Developing Climate-Adaptive Digital Twin Architectures for Predictive Supply Chain Disruption Management Using Spatio-Temporal Analytics and Edge Computing

In an era defined by climate volatility and increasingly complex global supply networks, the need for predictive and adaptive supply chain systems has become paramount. This paper presents a comprehensive framework for developing climate-adaptive digital twin architectures, leveraging spatio-temporal analytics and edge computing to enable real-time disruption management. By integrating geospatial climate data with real-time operational metrics, digital twins offer a dynamic virtual representation of physical supply chain assets, enabling scenario forecasting and resilience planning. The incorporation of edge computing enhances the timeliness and localization of decisions, especially in latency-sensitive environments. Through the convergence of these technologies, supply chains can proactively respond to climate-induced events such as floods, droughts, or extreme weather disruptions. The proposed architecture is designed to support modular deployment, interoperability with legacy systems, and scalable analytics, making it suitable for both regional and global logistics networks. The study also reviews use cases across food logistics, maritime transport, and warehouse operations, highlighting measurable improvements in risk anticipation and operational continuity. This work contributes to the evolving discourse on sustainable supply chain innovation, offering actionable insights for policymakers, engineers, and operations managers seeking to align digital transformation with climate resilience.