Analytical review synthesizing climate change impacts on power systems, integrating demand growth, infrastructure degradation, extreme events, uncertainty modeling, and renewable transition planning.
Graph Neural Network–based reinforcement learning framework for integrating hyperscale data centers into post-disaster distribution system restoration.
Capacity expansion modeling framework quantifying interactions between hyperscale data center growth, residential electrification, and long-term energy affordability.
Probabilistic energy transition planning framework integrating capacity expansion modeling, hierarchical Monte Carlo simulation, and machine learning surrogates.
Probabilistic integrated assessment modeling framework coupling carbon dioxide removal deployment with power-sector evolution under deep uncertainty.
Graph neural network framework for prediction-based compression with explicit decompression error guarantees across large-scale spatio-temporal datasets.
Systematic review of Graph Neural Network methodologies across transportation, power, water, and structural infrastructure systems, identifying research gaps and future directions.
Surrogate-accelerated chance-constrained optimal power flow framework combining multi-fidelity graph neural networks with hybrid constraint validation under renewable and load uncertainty.
Topology-aware multi-agent reinforcement learning framework for scalable power distribution system restoration after hurricanes.
Geospatial risk-based decision-support system for statewide prioritization of stormwater infrastructure inspection and maintenance under climate stressors.
Residual multi-fidelity graph neural network framework enabling scalable probabilistic power flow analysis under high-dimensional renewable and load uncertainty.
Regression-based machine learning framework for predicting rutting, cracking, and moisture resistance of asphalt mixtures and identifying feasible design regions under traffic-level constraints.
Utility-scale graph learning framework for structure-level failure localization and cause prediction across large transmission networks.