Houlong Zhuang

Prediction of New Methane-Capture Materials Using Large Language Models

Development of efficient methane-capture materials will mitigate global warming trends by removing a gas that traps 28 times more heat than CO2.

Program: FURI

Accelerating the Discovery of High-K Oxides for Future Generations of Semiconducting Devices through Computational Simulations

Computer simulations can enhance the discovery process of high-k oxides, which improve performance and sizing down of semiconducting devices.

Program: FURI

Exploration of Potential Anisotropic Optical Properties of Triclinic SiGe Lattices

The study of effective silicon photonics is a necessity for improving the operation speed of semiconductors.

Program: FURI

Utilizing Neural Networks with Molecular Dynamics to Design High-Entropy Functional Alloys for Thermoelectric Technology

Graph Neural Networks can make the process of identifying high-entropy functioning alloys much easier.

Program: FURI

Accelerating the Discovery of High-k Oxides for Future Generations of Semiconducting Devices through Computational Simulations

Computer simulations can enhance the discovery process of high-k oxides, which improve performance and sizing down of semiconducting devices.

Program: FURI

Computational Discovery of Novel Wide-Bandgap Semiconductors

Studying the optimization of Ga2O3-based semiconductors can lead to significant advancements in high-performance electronic devices.

Program: FURI

Thermoelectric Material Discovery Using Machine Learning

Using data-driven machine learning models and density functional theory will help identify potential new thermoelectric materials.

Program: MORE

Hydrogen Embrittlement Prediction Using Machine Learning

Using machine learning to predict hydrogen embrittlement will improve hydrogen storage so the world can shift to a sustainable alternative fuel.

Program: FURI

Neural ODE Modeling for Many-Body Interactions

Using neural ordinary differential equations to predict stochastic particle behavior will allow for prediction of the start and end behavior of cancer cells and tumors.

Program: FURI

Utilizing Density Functional Theory to Compute the Efficacy of a Rippled Janus Structure for use in Optoelectronics

Testing how certain sections of an atomic structure bind differently will lead to more efficient structures for use in advanced electronics.

Program: FURI

Neural ODE Modeling for Many-Body Interactions

Developing a neural network model for predictive modeling of many-body interactions will help simulate collective dynamics of cancer cells.

Program: FURI

Utilizing Density Functional Theory to Compute the Efficacy of a Practical Material for Industrial Direct Air Capture via a Copper Metal Organic Framework

Computational modeling of a specific atomic structure that is efficient at capturing CO2 from the air can help fight climate change.

Program: FURI

Discovering Tesselations of 2D Piezomagnetic Materials

Studying patterns in 2D materials can lead to discovering new useful material properties for technologies such as batteries.

Program: FURI

ML Phase Prediction of High-Entropy Alloys

Using machine learning to explore phase selection rules will help discover novel metal alloys with useful properties.

Program: MORE

Machine Learning Models for Accelerating Discovery and Design of Energy-Related Materials

Program: FURI

Ab Initio Playing Pentagon Puzzles

Program: MORE

Prediction of New Methane-Capture Materials Using Large Language Models

Development of efficient methane-capture materials will mitigate global warming trends by removing a gas that traps 28 times more heat than CO2.

Program: FURI