Ph.D. Candidate

Sweety Sarker

Ph.D., Aerospace Engineering, Embry-Riddle Aeronautical University

Machine learning and physics-informed neural network (PINN) models for real-time, micro-scale atmospheric flow prediction

Research Areas

Real-Time and AI-Accelerated Modeling Atmospheric and Environmental Flows

Projects

active2025–2027

Atmospheric Flight Path Prediction

Real-time and near-real-time CFD-based prediction of atmospheric flight trajectories, supporting rapid decision-making for aerospace systems operating in complex, evolving atmospheric conditions.

DARPA (subcontract through Mississippi State University)

Publications

2026

Physics-Informed Neural Networks for Real-Time, Micro-scale Atmospheric Flow Prediction

S Sarker, B Cavainolo, M Kinzel

AIAA SCITECH 2026 Forum, 1933, 2026

View ↗

2026

Session 1: Platform Development I

DKA Adkins, DGBH de Azevedo, BA Cavainolo, S Sarker, MP Kinzel, et al.

View ↗

2026

WindSDK: A Unified Framework for Querying Atmospheric Data

B Cavainolo, S Sarker, MP Kinzel, JJ Bird, J Dyer, M Berk

View ↗

2026

A Study of Physics-Informed Neural Networks applied to Real-Time Atmospheric Flow Estimation for Glider Flight Planning

S Sarker, BA Cavainolo, JJ Bird, M Berk, MP Kinzel

View ↗

2025

An Investigation of the Principle of Minimum Pressure Gradient Method on Airfoils Through Stall

S Sarker, MP Kinzel

AIAA SCITECH 2025 Forum, 1071, 2025

View ↗

2025

Physics-Informed Neural Networks for Predicting Steady Incompressible Flow Around Obstacles in Urban and Aerodynamic Settings

S Sarker, BA Cavainolo, M Kinzel

78th Annual Meeting of the Division of Fluid Dynamics, 2025

View ↗

2024

Analysis of the Principle of Minimum Pressure Gradient Method on Airfoil Behavior through Stall

S Sarker, M Kinzel

APS Division of Fluid Dynamics Meeting Abstracts, L13. 010, 2024

View ↗