New Technology– category –
-
Transition Metal Carbides: Composition-Based Melting Point Prediction
BIOENGINEER Overview Machine learning analysis reveals that elemental composition alone is sufficient to predict the melting temperatures of transition metal carbides. Adding complex descriptors like formation energies and bond geometry ... -
AI Materials Models: New Benchmark for Physics-Aware Accuracy
BIOENGINEER USA Overview Researchers from Columbia Engineering and the University of Cambridge have developed a benchmark to determine if machine learning models for materials science derive macroscopic properties from correct underlying... -
MXene Discovery: AI-Driven Identification of 33 2D Materials
xenospectrum Overview An international research team led by Linköping University identified 33 previously overlooked MXene candidates by applying machine learning to decades-old crystal data. The team successfully synthesized 18 multilay... -
Google Research VERID: AI Agents for Autonomous Wet Labs
Google Research Blog USA Overview Google Research is integrating AI agents with physical lab robotics via the VERID framework to automate molecular design cycles. By grounding agents in a semantic digital twin of the laboratory, the syst... -
GM EV Platform: Virtual Battery Testing and LMR Tech Specs
Interesting Engineering USA Overview General Motors has utilized computer simulations to test over 300,000 battery designs, reducing the timeline from initial concept to formal program approval to one month. This approach is central to a... -
Inverse Materials Design: Joint Generation of Crystal Structures and Electronic Descriptors
npj Computational Materials Overview A new diffusion framework improves the inverse design of inorganic crystals by jointly denoising structural variables and local electronic descriptors. The model achieves higher success rates in prope... -
LixSi Lithiation Tracking: ML-Enhanced XPS Binding Energies
npj Computational Materials Overview Researchers have developed a computational framework combining machine learning (ML) and atomistic simulations to quantitatively track the lithiation state of silicon-based anodes. By predicting core-... -
Electronic Structure Data: Redundancy and Dimensionality in ML
npj Computational Materials USA Overview Researchers have discovered significant redundancies in electronic structure datasets, revealing that high-accuracy machine learning models can be trained using up to two orders of magnitude less ... -
Metallic Conductivity Screening: ML-Driven Study of 2.8 Million Compounds
npj Computational Materials Overview Researchers have developed a computational framework combining machine learning with ab initio calculations to screen over 2.8 million compounds for high electrical conductivity. The study identified ... -
Multicomponent Transition Metal Carbides: Synthesizability and Hardness via MACE ML Potentials
npj Computational Materials Switzerland Overview Researchers have developed a machine-learned interatomic potential framework to predict the thermodynamic stability and hardness of multicomponent transition metal carbides. By screening o...
