Md Osman Gani

University of Maryland, Baltimore County

prof_pic.jpg

Office: ITE 426

Lab: ITE 461

1000 Hilltop Circle

Baltimore, MD 21250

I am an Assistant Professor of Information Systems at the University of Maryland, Baltimore County (UMBC), where I direct the Causal AI Lab. I am also a faculty affiliate in the Computer Science and Electrical Enginnering at UMBC and a member of the NSF HDR Institute for Harnessing Data and Model Revolution in the Polar Regions (iHARP).

My research interests are in machine learning (ML) and artificial intelligence (AI), with a significant emphasis on advancing methods that move beyond correlation to uncover causal relationships and estimate causal effects. My research develops data-driven and knowledge-guided causal AI methods that improve causal discovery and inference from complex and biased observational data. I apply these advances to pressing challenges in healthcare (e.g., treatment effect estimation from EHR data), climate science (e.g., modeling ice sheet melt and sea-level rise), natural language processing (e.g., hallucination detection in large language models), and rehabilitation engineering (e.g., personalized accessible navigation for wheelchair users). My work combines causal modeling, statistics, and ML to accelerate scientific discovery, inform policy decisions, and design technologies that positively impact society. My research has been supported by grants from NSF, NIH, NIDILRR, and UMBC.

I received my doctorate in Computational Sciences at Marquette University in 2017, where my dissertation focused on the development of a novel framework to recognize complex human activity. I received a B.Sc. degree in Computer Science and Engineering from Military Institute of Science and Technology (MIST), Bangladesh and an M.Sc. degree in Computational Sciences from Marquette University. Before joining UMBC, I was a Visiting Assistant Professor at Miami University where I co-lead a research group, SMART (Social Mobile Assisted Real-Time) Systems Research Group. I started my academic career right after my undergrad as a Lecturer in the CSE department at MIST. I was a competitive programmer during my undergrad and participated in many national and international programming competitions (my team achieved 7th Place in ACM ICPC 2008 Dhaka Regional Site).

Please feel free to contact me if you have any questions.


I am currently looking for motivated Ph.D. students to join our lab, Causal AI Lab. If you are interested please reach out at mogani [at] umbc [dot] edu. Before reaching out please read our recent works.


What a long strange trip its been ….


news

Jun 1, 2025 Our paper Learning What Matters: Causal Time Series Modeling for Arctic Sea Ice Prediction has been accepted for publication in AI for Time Series Analysis Workshop, the 34th International Joint Conference on Artificial Intelligence (IJCAI-25), August, 2025 Link to pre-print.
May 1, 2025 Our paper TimeGraph: Synthetic Benchmark Datasets for Robust Time-Series Causal Discovery has been accepted for publication in the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), August, 2025 Link to publication.
Jan 31, 2025 Three of our papers have been accepted for publication in the 1st Causal AI for Robust Decision Making Workshop, 2025 IEEE International Conference on Pervasive Computing and Communications, Mar 2025 Link to 1st publication; Link to 2nd publication; Link to 3rd publication .
Jan 1, 2025 Our paper LLM-based Corroborating and Refuting Evidence Retrieval for Scientific Claim Verification has been accepted for publication in the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25) Workshop, February, 2025 Link to pre-print.
Sep 1, 2024 Our paper on Time series classification of supraglacial lakes evolution over greenland ice sheet has been accepted for publication in 2024 International Conference on Machine Learning and Applications (ICMLA), December, 2024 Link to pre-print.
Sep 1, 2023 Our survey paper on A Survey on Causal Discovery Methods for I.I.D. and Time Series Data has been accepted for publication in Transactions on Machine Learning Research (TMLR), September, 2023 Link to publication. We received The Survey Certificate from the TMLR for an exceptionally thorough or insightful survey of the topic.