Shah Hamdi

Shah Hamdi serves as an Assistant Professor in the Computer Science Department at Utah State University's College of Engineering. His research bridges machine learning and space physics, with emphasis on time series analysis for solar phenomena prediction and explainable AI systems.

His primary research focuses include Time Series Analysis for space weather forecasting, Solar Physics applications in flare and particle event prediction, Explainable AI through counterfactual methods, and Natural Language Processing for social media analysis. He develops novel frameworks for multivariate time series classification, data augmentation of imbalanced datasets, and interpretable model architectures that handle complex spatio-temporal patterns.

Analysis of his recent publications reveals three dominant trends: (1) Application of graph neural networks and multimodal fusion to solar flare prediction using photospheric magnetic field data, (2) Development of shapelet-based and saliency-guided counterfactual explanation techniques for time series classification, and (3) Creation of generative models like ChronoGAN and AVATAR for synthetic time series data augmentation. His work consistently addresses challenges in imbalanced data and space weather forecasting accuracy.

Dr. Hamdi leads collaborative research initiatives including the CAIG project for synthetic data generation in solar energetic particle events. His grant portfolio demonstrates expertise in securing funding for interdisciplinary space weather and machine learning projects, while his advising focuses on training graduate students in time series analysis and explainable AI methodologies for real-world applications.