Mostafa Cham

iHARP Research Assistant | UMBC Ph.D. Candidate

Email: mcham2@umbc.edu
See me at Google Scholar Citation Page, LinkedIn

Research Interests

  • Artificial Intelligence/ Machine Learning
  • Earth Informatics
  • Big Data Analytics
Short Biography

Mostafa Cham is a Ph.D. candidate in Information Systems at the University of Maryland, Baltimore County (UMBC). He holds a Master’s degree in Information Systems from UMBC and a Bachelor’s degree in Computer Engineering from Azarbaijan Shahid Madani University. His research focuses on applying artificial intelligence (AI) to climate data, specifically on enhancing predictability and explainability in climate change models and weather forecasting. He is currently working as a research assistant at iHARP, focusing on predicting the future contribution of ice sheets in polar regions on climate change, more specifically on sea level rise.

Research Summary
Since joining iHARP in August 2024, Mostafa has contributed to the Ice Bed Topography Estimation project through multiple avenues. Initially, he focused on accelerating subglacial bed topography prediction in Greenland by applying parallelization techniques. Mostafa then developed a CNN-based model featuring a patch-based custom loss function to improve ice bed topography estimation. Following encouraging early results, he and the team began a collaboration with Dr. Bayu Adhi Tama to pursue a joint modeling approach. Looking ahead, Mostafa aims to develop a hybrid method combining Symbolic Regression with Neural Networks. This direction seeks to uncover underlying symbolic equations and partial differential equations (PDEs), enhancing the interpretability and scientific insight of ice bed topography models.
Publications
  • Tama, B. A., Krishna, M., Alam, H., Cham, M., Faruque, O., Cheng, G., Wang, J., Morlighem, M., & Janeja, V. (2025). “DeepTopoNet: A framework for subglacial topography estimation on the Greenland ice sheets.” arXiv. https://doi.org/10.48550/arXiv.2505.23980 (Submitted to SIGSPATIAL 2025)
  • Tama, B. A.,  Alam, H., Cham, M., Faruque, O., Wang, J., & Janeja, V. (2025). “GraphTopoNet: Confidence-Weighted and Uncertainty-Aware Graph Learning for Sparse Spatial Prediction.” (Submitted to ICDM 2025)
  • Francis Ndikum Nji, Omar Faruque, Mostafa Cham, Janeja Vandana, and Jianwu Wang. 2024. Hybrid Ensemble Deep Graph Temporal Clustering for Spatiotemporal Data. In IEEE Big Data 2024, 2024. arXiv, Washington D.C. https://doi.org/10.48550/ARXIV.2409.12590

Last updated 16 June 2025