Monitor this situation.

Unsubscribe anytime.

[SITUATION] · [ACTIVE] · [TECHNOLOGY]

2 clusters · 5 sources · 5 days · First seen 8 days ago · Last updated 4 days ago

AI advancements in materials engineering discovery

Overview

Researchers are advancing the use of artificial intelligence to accelerate materials engineering and discovery. Initial developments focused on high-fidelity explainable AI (XAI) frameworks that utilize SHapley Additive exPlanations to provide physical interpretability for non-linear regression, specifically regarding material performance and fracture energy.

Subsequent advancements include new modeling methods at Lawrence Berkeley National Laboratory capable of predicting kinetic factors and atomic movement in solid-state materials, simulating reaction paths in minutes. Additionally, research from Argonne National Laboratory has introduced a multi-agent AI framework to automate atomistic simulations, aiming to reduce material discovery timelines from years to days across sectors such as energy storage, aerospace, and electronics.

Entities

Argonne National Laboratory · Jasmine Wing Lam Tsang · Lawrence Berkeley National Laboratory · Kristin Persson · University of Illinois Chicago

Timeline

4 days ago

[TECHNOLOGY] 3 sources
AI modeling advances accelerate discovery of advanced materials
US researchers have developed AI models and multi-agent frameworks to automate atomistic simulations, potentially reducing the discovery time for advanced materials from years to days.
8 days ago

[TECHNOLOGY] 2 sources
Explainable AI Framework Enhances Materials Engineering Predictions
An explainable AI framework using SHAP and Random Forest improves material performance predictions, revealing fracture energy sensitivity at –40 °C while reducing lab testing.

Sources

engrxiv.org · finance.technews.tw · ibimapublishing.com · interestingengineering.com · news.m.pchome.com.tw