I’m a machine learning research engineer.
My work spans scientific machine learning, inverse problems, and applied AI, including language and vision models. I develop and evaluate research methods, and build systems that put those ideas to use.
I’m interested in philosophy, knowledge representation, leadership, and politics. More about me
Research
I currently work on scientific machine learning and its applications in computational fluid dynamics.
My published work focuses mainly on two-phase flow in porous media, including physics-informed models, training methods, and inverse modelling.
My personal interests, however, lie in knowledge representation, causality, and cognitive AI. I am still developing this research and have not yet published work on these questions.
Read about my researchWriting
Essays on personal experience, intelligence, philosophy, science, leadership, and world affairs.
No essays yet.
Open the writing archiveSelected publications
Coupled pressure and saturation prediction for two-phase flow in porous media using physics-informed neural networks (PINNs)
One physics-informed network trained on both the pressure and water-saturation equations got pressure right but misplaced the water front. Bigger networks and reweighting didn’t fix it; a small diffusion term with tuned weights did.
Computer Methods in Applied Mechanics and Engineering
Performance and stability of physics-informed Kolmogorov-Arnold networks for two-phase transport in porous media: A comparative study with physics-informed neural networks
Kolmogorov–Arnold networks promise accuracy with fewer parameters. On a sharp water front, ours used a third of the parameters but needed over twice the smoothing and about 50 times the training time.
Results in Engineering
Identifiability and Conditioning of Flux-Parameter Inversion for the Buckley–Leverett Equation
Physics alone cannot fix the viscosity ratio in a water-displaces-oil model. We show which measurements can, how much their errors are amplified, and why a good fitted field does not guarantee a good estimate.
Mathematics