Postdoctoral Associate

Machine Learning for Weather and Climate

I build AI and numerical-weather-modeling workflows for wind and extreme-weather prediction, with a focus on operationally useful, physically consistent forecasting tools.

Download Resume

About

I am an atmospheric scientist working at the intersection of numerical weather prediction (NWP) and machine learning. My research spans wind gust nowcasting, precipitation forecasting, and wind-profile estimation from sparse observations and global reanalysis products.

I currently work as a Postdoctoral Associate at the University at Albany. Previously, I was a Postdoctoral Researcher at TU Delft and completed an Integrated MS & PhD at IIT Madras focused on WRF calibration and cyclone prediction.

Core tools and methods

WRF
ERA5 / CERRA
Mesonet and lidar profilers
TensorFlow
PyTorch
Scikit-Learn
TabNet / CNN / U-Net / SwinTransformer
Gaussian Process Regression
Xarray / Dask / Zarr
HPC and multi-GPU training (NVIDIA DGX, A100 and H100)

Experience

University at Albany
TU Delft
IIT Madras

Postdoctoral Associate, Atmospheric Sciences Research Center - University at Albany

Sep 2024 - Present

Researching AI-augmented weather prediction for wind and extreme events.

Develop deep-learning frameworks for wind gust nowcasting and field reconstruction from sparse station data.
Build scalable training/inference workflows on NVIDIA A100 multi-GPU infrastructure.
Publish and present at venues including AMS and Gordon Research Conference.

Postdoctoral Researcher, Geosciences and Remote Sensing - TU Delft

Sep 2022 - Aug 2024

Led research on offshore wind resource assessment and atmospheric modeling.

Modeled frontal low-level jets and extreme wind ramps over the North Sea.
Estimated offshore wind power potential using gray-zone atmospheric modeling.
Published work in Wind Energy Science, Energy, and related journals.

Institute Postdoctoral Equivalent Fellow - IIT Madras

Jan 2022 - Jun 2022

Advanced WRF parameter sensitivity and calibration for tropical cyclone prediction.

Applied machine-learning-driven multi-objective optimization to improve cyclone forecasts.
Integrated data assimilation and sensitivity analysis for robust model performance.

Education

2017 - 2022

Integrated MS & PhD, Mechanical Engineering

Indian Institute of Technology Madras

Dissertation: Sensitivity based Calibration Strategy with Data Assimilation to Improve the Prediction of Cyclones over the Indian Subcontinent.

2011 - 2015

B.Tech (Honors), Mechanical Engineering

Rajiv Gandhi University of Technology - NUZVID

Selected Work

Deep Learning Nowcasting Mesonet

Wind Gust Field Generation from Sparse Observations

Deep-learning framework for generating high-resolution wind gust fields from sparse Mesonet observations, designed for operationally relevant nowcasting.

View Preprint