Filter Research Highlights
Area of Research
- Advanced Manufacturing (1)
- Building Technologies (1)
- Clean Energy (3)
- Climate and Environmental Systems (3)
- Computational Biology (1)
- Computational Engineering (8)
- Computer Science (52)
- Data (1)
- Energy Sciences (3)
- Geographic Information Science and Technology (1)
- Materials (7)
- Materials for Computing (3)
- Mathematics (4)
- Quantum information Science (10)
- Renewable Energy (2)
- Sensors and Controls (1)
- Supercomputing (9)
![Exploring Protein Self-Organization with Machine Learning](/sites/default/files/styles/list_page_thumbnail/public/2021-04/Kalinin_thumbnail_260x160.jpg?h=a08abdbb&itok=oCj9TN1a)
The dynamic of complex ordering systems with active rotational degrees of freedom exemplified by protein self-assembly is explored using a machine learning workflow that combines deep learning-based semantic segmentation and rotationally invariant
![Paul Kent highlight March 2021](/sites/default/files/styles/list_page_thumbnail/public/2021-03/Doc1%20%282%29.jpg?h=763d6ab5&itok=Ode0g1QQ)
Quantum Monte Carlo (QMC) methods are used to find the structure and electronic band gap of 2D GeSe, determining that the gap and its nature are highly tunable by strain.
![Cu-d and O-px/y orbitals in the CuO plane of the cuprate superconductors](/sites/default/files/styles/list_page_thumbnail/public/2021-03/2021-03_BES_Highlight_Maier_0.jpg?h=e1585ed0&itok=lmniq_aA)
Quantum Monte Carlo simulations reveal that Cooper pairs in the cuprate high-Tc superconductors are composed of electron holes on the Cu-d orbital and on the bonding molecular orbital constructed from the four surrounding O-p orbitals.
![Training runs with molecules of 20 atoms or less. Results are shown for control (blue) and drug replacement with recombination (green). A) Histogram showing number of new molecules produced in control run for different drug-likeness scores. B) Histogram showing number of new molecules produced in our approach using updates to the training data for different drug-likeness scores. C) A few sample new molecules from the drug replacement with recombination run. CSED ORNL Computational Sciences and Engineering](/sites/default/files/styles/list_page_thumbnail/public/2021-05/gans_csed_ornl.png?h=8681913c&itok=yes9lN-i)
Generative machine learning models, including GANs (Generative Adversarial Networks), are a powerful tool toward searching chemical space for desired functionalities.
![This figure illustrates our workflow for combining transfer learning and self-training to improve performance on biomedical NER tasks. CSED ORNL Computational Sciences and Engineering](/sites/default/files/styles/list_page_thumbnail/public/2022-02/a_pre-training_and_self-training_approach_for_biomedical_named_entity_recognition.png?h=2d435d45&itok=QBdj5pa5)
A team at ORNL has demonstrated that the combination of transfer learning and semi-supervised learning can significantly reduce the amount of labeled data required to obtain strong performance in biomedical named entity recognition (NER) tasks.
![Radiofrequency pulse is an approach to control Rabi oscillation for quantum optics, MRI, etc. The ORNL method enables the ideal location of photon measurements in the pulse frequency and duration space to achieve a Rabi oscillation with desired Rabi and detuning frequencies. Left: the designed measurement points (from pink dots to red dots). Right: the evolution of the posterior distribution (the blue clouds) with the increase of measurement from 1 to 500. Computer Science and Mathematics CSMD ORNL](/sites/default/files/styles/list_page_thumbnail/public/2021-05/a_novel_method_for_bayesian_experimental_design_with_implicit_models.png?h=08c29538&itok=LmjpLXrG)
ORNL researchers developed a stochastic approximate gradient ascent method to reduce posterior uncertainty in Bayesian experimental design involving implicit models.
![The team embedded a programmable model into a D-Wave quantum computer chip. Credit: D-Wave CSED Computational Sciences and Engineering Division ORNL](/sites/default/files/styles/list_page_thumbnail/public/2021-05/quantum_dwave_csed_ornl.png?h=5e46f5ac&itok=k0GGAlcm)
Researcher proved that quantum resources are capable of revealing the magnetic structure and properties of magnetic materials such as rare earth tetraborides.
![Excited State Pathways Present Lower Barriers for (Atomically Precise) Defect Manipulation in Graphene](/sites/default/files/styles/list_page_thumbnail/public/2021-02/Lingerfelt%20pic_thumbnail_260x160.jpg?h=a08abdbb&itok=KyxohsRx)
Single atom impurities in graphene diffuse under e-beam irradiation. This phenomenon has been used to direct defect diffusion site-by-site with focused high-energy e-beams found in STEMs and stable defect arrays and heterostructures have been