Background: The semiconductor industry is a globally interdependent sector characterized by extreme capital intensity, long lead times, technological complexity, and concentrated production geographies. These attributes make semiconductor supply chains particularly vulnerable to cascading disruptions, demand shocks, and structural uncertainty (Semiconductor Industry Association, 2021; OECD, 2025). Recent scholarship has applied a variety of modeling paradigms — agent-based models, system dynamics, production planning frameworks, and digital twin technologies — to understand and mitigate these vulnerabilities (Achter et al., 2017; Arumugam & Pitchaimani, 2025; Ashraf et al., 2024).

Objective: This research synthesizes these modeling approaches into an integrated conceptual and methodological framework for resilient decision-making under deep uncertainty, evaluates mitigation strategies such as operational slack and supply redundancy, and explores the role of reshoring and policy interventions on supply network stability.

Methods: The study constructs a multi-paradigm simulation and analytical narrative grounded in extant literature. It links agent-based representations of heterogeneous actors and strategic behavior (Achter et al., 2017) with system dynamics assessments of ripple effects across intertwined networks (Arumugam & Pitchaimani, 2025), and it places cognitive digital twins and hybrid deep learning disruption detection as operational enablers for real-time situational awareness (Ashraf et al., 2024). The framework also integrates empirical observations about production planning and master planning challenges in semiconductor manufacturing (Mönch et al., 2018) and accounts for market-level consequences such as economic costs and reshoring impacts (Villafranca, 2022; Lulla, 2025).

Results: The integrated framework demonstrates that multi-layered resilience — combining strategic redundancy, targeted operational slack, and real-time digital sensing — reduces ripple amplification and shortens recovery time when compared to single-policy interventions (Azadegan et al., 2021; Bais & Amechnoue, 2024). Agent heterogeneity and adaptive ordering rules create non-linear effects on inventory cycles; system-level reinforcing loops can generate prolonged shortages absent pre-positioned slack (Barnett & Freeman, 2001; Karimi-Nasab & Konstantaras, 2013). Policy levers such as reshoring materially influence long-run geographic risk concentrations but can introduce transitional brittleness without complementary investment in skilled labor and local supply ecosystems (Lulla, 2025; Semiconductor Industry Association, 2021). Interpretation: Robust resilience requires embracing model plurality and pragmatic

orchestration: planning processes informed by agent-based scenario exploration and system dynamics sensitivity analysis, combined with digital twin-enabled operational detection and coordination, offer superior outcomes under deep uncertainty (Achter et al., 2017; Ashraf et al., 2024; Arumugam & Pitchaimani, 2025). The paper concludes with prescriptive guidance for manufacturers, OEMs, and policymakers, and proposes an agenda for empirical validation and controlled field experiments.

Semiconductor supply chain, resilience, agent-based modeling, system dynamics

Achter, S., Lorscheid, I., Hauke, J., Meyer, M., Meyer-Riehl, D., Ponsignon, T., Sun, C., & Ehm, H. (2017). On agent-based modeling in semiconductor supply chain planning. In 2017 Winter Simulation Conference (WSC). Winter Simulation Conference Proceedings. pp. 3507–3518.

Arumugam, D. G., & Pitchaimani, K. (2025). A system dynamics model for assessing the ripple effect of intertwined supply networks. Journal of Simulation, 19(1), 24–38.

Ashraf, M., Eltawil, A., & Ali, I. (2024). Disruption detection for a cognitive digital supply chain twin using hybrid deep learning. Operational Research, 24(2).

Azadegan, A., Modi, S., & Lucianetti, L. (2021). Surprising supply chain disruptions: Mitigation effects of operational slack and supply redundancy. International Journal of Production Economics, 240.

Bais, A., & Amechnoue, K. (2024). New approaches to modeling resilient decisions under deep uncertainty to manage the downstream supply chain. LOGFORUM, 20(2), 227–242.

Barnett, W., & Freeman, J. (2001). Too much of a good thing? Product proliferation and organizational failure. Organization Science, 12(5), 539–558.

Karimi-Nasab, M., & Konstantaras, I. (2013). An inventory control model with stochastic review interval and special sale offer. European Journal of Operational Research, Elsevier.

Lulla, K. (2025). Reshoring GPU production: Testing strategy adaptations for US-based factories. International Journal of Applied Mathematics, 38(10s), 2411–2440.

Mönch, L., Uzsoy, R., & Fowler, J. W. (2018). A survey of semiconductor supply chain models part III: master planning, production planning, and demand fulfilment.

OECD. (2025). Vulnerabilities in the semiconductor supply chain. OECD Publishing. https://doi.org/10.1787/6bed616f-en

Semiconductor Industry Association. (2021). Strengthening the Global Semiconductor Supply Chain in an Uncertain Era. Semiconductor Industry Association. https://www.semiconductors.org/strengthening-the-global-semiconductor-supplychain-in-an-uncertain-era/

United Nations. (2023). Welcome to the United Nations. UN.org.

Villafranca, O. (2022). Chip shortage cost U.S. economy billions in 2021. CBS News. https://www.cbsnews.com/news/chip-shortage-cost-us-economy-billions-in-2021/

Precedence Research. (2024). Precedence Research - Market Research Reports & Consulting Firm. https://www.precedenceresearch.com.