UNCERTAINTY QUANTIFICATION FOR NEURAL NETWORK POTENTIAL FOUNDATION MODELS

Abstract For neural network potentials (NNPs) to gain widespread use, researchers must be able to trust model outputs.However, the blackbox nature of neural networks and their inherent stochasticity are often deterrents, especially for foundation models trained over broad swaths of chemical space.Uncertainty information provided at the time of pred

Concrete in construction has recently gained media coverage for its negative CO2 footprint, but this is not the only Flywheel Pulley problem associated with its use.Due to its chemical composition, freshly poured concrete changes the pH of water coming in contact with the surface to very alkaline values, requiring neutralization treatment before di