Researchers at the University of Virginia, in collaboration with Oak Ridge National Laboratory and other institutions, have developed an AI-enhanced technique to study the effects of radiation on materials at the nanoscale. Using transmission electron microscopy (TEM) and convolutional neural networks (CNNs), the team analyzed over 1,000 time-series images capturing more than 250,000 defects caused by ion irradiation. The study focused on understanding how different metals, such as copper, gold, and palladium, respond to radiation, revealing distinct behaviors in defect formation. The AI model reduces human error, speeds up analysis, and improves accuracy, offering new insights into materials’ reactions in extreme environments. This research holds potential for applications in renewable energy, space exploration, and electronics, aiming to improve the durability of materials in harsh conditions.
Please continue reading the full article under the link below:
Please consult also the Quantum Server Marketplace platform for the outsourcing of computational science R&D projects to external expert consultants through remote collaborations:
#materials #materialsscience #materialsengineering #computationalchemistry #modelling #chemistry #researchanddevelopment #research #MaterialsSquare #ComputationalChemistry #Tutorial #DFT #simulationsoftware #simulation