Using artificial neural networks designed to emulate the inner workings of the human brain, deep-learning algorithms deftly peruse and analyze large quantities of data. Applying this technique to science problems can help unearth historically elusive solutions.
Oak Ridge National Laboratory scientists have created open source software that scales up analysis of motor designs to run on the fastest computers available, including those accessible to outside users at the Oak Ridge Leadership Computing Facility.
A team of scientists led by Oak Ridge National Laboratory used machine learning methods to generate a high-resolution map of vegetation growing in the remote reaches of the Alaskan tundra.
By automating the production of neptunium oxide-aluminum pellets, Oak Ridge National Laboratory scientists have eliminated a key bottleneck when producing plutonium-238 used by NASA to fuel deep space exploration.
Scientists at Oak Ridge National Laboratory and Hypres, a digital superconductor company, have tested a novel cryogenic, or low-temperature, memory cell circuit design that may boost memory storage while using less energy in future exascale and quantum computing applications.
Oak Ridge National Laboratory scientists studying fuel cells as a potential alternative to internal combustion engines used sophisticated electron microscopy to investigate the benefits of replacing high-cost platinum with a lower cost, carbon-nitrogen-manganese-based catalyst.
ORNL helps develop hybrid computational strategy for efficient sequencing of massive genome datasets
Computing experts at the Department of Energy’s Oak Ridge National Laboratory collaborated with a team of university researchers and software companies to develop a novel hybrid computational strategy to efficiently discover genetic variants