ACEworks and Materials Design to continue their successful collaboration in the field of Machine-Learned Potentials

ACEworks and Materials Design are rolling forward their successful collaboration with the full integration of the GRACEmaker code of ACEworks in the MedeA computational environment. The GRACEmaker code is based on the Graph Atomic Cluster Expansion (GRACE), one of the most advanced methods for the generation of Machine-Learned Potentials (MLPs). MedeA 3.12 provides comprehensive support of the leading GRACE 1L and 2L potentials in MedeA LAMMPS. This includes access to the most recent Foundational GRACE potentials GRACE-1L-OMAT, GRACE-2L-OMAT, GRACE-1L-OAM, and GRACE-2L-OAM, which cover 89 chemical elements. These potentials are among the top scorers of the latest benchmarks and established a new 'Pareto front', offering the best available balance between high accuracy and computational speed. Furthermore, integration of GRACEmaker into the centerpiece of Materials Design’s MLP product line, the Machine-Learned Potential Generator (MLPG), allows seamless generation of custom GRACE potentials from user-generated training sets of DFT data.

#ACEworks #MaterialsDesign #ComputationalMaterials #MachineLearnedPotentials #MLP #GRACE #GRACEmaker #MedeA #LAMMPS #MaterialsInformatics #ComputationalChemistry #DFT #AtomisticSimulation #MaterialsScience #AIforScience #ScientificComputing #HighPerformanceComputing #DigitalMaterials