Shah Muhammad Hamdi, PhD
Shah Muhammad Hamdi, PhD

Assistant Professor of Computer Science

Biography

Dr. Shah Muhammad Hamdi is an Assistant Professor of Computer Science at Utah State University. His research develops machine learning techniques tailored to multivariate time series and graph data, with applications to the prediction and analysis of extreme solar events such as solar flares and solar energetic particles. He leads the design of ML-based cyberinfrastructure to integrate heterogeneous, large-scale scientific data and support reproducible forecasting workflows for the space weather community. Dr. Hamdi has secured over $1.3M in extramural funding, published more than 70 refereed papers, and was recognized as the Outstanding Computer Science Faculty Researcher of the Year by CS USU in 2024.

Interests
  • Multimodal AI
  • Time Series and Graph Learning
  • Cyberinfrastructure for Science
  • AI for Earth and Space Sciences
Education
  • Ph.D., Computer Science (2020)

    Georgia State University

  • M.S., Computer Science (2020)

    Georgia State University

  • B.Sc., Computer Science & Engineering (2014)

    Rajshahi University of Engineering and Technology, Rajshahi, Bangladesh

Recent News
  • August 2025 — Congratulations to Reza on our IEEE ICDM 2025 paper.
  • August 2025 — Congratulations to Santosh on our ACM CIKM 2025 paper.
  • August 2025 — Congratulations to Peiyu and Pouya on our two IEEE DSAA 2025 papers.
  • July 2025 — I am excited to serve as PI on our recently awarded NSF CAIG grant Award #2530946! Grateful to my collaborator Soukaina (Co-PI) for her excellent work on SEP prediction, to Reza for advancing multimodal augmentation theory, and to Ludger (Co-PI) for bringing deep physics expertise to the team.
  • December 2024 — Congratulations to Reza on our SIAM SDM 2025 paper.
  • December 2024 — Congratulations to Onur, Peiyu, Reza, and Pouya on four IEEE Big Data 2024 papers.
  • December 2024 — Soukaina and I got featured in Utah State Today.
  • December 2024 — Congratulations to Khaznah, Pouya, and Omar on three ICPR 2024 papers.
  • February 2023 — I received the NSF SHINE grant Award #2301397!
  • October 2022 — Congratulations to Soukaina on our ACM CIKM 2022 paper.
  • August 2022 — I started my Assistant Professor position at CS USU.
  • January 2022 — I received the NSF CRII award Award #2305781!
  • August 2020 — I started my Assistant Professor position at CS NMSU.
Featured Publications
(2025). AVATAR: Adversarial Autoencoders with Autoregressive Refinement for Time Series Generation. Proceedings of the 2025 SIAM International Conference on Data Mining, SDM 2025, Alexandria, VA, USA, May 1-3, 2025.
(2025). Pruning Strategies for Backdoor Defense in LLMs. Proceedings of the 34th ACM International Conference on Information and Knowledge Management (CIKM).
(2025). TIMED: Adversarial and Autoregressive Refinement of Diffusion-Based Time Series Generation. Proceedings of the 2025 IEEE International Conference on Data Mining (ICDM).
(2024). Impacts of Data Preprocessing and Sampling Techniques on Solar Flare Prediction from Multivariate Time Series Data of Photospheric Magnetic Field Parameters. The Astrophysical Journal Supplement Series.
Papers
(2025). An End-to-end Ensemble Machine Learning Approach for Predicting High-impact Solar Energetic Particle Events Using Multimodal Data. The Astrophysical Journal Supplement Series.
(2025). Predicting Solar Energetic Particle Events with Time Series Shapelets. The Astrophysical Journal.
(2025). AVATAR: Adversarial Autoencoders with Autoregressive Refinement for Time Series Generation. Proceedings of the 2025 SIAM International Conference on Data Mining, SDM 2025, Alexandria, VA, USA, May 1-3, 2025.
(2025). CACTUS: Cross-Aligned Counterfactual Explanation for Time Series Classification. Proceedings of the 2025 IEEE 12th International Conference on Data Science and Advanced Analytics (DSAA).
(2025). Diverse and Plausible Counterfactual Explanations for Time Series via Latent Space Optimization. Proceedings of the 2025 IEEE 12th International Conference on Data Science and Advanced Analytics (DSAA).