A research collaboration between Lawrence Berkeley National Laboratory (Berkeley Lab), Pacific Northwest National Laboratory (PNNL), Brown University, and NVIDIA has achieved exaflop performance on the Summit supercomputer with a deep learning application used to model subsurface flow in the study of nuclear waste remediation. Their achievement, which will be presented during the "Deep Learning on Supercomputers" workshop at SC19, demonstrates the promise of physics-informed generative adversari... PHYS.ORG · 1 month
Researchers perfect nanoscience tool for studies of nuclear waste storage  nanowerk · 2 days
The study involved the first-ever use of antimatter to investigate processes connected to potential long-term storage of waste from nuclear reactors. more
Researchers perfect nanoscience tool for studies of nuclear waste storage  PHYS.ORG · 3 days
Safe nuclear waste storage, new ways of generating and storing hydrogen, and technologies for capturing and reusing greenhouse gases are all potential spinoffs of a new study by... more
Researchers perfect nanoscience tool for studies of nuclear waste storage  SCIENCE DAILY · 3 days
Studying radiation chemistry and electronic structure of materials at scales smaller than nanometers, scientists prepared samples of clay in ultra-thin layers. Working at the TRIUMF particle accelerator, they... more
Deep learning helps tease out gene interactions  SCIENCE DAILY · 4 days
Computer scientists have taken a deep learning method that has revolutionized face recognition and other image-based applications in recent years and redirected its power to explore the relationship between genes. more
All-optical diffractive neural networks process broadband light  PHYS.ORG · 2 weeks
Diffractive deep neural network is an optical machine learning framework that blends deep learning with optical diffraction and light-matter interaction to engineer diffractive surfaces that collectively perform optical computation at the speed of light.... more
Breakthrough in 'distributed deep learning'  SCIENCE DAILY · 6 days
Computer scientists, using a divide-and-conquer approach that leverages the power of compressed sensing, have shown they can train the equivalent of a 100 billion-parameter distributed deep learning network on a single machine in less than 35 hours for... more
Neural architecture search automates the development of deep learning-based models for cancer research  NEWS MEDICAL · 4 weeks
Argonne researchers have created a neural architecture search that automates the development of deep-learning-based predictive models for cancer data. more
Study reveals role of corpora amylacea in expelling brain waste substances  NEWS MEDICAL · 2 weeks
An article published in Proceedings of the National Academy of Sciences describes a new pathway in the central nervous system to expel waste substances from the... more
Swimming a 'no-no' for those undergoing deep brain stimulation therapy  NEWS MEDICAL · 2 weeks
Researchers have found that persons who have had a deep brain stimulation device implanted for treatment of Parkinson’s disease may have lost their ability to swim. The small... more
Deep learning shows potential to improve chest X-ray interpretation  NEWS MEDICAL · 2 weeks
A sophisticated type of artificial intelligence can detect clinically meaningful chest X-ray findings as effectively as experienced radiologists, according to a study published in the journal Radiology. more
Using AI to predict Earth's future  PHYS.ORG · 4 weeks
A recent "deep learning" algorithm—despite having no innate knowledge of solar physics—could provide more accurate predictions of how the sun affects our planet than current models based on scientific understanding. more
Using AI to predict Earth’s future  ESA · 4 weeks
A recent ‘deep learning’ algorithm – despite having no innate knowledge of solar physics – could provide more accurate predictions of how the Sun... more
Machine learning successfully replicates cell architecture  NEWS MEDICAL · 3 weeks
A new study reports the use of machine learning to help form complex cell architectures from pluripotent stem cells. more
Machine learning can help us understand conversations about death  SCIENCE DAILY · 5 days
Researchers have used machine learning and natural language processing to better understand what end-of-life conversations look like. Borrowing techniques used to study fiction, where machine learning algorithms analyze manuscripts to... more
Deep learning to analyze neurological problems  SCIENCE DAILY · 3 weeks
Getting to the doctor's office for a check-up can be challenging for someone with a neurological disorder that impairs their movement, such as a stroke. But what if the patient could just take a video clip... more
