Author: Patricia DeLacey
-
OptoGPT for improving solar cells, smart windows, telescopes and more
Taking advantage of the transformer neural networks that power large language models, engineers can get recipes for materials with the optical properties they need.
-
Pinpointing coal plants to convert to nuclear energy, considering both practicality and community support
The most comprehensive coal-to-nuclear analysis to date could help policymakers and utilities plan how to meet climate targets.
-
US public opinion on social media is warming to nuclear energy, but concerns remain
300,000 X posts show 48 of 50 states have a more positive than negative tone about nuclear energy, with a national average at 54% positive.
-
Renewable grid: Recovering electricity from heat storage hits 44% efficiency
Thermophotovoltaics developed at U-M can recover significantly more energy stored in heat batteries.
-
Biases in large image-text AI model favor wealthier, Western perspectives
AI model that pairs text, images performs poorly on lower-income or non-Western images, potentially increasing inequality in digital technology representation.