news 2022

Machine learning improves climate models Accurately modeling extreme precipitation events remains a major challenge for climate models. These models predict how the earth's climate may change over the course of decades and even centuries. To improve them especially with regard to extreme events, researchers now use machine learning methods otherwise applied to image generation.

A new technique enables AI models to continually learn from new data on intelligent edge devices like smartphones and sensors, reducing energy costs and privacy risks. Microcontrollers, miniature computers that can run simple commands, are the basis for billions of connected devices, from internet-of-things (IoT) devices to sensors in automobiles.

Scientific discovery during the Stockpile Stewardship Program maintains confidence in the nuclear deterrent without testing, brings other benefits The last nuclear test, code-named Divider, took place 30 years ago, on September 23, 1992. That year, President Bush declared a temporary moratorium on nuclear testing, which became permanent during the Clinton administration.

With access to some of the best digital tools and learning systems ever seen, it's a wonder that there is currently no easy way for teachers to conduct experiments to see what is working best in their classrooms. Carnegie Mellon University and its partners were recently awarded a nearly $3 million National Science Foundation grant to fund a new framework for adaptive experimentation in classrooms and digital learning spaces like CMU's (OLI) and the Carnegie Learning K-12 platform.

The official opening of the supercomputer DelftBlue will take place on 30 September at the Prinsenhof in Delft, also marking the fifth anniversary of the TU Delft Institute for Computational Science & Engineering. The programme features scientists and companies working with supercomputers, explaining the importance of supercomputing for healthcare, logistics and the energy transition.

Explainable AI (XAI) is an exciting new field in computer science. PhD-candidate Ana Lucic developed some new algorithms to make the black box of machine learning more transparant. One of them could help healthcare in underserved communities. Lucic will defend her PhD-thesis on Friday 23 September at the UvA.

By continuously monitoring a patient's gait speed, the system can assess the condition's severity between visits to the doctor's office. Parkinson's disease is the fastest-growing neurological disease, now affecting more than 10 million people worldwide, yet clinicians still face huge challenges in tracking its severity and progression.

Scientists develop platform that combines measurements of surface topography in a digital twin Scientists from the University of Freiburg, Germany, and the University of Pittsburgh have developed a software platform that facilitates and standardizes the analysis of surfaces. The platform enables users to create a digital twin of a surface and thus to help predict, for example, how quickly it wears out, how well it conducts heat, or how well it adheres to other materials.

PhD candidate uses tools from quantum mechanics to help computers interpret ambiguous language. Words or sentences can often have multiple meanings. This is a concept that is hard to grasp for regular computers. PhD candidate Adriana Duarte Correia used quantum algorithms to make computers understand that a sentence like 'Look at the dog with one eye' can mean two different things at the same time.

First, pause and take a deep breath. When we breathe in, our lungs fill with oxygen, which is distributed to our red blood cells for transportation throughout our bodies. Our bodies need a lot of oxygen to function, and healthy people have at least 95% oxygen saturation all the time. Conditions like asthma or COVID-19 make it harder for bodies to absorb oxygen from the lungs.

Researchers in Graz develop technology for precise assessment of the danger of virus variants One of the greatest difficulties in combating viral infectious diseases is the excellent adaptability of the viruses. In the case of SARS-CoV-2, we have seen how quickly new variants are constantly being formed that bring with them different properties.

Freiburg computer scientists make an important step towards advancing perception in complex urban environments How can mobile robots perceive and understand the environment correctly, even if parts of the environment are occluded by other objects? This is a key question that must be solved for self-driving vehicles to safely navigate in large crowded cities.

The expectations for autonomous driving are clear: "Cars have to travel safely not only at low speeds, but also in fast-moving traffic," says Jörg Schrepfer, the Head of Driving Advanced Research Germany at Valeo. For example, when objects fall off a truck, the "egocentric" perspective of a car will often be unable to detect the hazardous debris in time.

A new system capable of reading lips with remarkable accuracy even when speakers are wearing face masks could help create a new generation of hearing aids. An international team of engineers and computing scientists developed the technology, which pairs radio-frequency sensing with artificial intelligence for the first time to identify lip movements.

By comparing ants and robots, researchers found that the math for slithering can be applied to most multi-legged creatures too The physics of walking for multi-legged animals and robots is simpler than previously thought. That is the finding described by a team of roboticists, physicists and biologists in the Sept.

With energy prices soaring, heating costs will also inevitably rise in the coming winter. In order to mitigate this, solutions for operating buildings more efficiently are needed. The Empa spin-off viboo has developed an algorithm that makes it possible to operate even older buildings with around 25 percent less energy - while user comfort remains the same or even improves.

Canadians think they know a lot about snow. It is practically a national pastime to discuss winter weather. But a PhD candidate in the Department of Geography and Environmental Management at the University of Waterloo is taking the Canadian obsession with weather to a whole new level. Fraser King is studying the ways machine learning can be applied to predicting patterns of precipitation, and especially annual snowfall and snowmelt in the context of climate change.

Researchers led by Göttingen University develop new machine-learning method to understand force chains Granular matter is all around us. Examples include sand, rice, nuts, coffee and even snow. These materials are made of solid particles that are large enough not to experience thermal fluctuations. Instead, their state is determined by mechanical influences: shaking produces -granular gases- whilst by compression one gets -granular solids-.

A 2D material sample that is held within an ultrahigh vacuum, low-temperature scanning probe microscope. (Credit: Marilyn Sargent/Berkeley Lab) - Stephen Ornes Two-dimensional materials, which consist of a single layer of atoms, exhibit unusual properties that could be harnessed for a wide range of quantum and microelectronics systems.

It could be so simple: producing global maps for vegetation, climate or soil at the touch of a button. Whether in Africa, America or Europe; whether up in the mountains or deep in the forest. No laborious on-site fieldwork would be necessary, nor would days spent evaluating data in a lab. Simply "train" the computer system to provide, as accurately as possible, predictions for any and every environmental variable.