MatDBForge
Stars: 3
An integrated platform to orchestrate Machine Learning Interatomic potential training, data generation and benchmarking via Active Learning.
Portfolio
A collection of some of my projects, publications and designs.
Published Codes
simul-protein-small-molecule
Stars: 6
Toolkit to study Liquid-Liquid Phase Separation in Intrinsically Disordered Protein systems using the OpenMM python API.
Publications
A foundational model for reaction networks on metal surfaces
Year: 2026 | Citations: 8
This paper introduces CARE, a foundational model that combines a rule-based reaction network generator, a graph neural network with uncertainty quantification (GAME-Net-UQ), and microkinetic modeling to evaluate complex catalytic reactions on metal surfaces, such as the Fischer-Tropsch synthesis with over 370,000 reactions thereby breaking previous limits in atomistic simulations.
Nature Chemical Engineering, 1-12
Water-hydroxide trapping in cobalt tungstate for proton exchange membrane water electrolysis
Year: 2024 | Citations: 332
This paper presents a novel cobalt tungstate catalyst for proton exchange membrane water electrolysis that achieves a threefold improvement in activity and maintains stable operation for over 600 hours without relying on precious metals.
Science, Vol 384, Issue 6702, 1373-1380
Polyethylene hydrogenolysis to liquid products over bimetallic catalysts with favorable environmental footprint and economics
Year: 2025 | Citations: 4
This paper presents a novel bimetallic ruthenium-nickel catalyst for the hydrogenolysis of polyethylene waste into liquid products and uses system-level technoeconomic and life cycle assessments to define a viable threshold for profitable and low-emission plastic recycling.
Nature Communications, Vol 16, Issue 1, 9791
Enhanced proton transport in Fluorine-free membranes by balancing confinement and pore chemistry
Year: 2025 | Citations: 1
This paper describes the optimization of a fluorine-free liquid crystalline poly(epichlorohydrin) proton exchange membrane by using machine learning potentials to identify key descriptors for proton mobility based on water confinement and internal pore chemistry
ChemRxiv Vol 2025, Issue 0616
Dynamic Polaronic Control of Metal Cluster Adaptability on Reducible Oxides
Year: 2026 | Citations: 0
The paper showcases a physics-guided machine learning framework to evaluate platinum clusters on reducible ceria, revealing that dynamic polaron swarms predominantly control the structural and electronic adaptability of the metal catalysts, offering new quantitative design principles for defect-driven catalyst optimization.
Journal of the American Chemical Society
3D Design
