FC

S M Tanvir Faysal Alam Chowdhoury, Ph.D.

Research Associate, Rochester Institute of Technology · Rochester, NY

LinkedIn Email Google Scholar ORCID GitHub ResearchGate

About

I am a Research Associate at the Rochester Institute of Technology, working with Dr. Lu Sun. I build physics-informed machine learning models for electric-vehicle charging demand, power-grid stability, and transportation safety, and I validate them on real-world networks.

I received my Ph.D. in Interdisciplinary Engineering (Electrical and Computer Engineering concentration) from Kennesaw State University in 2026, advised by Dr. Mahyar Amirgholy in the Futra Lab. My dissertation, Machine Learning for Predictive Energy and Emissions Modeling of Vehicles and Power Grids in the United States, led to TEEMAT, an open tool that predicts vehicle and grid emissions across the country.

Research interests

Physics-informed machine learningSustainable transportationVehicle and grid emissionsEV charging demandCoupled transportation–power grid simulationTransferable predictive modelsDecision support for clean energy planning

Experience and education

Research Associate

Rochester Institute of Technology · Aug 2026 – present
  • Co-developing federal research proposals with Dr. Lu Sun on AI for energy, transportation, and infrastructure.
  • Building predictive models and data pipelines with statistical inference and optimization.

Graduate Research Assistant, Futra Lab

Kennesaw State University · Aug 2022 – Jul 2026
  • Developed TEEMAT, combining Meta Prophet, deep neural networks, and Seq2Seq models trained on NREL Cambium and EPA MOVES data.
  • Ran distributed pipelines in PySpark and Hadoop, and built the web interface (FastAPI, React, Leaflet, D3.js).

Ph.D., Interdisciplinary Engineering (ECE concentration)

Kennesaw State University · 2026

B.Sc., Civil Engineering

Ahsanullah University of Science and Technology, Dhaka · 2012

Selected publications

Amirgholy, M., Chowdhoury, F.A., Wang, C., & Kanigiri, S.N. (2026). Predictive analysis of greenhouse gas emissions from electric vehicle charging in the United States. Scientific Reports, 16, 12853. doi:10.1038/s41598-026-43525-5

Chowdhoury, F.A., Gabriel, K., Rocker, J., Wang, C., & Amirgholy, M. (2026). Machine learning for scenario-based prediction of grid emissions from EV charging across the United States. 105th Transportation Research Board Annual Meeting, Washington, D.C.

Chowdhoury, F.A., Wang, C., & Amirgholy, M. (2026). Machine learning for predictive analysis of tailpipe and grid emissions from EV charging across the United States. 105th Transportation Research Board Annual Meeting, Washington, D.C.

Kanigiri, S.N., Chowdhoury, F.A., Licona-Hernandez, C., & Amirgholy, M. (2025). Predicting greenhouse gas emissions from EV charging in the United States. Transportation Research Board Annual Meeting, Washington, D.C.

Full list on Google Scholar.

Tools

TEEMAT: Transportation Energy and Emissions Modeling and Analysis Tool

An interactive machine-learning tool that predicts tailpipe and power-grid greenhouse gas emissions under rising EV adoption for U.S. regions. Source code and updates are on GitHub.

Mentoring and service

Since 2023 I have mentored more than a dozen undergraduate and graduate researchers at Kennesaw State on machine-learning model development, interface design, data generation, and conference presentations, including Transportation Research Board submissions and C-Day posters. I also review manuscripts for Transportation Research Record.

Honors