Skip to main content

AI in the News

Adaptive Language Model Training for Molecular Design
Andrew Blanchard
April 21, 2022

Oak Ridge National Laboratory (ORNL) researchers have developed a new strategy for molecule generation to accelerate molecular design for drug discovery applications. 

Generalizable Flow-based Policy Learning in Reinforcement Learning
Sirui Bi
April 01, 2022

Oak Ridge National Laboratory (ORNL) researchers have developed a novel, generalizable policy learning approach in deep reinforcement learning (RL) for future applications in additive manufacturing. 

Crystal Structure Generation by Reconstructing Representations
Victor Fung
March 31, 2022

Researchers have developed a novel architecture-agnostic method for the generation of atomic structures for use in materials discovery.

Adaptive Single Parameter Total Variation Regularization for Derivative Estimation
Wesley Williams
March 22, 2022

An adaptive single parameter total variation regularization (ASP-TVR) was developed for accurate and faster estimation of derivatives from noisy data to support the development of physics-informed machine learning methods.

Data Augmentation for Reinforcement Learning 
Helia Zandi, Data Augmentation for RL
March 03, 2022

Researchers have developed generated synthetic data that preserves both the feature distributions and the temporal dynamics in the original data.  

Graph Neural Networks for Prediction of CO2 Adsorption in Nano-Pores 
Guojing Cong, Accelerated Discovery
March 03, 2022

Researchers have developed a graph-based convolutional neural network approach for predicting and ranking gas adsorption properties of crystalline MOF adsorbents for application in post-combustion capture of CO2.

Artificial Neural Network Potentials for Mechanics and Fracture Dynamics of Materials
Gang Seob Jung, Artificial Intelligence for Scientific Discovery
January 11, 2022

Researchers have developed a training data and artificial neural network potential for mechanics and fracture of materials. 

Machine Learning Force Fields for Neutron Scattering Data Analysis 
Yongqiang Cheng, Machine Learning for Neutrons.  
January 10, 2022

Researchers have developed a workflow to simulate neutron scattering spectra using complex atomistic models enabled by machine learning force fields.

Self-Supervised Anomaly Detection via Normalizing Flows 
Jiaxin Zhang, Artificial Intelligence for Robust Engineering and Science
December 06, 2021

Researchers have developed a novel self-supervised anomaly detection approach based on normalizing flows with an active learning scheme for determining processing parameters in additive manufacturing.

Crystallographic and Thermodynamic Properties of Multi-Component Solid Solution Alloys
Massimiliano (Max) Lupo Pasini, Artificial Intelligence for Scientific Discovery: Surrogates.
December 06, 2021

Researchers have developed deep learning models that have trained to predict crystallographic and  thermodynamic properties of multi-component solid solution alloys, enabling the design of advanced alloys.

A Prediction Interval Method for Machine Learning Model Uncertainty Quantification 
Dan Lu, Assurance Crosscut
December 06, 2021

Researchers have developed a distribution-free, computationally efficient, and practically reliable prediction interval method to quantify machine learning (ML) model prediction uncertainty.

HydraGNN— Distributed Multi-Headed Graph Convolutional Neural 
Massimiliano (Max) Lupo Pasini, Artificial Intelligence for Scientific Discovery: Surrogates.
October 18, 2021

Researchers have developed a distributed implementation of graph convolutional neural networks.  The code has been shown to successfully take advantage of ORNL’s HPC resources to produce fast and accurate predictions of macroscopic material properties using atomic information.