COGNITIVE DIGITAL TWIN-DRIVEN STRUCTURAL SYSTEMS FOR REAL-TIME DEFORMATION FORECASTING USING MULTI-SENSOR FUSION AND NEURO-SYMBOLIC AI IN CLIMATE-STRESSED URBAN ENVIRONMENTS

Rapid urbanization combined with escalating climate stress poses significant challenges for maintaining the structural health of urban infrastructure. Traditional monitoring systems often fall short in providing real-time, context-aware, and adaptive decision-making capabilities. This paper proposes a Cognitive Digital Twin (CDT) framework that integrates multi-sensor fusion with neuro-symbolic artificial intelligence (NS-AI) to deliver real-time structural deformation forecasting. The CDT system models and predicts structural behavior in climate-stressed environments by synchronizing physical infrastructure data with a continuously learning virtual counterpart. By merging symbolic reasoning with neural learning, the proposed system achieves both interpretability and adaptiveness, addressing the limitations of purely data-driven or rule-based systems. Experimental results demonstrate improved forecasting accuracy and enhanced operational resilience in the face of climate volatility.