AladynPi – Adaptive Neural Network Molecular Dynamics Simulation Code with Physically Informed Potential: Computational Materials Mini-Application(LAR-19727-1)
materials and processes
AladynPi – Adaptive Neural Network Molecular Dynamics Simulation Code with Physically Informed Potential: Computational Materials Mini-Application
AladynPi is a basic molecular dynamics codes written in FORTRAN 2008, which is designed to demonstrate the use of artificial neural networks (ANNs) in atomistic simulations. The role of ANNs is to efficiently reproduce the very complex energy landscape resulting from the atomic interactions in materials with the accuracy of the more expensive quantum mechanics-based calculations. An input for the ANN is a set of structure coefficients, characterizing the local atomic environment of each atom, for which the atomic energy is obtained in the ANN inference process. The ANN gives optimized parameters for a predefined empirical function, known as bond-order-potential (BOP). Thus parameterized BOP function is then used to calculate the energy of an atom. AladynPi code is being released to serve as a training testbed for students and professors in academia to explore possible optimization algorithms for parallel computing on multiprocessor computers or computers equipped with graphic processing units (GPUs).
Materials and Processes
Contact Us About This Technology
Langley Research Center