.description.version | Published Version | en |
| dc.format.mimetype | application/pdf | en |
| dc.identifier.citation | Ozturk, C. and O’ Sullivan, B. (2026) ‘An adaptive supply chain stress testing framework with deep learning’, in McNally C., Carroll P., Martinez-Pastor B., Ghosh B., Efthymiou M. and Valantasis-Kanellos V. (eds) Transport Transitions: Advancing Sustainable and Inclusive Mobility, Lecture Notes in Mobility, pp. 520–526. https://doi.org/10.1007/978-3-032-04774-8_75 | en |
| dc.identifier.doi | 10.1007/978-3-032-04774-8_75 | en |
| dc.identifier.endpage | 526 | en |
| dc.identifier.isbn | 978-3-032-04774-8 | en |
| dc.identifier.journaltitle | Lecture Notes in Mobility | en |
| dc.identifier.startpage | 520 | en |
| dc.identifier.uri | https://hdl.handle.net/10468/18040 | |
| dc.language.iso | en | en |
| dc.publisher | Springer, Cham | en |
| dc.relation.ispartof | https://link.springer.com/series/11573 | en |
| dc.relation.project | info:eu-repo/grantAgreement/SFI/National Challenge Fund::Digital for Resilience Challenge/22/NCF/DR/11264/IE/Deep Learning based Transferrable Supply Chain Stress Test/ | en |
| dc.rights | © 2026, the Authors. | en |
| dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | en |
| dc.subject | Supply chain resilience | en |
| dc.subject | Digital twin | en |
| dc.subject | Machine learning | en |
| dc.subject | Simulation | en |
| dc.subject | Optimization | en |
| dc.subject | Deep learning | en |
| dc.title | An adaptive supply chain stress testing framework with deep learning | en |
| dc.type | Conference item | en |
