'Discovery learning' AI tool predicts battery cycle life with just a few days' data
Peer-Reviewed Publication
Updates every hour. Last Updated: 3-Apr-2026 18:16 ET (3-Apr-2026 22:16 GMT/UTC)
An agentic AI tool for battery researchers harnesses data from previous battery designs to predict the cycle life of new battery concepts. With information from just 50 cycles, the tool—developed at University of Michigan Engineering—can predict how many charge-discharge cycles the battery can undergo before its capacity drops below 90 percent of its design capacity.
Scientists developed a terahertz microscope that compresses terahertz light down to microscopic dimensions. This pinpoint of terahertz light can resolve quantum details in materials that were previously inaccessible.
The research focused on the Hankou Tunnel, a deep-lying section of the challenging Xinjin Expressway spiral tunnel group. To find the best way to support the tunnel walls, the research team turned to advanced computer simulation technology (using the ABAQUS platform). Researchers created detailed digital models to simulate the entire construction process from start to finish. Published in Smart Construction, the findings offer crucial reference for designing more effective support systems for other deep mountain tunnels built in similar rock formations.