We successfully utilized OCLF ORNL GPU computing resources for efficient uncertainty analysis, which addressed the computational overhead caused by our proposed probabilistic models.
Filter Research Highlights
Area of Research
A graph convolutional neural network (GCNN) was trained to accurately predict formation energy and mechanical properties of solid solution alloys crystallized in different lattice structures, thereby advancing the design of alloys for improving mechanic
A new method was developed for the discovery of fundamental descriptors for gas adsorption through deep learning neural network (DNN) approach. This approach has great potential to identify structural parameters for gas adsorption.
Developed a deep-learning approach to automatically create libraries of structural and electronic properties of atomic defects in 2D materials.
Direct experimental evidence of gas-phase methyl radicals in propane oxidative dehydrogenation (ODHP) combined with density functional theory (DFT) calculations uncovers the mechanism behind the exceptional selectivity to olefins over BN catalysts