Pei Zhang Computational Scientist Contact ZHANGP1@ORNL.GOV All Publications Scalable training of trustworthy and energy-efficient predictive graph foundation models for atomistic materials modeling: a case study with HydraGNN MDLoader: A Hybrid Model-Driven Data Loader for Distributed Graph Neural Network Training Enhancing molecular design efficiency: Uniting language models and generative networks with genetic algorithms Transferring a Molecular Foundation Model for Polymer Property Predictions DDStore: Distributed Data Store for Scalable Training of Graph Neural Networks on Large Atomistic Modeling Datasets User Manual - HydraGNN: Distributed PyTorch Implementation of Multi-Headed Graph Convolutional Neural Networks Deep learning workflow for the inverse design of molecules with specific optoelectronic properties... A direct numerical simulation study of the dilution tolerance of propane combustion under spark-ignition engine conditions... Computational Workflow for Accelerated Molecular Design Using Quantum Chemical Simulations and Deep Learning Models Autoencoder neural network for chemically reacting systems Scalable training of graph convolutional neural networks for fast and accurate predictions of HOMO-LUMO gap in molecules Multi-task graph neural networks for simultaneous prediction of global and atomic properties in ferromagnetic systems PI3NN: Out-of-distribution-aware Prediction Intervals from Three Neural Networks... An out-of-distribution-aware autoencoder model for reduced chemical kinetics A prediction interval method for uncertainty quantification of regression models... A priori examination of reduced chemistry models derived from canonical stirred reactors using three-dimensional direct numerical simulation datasets Reduced Models for Chemical Kinetics derived from Parallel Ensemble Simulations of Stirred Reactors Key Links Organizations Computing and Computational Sciences Directorate Computational Sciences and Engineering Division Advanced Computing Methods for Physical Sciences Section Multiscale Materials Group