Sukanta Basu

ETEC 321 · +1 518-437-8633

sbasu@albany.edu

University at Albany

Albany, NY, USA

I am a Professor of Empire Innovation at the University at Albany (SUNY), jointly appointed in the Atmospheric Sciences Research Center and the Department of Environmental and Sustainable Engineering.

Before joining the University at Albany, I was a tenured Associate Professor at Delft University of Technology (2016–2023). Earlier, I held faculty positions at North Carolina State University and Texas Tech University. I received my Ph.D. in Civil Engineering from the University of Minnesota and was a recipient of the NSF CAREER Award.

80+

Journal articles

25+

Funded projects

40+

Students & postdocs

15+

ML competitions

Over the past two decades, my research group and collaborators have used a diverse suite of physics-based modeling techniques (e.g., direct numerical simulation, large-eddy simulation, and mesoscale modeling) and developed associated parameterizations to deepen our understanding of atmospheric turbulence. More recently, we have substantially expanded our modeling portfolio by incorporating modern artificial intelligence (AI) and machine learning (ML) methods, including deep learning. Beyond conventional weather forecasting, our findings have direct implications for the design and operation of next-generation utility-scale wind turbines, high-energy laser systems, free-space optical communication networks, and other technologies influenced by atmospheric turbulence.

I am an avid enthusiast of machine learning competitions and a contributor to the Kaggle platform. In 2021, I placed first globally in the SHELL.ai Hackathon on solar energy forecasting. In 2022, I placed third in the NASA Airathon competition, which focused on predicting nitrogen oxide (NOx) levels. I continue to participate in various applied machine learning and forecasting challenges.

news

Aug 19, 2026	Our paper introducing S2G-DI, a deep learning framework for generating high-resolution wind-gust fields from sparse Mesonet observations, was published in Artificial Intelligence for the Earth Systems.
Aug 04, 2026	Elected a Full Member of Sigma Xi, The Scientific Research Honor Society.
Jul 07, 2026	Awarded a NASA grant (`$500K`) for “Coupling NASA Earth Observation and Weather-Climate Foundation Models for Power Outage Management.”
Mar 15, 2026	Our Applied Optics paper on leveraging deep-learning foundation models for optical turbulence ($C_n^2$) estimation under data scarcity was selected as an Editor’s Pick.
Mar 06, 2026	Invited seminar at Johns Hopkins University on AI/ML-driven modeling of atmospheric turbulence.
Nov 19, 2025	Invited seminar at the University of Alabama in Huntsville on AI/ML-driven modeling of atmospheric turbulence.

selected publications

Optics

Leveraging deep learning-based foundation models for optical turbulence ($C_n^2$) estimation under data scarcity

S Basu

Applied Optics, 2026

Editor’s Pick, Applied Optics Bib Code

true

@article{basu2026AO,
  title = {Leveraging deep learning-based foundation models for optical turbulence (\(C_n^2\)) estimation under data scarcity},
  author = {Basu, S},
  journal = {Applied Optics},
  year = {2026},
  volume = {65},
  pages = {2497--2504},
}

S2G-DI: A Deep Learning Framework for Generating High-Resolution Wind Gust Fields from Sparse Mesonet Observations

H Baki, M Pierzyna, and S Basu

Artificial Intelligence for the Earth Systems, 2026

Early Online Release

DOI Bib Code

@article{baki2026AIES,
  title = {{S2G-DI}: A Deep Learning Framework for Generating High-Resolution Wind Gust Fields from Sparse Mesonet Observations},
  author = {Baki, H and Pierzyna, M and Basu, S},
  journal = {Artificial Intelligence for the Earth Systems},
  year = {2026},
  doi = {10.1175/AIES-D-25-0111.1},
  note = {Early Online Release}
}

Renewable

Impact of atmospheric turbulence on performance and loads of wind turbines: Knowledge gaps and research challenges

B Kosović, S Basu, J Berg, and 7 more authors

Wind Energy Science, 2026

Bib

@article{kosovic2026WES,
  title = {Impact of atmospheric turbulence on performance and loads of wind turbines: Knowledge gaps and research challenges},
  author = {Kosovi\'{c}, B and Basu, S and Berg, J and Berg, L K and Haupt, S E and Lars\'{e}n, X G and Peinke, J and Stevens, R J A M and Veers, P and Watson, S},
  journal = {Wind Energy Science},
  year = {2026},
  volume = {11},
  pages = {509--555},
}

Renewable

A Chebyshev polynomial-based wind speed profile characterization framework: Applications in mesoscale model evaluation

H Baki and S Basu

Wind Energy, 2026

DOI Bib

@article{baki2026WE,
  title = {A {Chebyshev} polynomial-based wind speed profile characterization framework: Applications in mesoscale model evaluation},
  author = {Baki, H and Basu, S},
  journal = {Wind Energy},
  year = {2026},
  volume = {29},
  pages = {e70080},
  doi = {10.1002/we.70080},
}

Optics

OTCliM: generating a near-surface climatology of optical turbulence strength ($C_n^2$) using gradient boosting

M Pierzyna, S Basu, and R Saathof

Artificial Intelligence for the Earth Systems, 2025

Bib

@article{pierzyna2025AIES,
  title = {{OTCliM}: generating a near-surface climatology of optical turbulence strength (\(C_n^2\)) using gradient boosting},
  author = {Pierzyna, M and Basu, S and Saathof, R},
  journal = {Artificial Intelligence for the Earth Systems},
  year = {2025},
  volume = {4},
  pages = {e240076},
}