Research Statement: Exploring the impact tolerance of composite materials demands a multi-faceted approach, integrating experimental, analytical, numerical, and machine learning methods. By leveraging machine learning, we aim to enhance our understanding of composite behavior under impact loads, advancing their performance and durability across various applications.

Research Statement: The investigation of post impact flexural strength in composite materials is critical for enhancing the structural integrity and performance of various applications, ranging from aerospace to automotive industries. In my research, I adopt a multidisciplinary approach, combining experimental analysis, simulation techniques, and Machine Learning methodologies to comprehensively study and optimize the post impact flexural strength of composite materials.

Research statement: Bulk mechanical properties are an important aspect when designing a polymer system. Not only will the chains components (such as functional groups) play a role, but so will any interactions between chains such as interchain crosslinks. Through the use of machine learning, we aim to explore with experimental data how to design materials and elucidate the underlying mechanisms that contribute to bulk mechanical properties.

Research Statement: Lithium-Ion batteries are an increasingly important aspect of everyday technology that still needs to be improved. Using a Machine Learning approach, which is a branch of artificial intelligence (AI) that focuses on the use of data and algorithms to gradually improve the accuracy of how we learn, we look to understand and improve on solid state polyelectrolytes in lithium-ion batteries.

Electrospinning is a technique used to fabricate microscale and nanoscale fibers with numerous applications ranging from filtration to biomedical. Generating machine learning models that predict electrospun fiber morphology can reduce the time and materials used to generate electrospun fibers with the desired morphology.

The growing problem of human hair waste has inspired creative study into its potential usage in air filtration and composite materials. In this work, we present a novel approach to nanofiber reinforcement of Kevlar aerogels using discarded human hair. By using the power of Machine Learning and Python, we find pathways to optimize aerogel designs for superior filtration performance.

Soft particle glasses (SPGs) are complex yield stress fluids widely used as rheology modifiers. Using a machine learning approach, our goal is to predict the stress-induced dynamics and flow heterogeneities in these fluids.

Vitrimers are polymerics with dynamic covalent crosslinking bonds which allow for rapid rearrangement of the topology at elevated temperatures. Our objective is to use molecular simulations to study the macroscopic and rheological properties of these materials under various stimuli such as temperature and stress.

Feature selection techniques play a crucial role in steering machine learning models towards identifying their most crucial features. In this context, our research zeroes in on Bayesian methods, setting them against conventional feature selection approaches. By leveraging Ionic Liquid data, we aim to scrutinize their respective impacts on the performance and interpretability of models.

Microscopic dynamics and rheology of ionomers

Ionomers are polymers in which ionized groups create ionic crosslinks in the intermolecular structure. The primary effects of ionic functionalization of a polymer are to increase the glass transition temperature, melt viscosity, and characteristic relaxation times. Polymer microstructure is also affected, and it is generally agreed that in most ionomers, microphase-separated, ion-rich aggregates form as a result of strong ion–dipole attractions. The major effect of the ionic aggregate was to increase the relaxation processes. This in turn increases the melt viscosity and is responsible for the network-like behavior of ionomers above the glass transition temperature. Coarse-grained MD simulations are used in this project to connect their molecular structure to their macroscopic rheology. In this work, we create ionomer structures with different architectures and study the network formation at different degrees of electrostatic interactions