Osaka team uses AI to fix alloy calculation errors
Researchers at Osaka Metropolitan University developed an artificial intelligence method to correct volume size factor calculations for metal alloys.
New database built on calculations
A research team led by Professor Tokuteru Uesugi constructed a large-scale database using first-principles calculations. This dataset covers 1,998 binary solid-solution systems to address data gaps in alloy properties. The project aims to reduce the time and cost required for measuring these factors experimentally.
AI method corrects prediction errors
The group developed an AI-driven transfer-learning method that adjusts discrepancies between calculated and experimental values. This approach improved accuracy for alloys with existing data while testing performance on unexplored systems. The work has been published in the journal Materialia.
Results apply to new materials
The technique demonstrated reliable predictive performance for previously unexplored alloy systems without needing experimental input first. Scientists expect this achievement will help identify promising candidate materials before physical testing begins. The method allows researchers to tailor strength and stability by adding different elements to metals.
Reported by one outlet
Only one outlet has published this. Nothing here has been checked against a second report, so read it as that outlet's account and follow the link below for the original.
Reported by
1 independent outlet. Headline as published. Links open the original report.