The overarching research theme of Dr. Alam’s lab is “Hybrid Data+Physics-Driven & Explainable Machine Learning Techniques and Multiscale Modeling with Surrogate-Modeling-Based Uncertainty Quantification and Robust Optimization for Multi-Criteria Decision making for Nuclear Engineering Problems.”

Accordingly, Dr. Alam’s research interests and expertise broadly lie in the intersection of nuclear engineering, explainable machine learning, mechanics & materials — focusing on data-driven analysis that warrants frequent excursions among the boundaries of applied mathematics and data science. Our group is currently exploring and developing the techniques below for advanced nuclear systems:

Explainable AI (XAI)-Infused Digital Twin System

Physics-Informed Multi-Fidelity Machine Learning

Operator Learning as Faster Surrogate for Digital Twin

Digital Twin Temporal Synchronization Module

Surrogate-Driven Physics-Informed Multi-fidelity Kriging

Composite Accident Tolerant Fuel

Uncertainty Quantification & Sensitivity Analysis

Reduced-Order Model

Explainable AI (XAI) & Interpretable AI

Reliability-Based Robust Design Optimization

Multiscale Modeling

Zero-Trust-Infused Framework for Cyber Threats