DIGITAL TWINS FOR INTELLIGENT COMPUTING: MODELS, APPLICATIONS, AND CHALLENGES

Abstract

Digital Twins (DTs) have emerged as a transformative technology for bridging physical and virtual systems, enabling real-time monitoring, predictive analytics, and intelligent decision-making across diverse application domains. Recent advances in artificial intelligence (AI), machine learning, the Internet of Things (IoT), cloud-edge computing, and cyber physical systems have accelerated the evolution of conventional DTs into Intelligent Digital Twins (IDTs), capable of adaptive learning and autonomous operation. This narrative review synthesizes recent developments in DT research by examining their conceptual evolution, modeling paradigms, integration with intelligent computing techniques, and representative applications in manufacturing, healthcare, smart cities, infrastructure, supply chains, and energy systems. The review further discusses physics-based, data-driven, and hybrid modeling approaches, highlighting their respective strengths and limitations in developing reliable and intelligent DT frameworks. In addition, key challenges related to interoperability, scalability, cybersecurity, data governance, and model reliability are critically analyzed, together with emerging research opportunities involving explainable AI, federated learning, and edge intelligence. The findings demonstrate that Intelligent Digital Twins are evolving beyond digital representations into intelligent computational ecosystems that support autonomous, data-driven, and resilient operations. This review provides researchers and practitioners with a comprehensive understanding of current advances, identifies critical research gaps, and outlines future directions for realizing the full potential of Intelligent Digital Twins in next-generation intelligent computing.