Publications
An early version of this site said, "on the path to finding myself at an institute of technology, I've done... a surprisingly small amount of engineering." I don't think this was ever true, as many of my early projects have an engineer-like curiosity to them, but it is absolutely not true now. Technical research in materials and chemical informatics, decarbonization, operations, and even history have become core parts of my life. The publications below are only a small sample of my interests. For a better look, please go to "OTHER PROJECTS."
Machine Learning for Green Solvents: Assessment,Selection and Substitution
This work was published in Advanced Science on November 16, 2025. Read it here!
Abstract
Strict environmental regulations have intensified the demand for green solvents that can replace hazardous ones without compromising performance. Existing methods for estimating solvent sustainability rely on Solvent Selection Guides (SSGs), which assign scores based on environmental, health, safety, and waste (EHSW) criteria, covering as few as 200 solvents. Expanding these guides is tedious, as it requires over 30 properties per solvent, many of which are often unavailable. Moreover, identifying greener alternatives within the limited SSG pool is challenging due to the need to balance conflicting criteria such as sustainability, cost, and performance. To address these limitations, a data-driven pipeline is presented for assessing the sustainability of solvents and identifying greener substitutes. Three models are trained and evaluated on the GlaxoSmithKline Solvent Sustainability Guide (GSK SSG) to predict “greenness” metrics: a traditional Gaussian Process Regression (GPR) model, a fine-tuned GPT model (FT GPT), and a GPT model using in-context learning (ICL). It is found that GPR slightly outperforms language-based GPT models and is used to evaluate 10,189 solvents, forming GreenSolventDB–the largest public database of green solvent metrics. These predictions are combined with Hansen solubility parameter-based metrics to identify greener solvents with solubility behavior similar to hazardous solvents. This approach is validated through case studies on benzene and diethyl ether, with predicted alternatives aligning well with known greener substitutes. Building on this success, novel alternatives are proposed for the hazardous solvents listed in the GSK SSG. This framework for quantifying solvent sustainability and identifying greener substitutes is expected to significantly accelerate the discovery and adoption of environmentally-friendly solvents.
Polymer design for solvent separations by integrating simulations, experiments and known physics via machine learning
This work was published in Nature Computational Materials on June 19, 2025. Read it here!
Abstract
This study guides the discovery of sustainable high-performance polymer membranes for organic binary solvent separations. We focus on solvent diffusivity in polymers, a key factor in quantifying solvent transport. Traditional experimental and computational methods for determining diffusivity are time- and resource-intensive, while current machine learning (ML) models often lack accuracy outside their training domains. To overcome this, we fuse experimental and simulated diffusivity data to train physics-enforced multi-task ML models, achieving more robust predictions in unseen chemical spaces and outperforming single-task models in data-limited scenarios. Next, we address the challenge of identifying optimal membranes for a model toluene-heptane separation, identifying polyvinyl chloride (PVC) as the optimal membrane among 13,000 polymers, consistent with literature findings, thereby validating our methodology. Expanding our search, we screen 1 million publicly available and 7 million chemically recyclable polymers, identifying greener halogen-free alternatives to PVC. This capability is expected to advance membrane design for solvent separations.
Conductivity Prediction Model for Ionic Liquids
Using Machine Learning
I worked with the Ramprasad Group at Georgia Tech and graduate student Dr. Shruti Venkatram from October 2020 to June 2022 to explore the capabilities of deep neural networks to predict the conductivity of Ionic liquids (ILs). What began as a small lab internship quickly turned into a published first-author paper and accompanying ML model. In our work, we sought to construct a deep neural network to rapidly and accurately predict the conductivity of ionic liquids. We hope our model furthers research in the fields of batteries, fuel cells, and supercapacitors.
The work was published by the Journal of Chemical Physics (JCP) as part of the Chemical Design by Artificial Intelligence special topic on June 7, 2022. Read it here! (DOI: 10.1063/5.0089568)