Physics-informed learning
Learning methods that respect physical laws, combining differential equations and data to model complex systems.
Research portfolio
Learning the language of physical systems.
Scientific machine learning for fluid dynamics, climate, thermal transport, and materials design.
Resolving the missing scales of turbulence
Combining neural operators and diffusion models to recover high-frequency flow structures.
Explore the research ↗
Bringing learned corrections into Earth systems
Online neural operator updates for stable, multiyear hybrid climate simulations.
Explore the research ↗
Designing materials from desired behavior
Data-efficient neural operators for the characterization and inverse design of stochastic metamaterials.
Explore the research ↗
Learning heat transfer at ultrafast scales
Neural network modeling of electron and lattice dynamics in laser-heated thin films.
Explore the research ↗Research directions
Methods that connect across domains.
Generative AI for science
Generative models that recover fine-scale structure and improve scientific prediction, from turbulent flows to climate.
Scientific discovery & decision-making
Interpretable, data-efficient AI and autonomous decision-making through reinforcement learning, agentic systems, and physical knowledge.
Connect
Good science starts
with a conversation.
Interested in research collaboration or joining SPARKS Lab? I welcome conversations across computer science, mathematics, physics, and engineering.
aniruddha_bora@txstate.edu ↗
Department of Computer Science · Texas State University
310D Comal · San Marcos, Texas 78666