NEWS FEEDS
Select a tab to change feeds.
- Science Daily
- Interesting Engineering
Scientists found that neural networks cannot yet forecast 'gray swan' weather events, which might not appear in existing training data but could still happen -- like 200-year floods or massive hurricanes.
SeaSplat is an image-analysis tool that cuts through the ocean's optical effects to generate images of underwater environments reveal an ocean scene's true colors. Researchers paired the color-correcting tool with a computational model that converts images of a scene into a three-dimensional underwater 'world' that can be explored virtually.
Humans no longer have exclusive control over training social robots to interact effectively, thanks to a new study. The study introduces a new simulation method that lets researchers test their social robots without needing human participants, making research faster and scalable.
A new AI decision making tool effectively balances various complex trade-offs to recommend ways of maximizing carbon storage, minimizing economic disruptions and helping improve the environment and people's everyday lives. It uses evolutionary AI, a kind of digital version of biological natural selection, to optimize policies in the face of competing priorities.
Engineers have developed a groundbreaking computational model to study the movement of granular materials such as soils, sands and powders. By integrating the dynamic interactions among particles, air and water phases, this state-of-the-art system can accurately predict landslides, improve irrigation and oil extraction systems, and enhance food and drug production processes.
Found in knee replacements and bone plates, aircraft components, and catalytic converters, the exceptionally strong metals known as multiple principal element alloys (MPEA) are about to get even stronger through to artificial intelligence. Scientists have designed a new MPEA with superior mechanical properties using a data-driven framework that leverages the supercomputing power of explainable artificial intelligence (AI).
Traditional methods of assessing damage after a disaster can take weeks or even months, delaying emergency response, insurance claims and long-term rebuilding efforts. New research might change that. Researchers have developed a new method that combines remote sensing, deep learning and restoration models to speed up building damage assessments and predict recovery times after a tornado. Once post-event images are available, the model can produce damage assessments and recovery forecasts in less than an hour.
Listen to the first notes of an old, beloved song. Can you name that tune? If you can, congratulations -- it's a triumph of your associative memory, in which one piece of information (the first few notes) triggers the memory of the entire pattern (the song), without you actually having to hear the rest of the song again. We use this handy neural mechanism to learn, remember, solve problems and generally navigate our reality.
Data science has revolutionized the hunt for high-performing catalysts, enabling scientists to quickly identify and test suitable materials.
An artificial intelligence (AI) model improved outcomes in hospitalized patients by quadrupling the rate of detection and treatment of delirium. The model identifies patients at high risk for delirium and alerts a specially-trained team to assess the patient and create a treatment plan, if needed.