Atmospheric Water Harvesting with MOFs and COFs
Grand Canonical Monte Carlo simulations and machine-learned potentials to design metal-organic and covalent-organic frameworks for industrial-scale water capture.
Research
A few highlights from my research on molecular simulation and machine learning for soft and nano materials. For the full publication record, see [Publications](/publications/).Coarse-Grained Modeling of Nanoparticle Self-Assembly
Kremer–Grest based coarse-grained models of grafted nanoparticles to study self-assembly, phase behavior, and shear viscosity.
Sequence-Defined Design of Copolymers
Combining evolutionary computing with coarse-grained MD to map the sequence–structure Pareto frontier of copolymers.
Predictive Machine Learning for Industrial Coatings
A data-driven framework linking molecular-level descriptors of polymer-nanoparticle formulations to the rheology and performance of industrial paints, developed with Accenture.
Machine-Learned Potentials for Polymer-Grafted Nanoparticles
Deep learning models of the potential of mean force (PMF) between polymer-grafted nanoparticles, replacing expensive direct MD calculations.