Researchers have shown that an algorithm with no training in materials science can scan the text of millions of papers and uncover new scientific knowledge. A Berkeley Lab-led team collected 3.3 million abstracts of published materials science papers and fed them into an algorithm. By analyzing relationships between words the algorithm was able to predict discoveries of new thermoelectric materials years in advance and suggest as-yet unknown materials as candidates for thermoelectric materials.
A team of researchers from Berkeley Lab and UC Berkeley are developing innovative machine learning tools to pull contextual information from scientific datasets and automatically generate metadata tags for each file. Scientists can then search these files via a web-based search engine for scientific data, called Science Search, that the Berkeley team is building.
How will the farms of the future feed a projected 9.8 billion people by 2050? Berkeley Lab’s “smart farm” project marries microbiology and machine learning in an effort to reduce the need for chemical fertilizers and enhance soil carbon uptake, thus improving the long-term viability of the land while increasing crop yields.
While it may be the era of supercomputers and “big data,” without smart methods to mine all that data, it’s only so much digital detritus. Now researchers at Lawrence Berkeley National Laboratory and UC Berkeley have come up with a novel machine learning method that enables scientists to derive insights from systems of previously intractable complexity in record time.
Berkeley Lab mathematicians have developed a new approach to machine learning aimed at experimental imaging data. Rather than relying on the thousands of images used by typical machine learning methods, this new approach “learns” much more quickly and requires far fewer images.
Berkeley Lab physicists and their collaborators have demonstrated that computers are ready to tackle the universe’s greatest mysteries – they used neural networks to perform a deep dive into data simulating the subatomic particle soup that may have existed just microseconds after the big bang.
A team of scientists at Berkeley Lab has developed an unsupervised multi-scale machine learning technique that can automatically and specifically capture biomedical events or concepts directly from raw data.