Virtual and mixed reality inferior to traditional learning in anatomy education  PHYS.ORG · 4 weeks
A study from McMaster University has shown that traditional ways of learning anatomy remain superior to those that rely on digital media. more
Why doesn't deep-brain stimulation work for everyone?  SCIENCE DAILY · 5 days
Researchers have mapped nine functional networks in the deep-brain structures of 10 healthy people, an accomplishment that could lead to improvements in deep-brain stimulation therapy for severe cases of Parkinson's disease and other neurological... more
Biotech breakthrough turns waste biomass into high value chemicals  PHYS.ORG · 3 weeks
A move towards a more sustainable bio-based economy has been given a new boost by researchers who have been able to simplify a process to transform waste materials into high... more
Biotech breakthrough turns waste biomass into high value chemicals  nanowerk · 3 weeks
A move towards a more sustainable bio-based economy has been given a new boost by researchers who have been able to simplify a process to transform waste materials into high... more
Super-cool addition to deep space family  ESA · 3 days
Image: It's confirmed! ESA is building its fourth deep space antenna – much like the Cebreros dish pictured here – that will ensure upcoming missions like... more
Deep learning identifies molecular patterns of cancer  SCIENCE DAILY · 2 weeks
An artificial intelligence platform can analyze genomic data extremely quickly, picking out key patterns to classify different types of colorectal tumors and improve the drug discovery process. The deeper analysis shows some colorectal subtypes... more
Study uses machine learning and health data to identify suicide risk factors  NEWS MEDICAL · 6 days
First-of-its-kind study used machine learning and health data from the entire Danish population to create sex-specific suicide risk profiles, illuminating the complex mix of... more
Sustaining roads with grape and agricultural waste  SCIENCE DAILY · 2 weeks
The US spends $5 billion a year to repair damages to road infrastructure from winter snow and ice control operations and the use of traditional deicers. A team of researchers is developing a more... more
Face time innovates online language learning  PHYS.ORG · 2 weeks
Learning another language can take years of commitment and effort amid our busy lives. A new online learning innovation pairing students face-to-face with native speakers is helping to speed up progress because it is tailored to... more
New research expands the answers we can get from bat guano  PHYS.ORG · 1 month
Here's the thing about bats: They can fly. And they do that in the dark. more
Sustaining roads with grape and agricultural waste  PHYS.ORG · 2 weeks
The U.S. spends $5 billion a year to repair damages to road infrastructure from winter snow and ice control operations and the use of traditional deicers. A team of researchers at WSU is developing... more
Using the power of microwaves to recycle plastics  PHYS.ORG · 3 weeks
Despite continued efforts to reduce plastic waste, only a fraction of it is recycled. For example, less than 30 percent of plastic waste is recycled in the EU. Some of it is... more
Researchers use deep learning method to delve into predicting RNA structures in world first  PHYS.ORG · 3 weeks
In a world-first, a team of Griffith University researchers has used an artificial intelligence method to better predict RNA secondary... more
Traditional ways of learning anatomy remain superior than virtual and mixed reality models  NEWS MEDICAL · 4 weeks
A study from McMaster University has shown that traditional ways of learning anatomy remain superior to those that rely on digital media. more
Deep-sea bacteria copy their neighbors' diet  SCIENCE DAILY · 4 weeks
A new group of symbiotic bacteria in deep-sea mussels surprises with the way they fix carbon: They use the Calvin cycle to turn carbon into tasty food. The bacteria acquired the genes for this process from... more
MORE SCIENCE VIDEO
Antarctic video reveals deepest canyon on Earth
Science Magazine
Sébastien's YGT: System Engineer in the Clean Space Office
ESA
World's oldest artwork uncovered in Indonesian cave: study
PHYS.ORG
The return to Venus and what it means for Earth
PHYS.ORG
Automobile parts from agricultural waste
PHYS.ORG
X-ray satellite XMM-Newton celebrates 20 years in space
PHYS.ORG
Cheops: The Hunt for Exoplanets
ESA
Spying on hippos with drones to help conservation efforts
PHYS.ORG
CMU becomes go-to place for machine learning in catalysis research
PHYS.ORG
Watching a drug in action: Precise action anti-cancer drugs in the cell clarified
PHYS.ORG
FRESH SCIENCE