Category: Research
-
How food banks facing cuts could harness data, maximize efficiency
While federal food assistance cuts are too large to make up for in efficiencies, pooling resources among hunger relief agencies could help the remaining aid go further.
-
AI leaderboards can be trustworthy by following these tips
Methods for ranking chess players and athletes don’t always translate to AI. U-M researchers identify and outline best practices.
-
Solving a moon mystery helps game out future landings
U-M, Johns Hopkins partnership explains a consistent pattern in the dust under moon landings.
-
At-home melanoma testing: Skin patch test works in mice
A microneedle patch captures cancer biomarkers in the top-most layer of skin to detect melanoma in animal tissue samples.
-
Improving AI models: Automated tool detects silent errors in deep learning training
TrainCheck uses training invariants to find the root cause of hard-to-detect errors before they cause downstream problems, saving time and resources.
-
New air mobility corridor to advance eVTOLs and beyond-line-of-sight UAVs
The newly designated airspace links U-M’s autonomy testbed with Detroit’s innovation district.
-
Digital twins for manufacturing: industry collaborators wanted
Focusing on precompetitive problems, such as enabling communication between digital twins, U-M and ASU are seeking industry partners for an NSF research center.
-
Satellites reveal tropical wetland flooding did not cause methane surge
Human activity or other wetland factors like temperature or soil chemistry could be at play.
-
Conference: Scientific discovery in the age of AI
Experts from academia, industry and government discussed the growing utility of generative AI in science and what’s coming next.
-
New blue fluorophore breaks efficiency records in both solids and solutions
Reaching 98% efficiency in a solid state and 94% in solution, the small fluorescent molecule’s design could cut down development time and cost for future applications.
-
Reinforcement learning for nuclear microreactor control
A machine learning approach outcompetes the industry standard for adjusting power generation to meet demand, especially in imperfect conditions.
-
US high schoolers monitor solar storms with an accessible antenna kit
An easy-to-install antenna allows high school students to collect data for NASA, helping improve knowledge of space weather.