Materials Project
PulseAugur coverage of Materials Project — every cluster mentioning Materials Project across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New framework offers guaranteed SPD uncertainty for tensor-valued geometric learning
Researchers have developed a new framework for uncertainty quantification in tensor-valued geometric learning, specifically addressing the prediction of symmetric rank-2 tensors. This method ensures positive-definite co…
-
New GNN models advance crystal property prediction and molecular simulations
Researchers have developed new graph neural network (GNN) models for predicting crystal properties. One approach, CPGN, uses a multi-scale GNN to jointly learn atomic, bond, and coordination-polyhedron representations, …
-
New dataset PhononBench-MP40 aids computational materials screening
Researchers have introduced PhononBench-MP40, a new dataset designed to improve the accuracy of computational materials screening by addressing the issue of imaginary phonon modes. This dataset, derived from Materials P…
-
Machine learning for battery materials validation faces significant errors
A new research paper highlights critical issues with using computational references to validate machine-learned battery materials. The study found that the machine-learning screening stack, when pre-registered for valid…