Omar Faruque

iHARP Research Assistant | UMBC Ph.D. Student

Email: omarf1@umbc.edu
See me at Google Scholar Citation Page, LinkedIn

Research Interests

  • Artificial Intelligence
  • Causal Analysis
  • Machine Learning
  • Interventional Data Analytics
Short Biography

Omar Faruque is a PhD student specializing in Causality Analysis for time series and spatiotemporal data, leveraging Deep Learning and AI techniques. His research primarily focuses on Climate and Earth domains, but he maintains an open interest in NLP, medical, and biological applications. Omar’s expertise extends to computer vision and machine learning, with a growing curiosity for Foundation Models and Diffusion Models. His interdisciplinary approach and diverse interests position him as a versatile researcher at the forefront of AI applications in various scientific fields.

Research Summary

Omar’s research aims to discover and quantify causal relationships between key climate variables such as temperature, precipitation, wind velocity, heat flux, and ice melt in the Arctic region, particularly over Greenland. He uses deep learning techniques, including a transformer-based framework, to analyze 40 years of non-stationary reanalysis data and identify both contemporaneous and time-lagged causal links across different timescales. These data-driven findings are validated against known physical relationships to ensure scientific plausibility. By altering specific causal variables, such as temperature or wind patterns, he quantifies the resulting changes across the Arctic system, helping to evaluate the strength and influence of different causal relationships on ice melt and climate dynamics. This work supports the development of more physically consistent and interpretable climate models, contributing to improved predictions of future changes in the Greenland Ice Sheet.

Publications
  • 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
  • Akila Sampath, Omar Faruque, Azim Khan, Vandana Janeja, and Jianwu Wang. 2024. Physics-Informed Machine Learning for Sea Ice Thickness Prediction. In 2024 IEEE International Conference on Knowledge Graph (ICKG), December 11, 2024. IEEE, Abu Dhabi, United Arab Emirates, 325–333. https://doi.org/10.1109/ICKG63256.2024.00048
  • Sahara Ali, Omar Faruque, and Jianwu Wang. 2024. Estimating Direct and Indirect Causal Effects of Spatiotemporal Interventions in Presence of Spatial Interference. In Machine Learning and Knowledge Discovery in Databases. Research Track, Albert Bifet, Jesse Davis, Tomas Krilavičius, Meelis Kull, Eirini Ntoutsi and Indrė Žliobaitė (eds.). Springer Nature Switzerland, Cham, 213–230. https://doi.org/10.1007/978-3-031-70352-2_13
  • Sahara Ali, Uzma Hasan, Xingyan Li, Omar Faruque, Akila Sampath, Yiyi Huang, Md Osman Gani, and Jianwu Wang. 2024. Causality for Earth Science — A Review on Time-series and Spatiotemporal Causality Methods. https://doi.org/10.48550/arXiv.2404.05746
  • Sahara Ali, Omar Faruque, Yiyi Huang, Md Osman Gani, Aneesh Subramanian, Nicole-Jeanne Schlegel, and Jianwu Wang. “Estimating Causal Effects of Greenland Blocking on Arctic Sea Ice Melt Using Deep Learning Technique,” 2023. In American Meteorological Society’s 23rd Conference on Artificial Intelligence for Environmental Science 2024. Poster at AMS, 668. [Conference Paper/Poster]
  • Sahara Ali, Omar Faruque, Yiyi Huang, Md. Osman Gani, Aneesh Subramanian, Nicole-Jeanne Schlegel, and Jianwu Wang. 2023. Quantifying Causes of Arctic Amplification via Deep Learning Based Time-Series Causal Inference. In 2023 International Conference on Machine Learning and Applications (ICMLA), December 15, 2023. IEEE, Jacksonville, FL, USA, 689–696. https://doi.org/10.1109/ICMLA58977.2023.00101
  • Katherine Yi, Angelina Dewar, Tartela Tabassum, Jason Lu, Ray Chen, Homayra Alam, Omar Faruque, Sikan Li, Mathieu Morlighem, and Jianwu Wang. “Evaluating Machine Learning and Statistical Models for Greenland Subglacial Bed Topography.” In 2023 International Conference on Machine Learning and Applications (ICMLA), 659–66. Jacksonville, FL, USA: IEEE, 2023. https://doi.org/10.1109/ICMLA58977.2023.00097. [Conference Paper]

Last updated 16 June 2025