Static image taken from video (shown below). Right: using AI-based method to remove the noise. A team of scientists has developed a method to illuminate the dynamic behavior of nanoparticles. The work, reported in Visualizing Nanoparticle Surface Dynamics and Instabilities Enabled by Deep Denoising, in the journal Science, combines artificial intelligence with electron microscopy to render visuals of how these tiny bits of matter respond to stimuli. "The nature of changes in the particle is exceptionally diverse, including fluxional periods, manifesting as rapid changes in atomic structure, particle shape, and orientation; understanding these dynamics requires new statistical tools," said David S. Matteson (Cornell University), one of the paper's authors.

Soon enough, AI competency will be an essential workforce skill. A group of computer scientists and learning science experts are considering what a foundational introduction to AI might look like for middle school and high school students. The rise of artificial intelligence (AI) and a branch of AI called machine learning, which focuses on the use of data and algorithms to imitate the way that humans learn, is rapidly changing the way data-intensive scientific discovery is being done. Data-intensive science is a modern, exploration-centered style of science that heavily relies on advanced computing capabilities and software tools to manipulate and explore massive data sets. The introduction of new and better machine learning techniques is now being used to assist and automate scientific discovery of increasingly complex problems.

In this paper, we present Pangu-Weather, a deep learning based system for fast and accurate global weather forecast. For this purpose, we establish a data-driven environment by downloading $43$ years of hourly global weather data from the 5th generation of ECMWF reanalysis (ERA5) data and train a few deep neural networks with about $256$ million parameters in total. The spatial resolution of forecast is $0.25^\circ\times0.25^\circ$, comparable to the ECMWF Integrated Forecast Systems (IFS). More importantly, for the first time, an AI-based method outperforms state-of-the-art numerical weather prediction (NWP) methods in terms of accuracy (latitude-weighted RMSE and ACC) of all factors (e.g., geopotential, specific humidity, wind speed, temperature, etc.) and in all time ranges (from one hour to one week). There are two key strategies to improve the prediction accuracy: (i) designing a 3D Earth Specific Transformer (3DEST) architecture that formulates the height (pressure level) information into cubic data, and (ii) applying a hierarchical temporal aggregation algorithm to alleviate cumulative forecast errors. In deterministic forecast, Pangu-Weather shows great advantages for short to medium-range forecast (i.e., forecast time ranges from one hour to one week). Pangu-Weather supports a wide range of downstream forecast scenarios, including extreme weather forecast (e.g., tropical cyclone tracking) and large-member ensemble forecast in real-time. Pangu-Weather not only ends the debate on whether AI-based methods can surpass conventional NWP methods, but also reveals novel directions for improving deep learning weather forecast systems.

Atrial fibrillation -- an irregular and often rapid heart rate -- is a common condition that often leads to the formation of clots in the heart that can travel to the brain to cause a stroke. The study was published in Circulation. The investigators developed the artificial intelligence-based method to predict the risk of atrial fibrillation within the next five years based on results from electrocardiograms (noninvasive tests that record the electrical signals of the heart) in 45,770 patients receiving primary care at MGH. Next, the scientists applied their method to three large data sets from studies including a total of 83,162 individuals. The AI-based method predicted atrial fibrillation risk on its own and was synergistic when combined with known clinical risk factors for predicting atrial fibrillation. The method was also highly predictive in subsets of individuals such as those with prior heart failure or stroke.

Researchers have used artificial intelligence to screen 80 FDA-approved drugs and reveal which could be used as Alzheimer's treatments. A team at Massachusetts General Hospital (MGH) and Harvard Medical School (HMS), both US, has developed an artificial intelligence (AI)-based method to screen currently available medications as possible treatments for Alzheimer's disease. According to the researchers, the method could represent a rapid and inexpensive way to repurpose existing therapies into new treatments for the neurodegenerative condition. It could also help reveal new, unexplored targets for therapy by pointing to mechanisms of drug action. "Repurposing US Food and Drug Administration (FDA)-approved drugs for Alzheimer's disease is an attractive idea that can help accelerate the arrival of effective treatment – but unfortunately, even for previously approved drugs, clinical trials require substantial resources, making it impossible to evaluate every drug in patients with Alzheimer's disease," explained Dr Artem Sokolov, at HMS. "We therefore built a framework for prioritising drugs, helping clinical studies to focus on the most promising ones."

One day in the future when you need medical care, someone will examine you, diagnose the problem, remove some of your body's healthy cells, and then use them to grow a cure for your ailment. The therapy will be personalized and especially attuned to you and your body, your genes, and the microbes that live in your gut. This is the dream of modern medical science in the field of "regenerative medicine." There are many obstacles standing between this dream and its implementation in real life, however. Cells often differ so much from one another and differ in so many ways that scientists have a hard time predicting what the cells will do in any given therapeutic scenario.

Researchers at the University of Zurich's Brain Research Institute have recently developed a technique to automatically detect neurons of different types in a variety of brain regions at different developmental stages. They presented this deep learning-based tool, called DeNeRD, in a paper published in Nature Scientific Reports. Mapping the structure of the mammalian brain at the cellular level is an important, yet demanding task, which typically involves capturing specific anatomical features and analyzing them. In the past, researchers were able to gather several interesting observations and insights about the mammalian brain's structure using classical histological and stereological techniques. Although these methods have proved to be very useful for studying the anatomy of the brain, carrying out a truly brain-wide analysis typically requires a different approach.

The innovation uses computational neural networks, a form of artificial intelligence, to "learn" how a nanoparticle's structure affects its behavior, in this case the way it scatters different colors of light, based on thousands of training examples. Then, having learned the relationship, the program can essentially be run backward to design a particle with a desired set of light-scattering properties -- a process called inverse design. The findings are being reported in the journal Science Advances, in a paper by MIT senior John Peurifoy, research affiliate Yichen Shen, graduate student Li Jing, professor of physics Marin Soljacic, and five others. While the approach could ultimately lead to practical applications, Soljacic says, the work is primarily of scientific interest as a way of predicting the physical properties of a variety of nanoengineered materials without requiring the computationally intensive simulation processes that are typically used to tackle such problems. Soljacic says that the goal was to look at neural networks, a field that has seen a lot of progress and generated excitement in recent years, to see "whether we can use some of those techniques in order to help us in our physics research. So basically, are computers'intelligent' enough so that they can do some more intelligent tasks in helping us understand and work with some physical systems?"