NEURO-SYMBOLIC TWIN FRAMEWORK FOR AUTONOMOUS INFRASTRUCTURE LIFECYCLE OPTIMIZATION: COMBINING EDGE AI, SENSOR FUSION, AND PREDICTIVE RESILIENCE MODELING IN CLIMATE-VULNERABLE SMART CITIES

The rapid urbanization of climate-vulnerable regions has necessitated robust, intelligent systems capable of managing infrastructure resilience. Traditional digital twin architectures often lack real-time adaptability and semantic interpretability, limiting their application in dynamic, uncertain environments. This paper introduces a Neuro-Symbolic Twin Framework (NSTF) that integrates Edge AI, sensor fusion, and predictive resilience modeling for autonomous infrastructure lifecycle optimization. By combining the learning capabilities of neural networks with the interpretability of symbolic AI, this hybrid architecture enables real-time decision-making at the edge. Implemented within a simulated smart city environment subjected to climate-induced stressors (e.g., flooding, heatwaves), the NSTF significantly enhances infrastructure longevity, reduces operational costs, and improves the precision of failure prediction.