Updates to the DScribe Library: New Descriptors and Derivatives

Abstract

We present an update of the DScribe package, a Python library for atomistic descriptors. The update extends DScribe's descriptor selection with the Valle-Oganov materials fingerprint and provides descriptor derivatives to enable more advanced machine learning tasks, such as force prediction and structure optimization. For all descriptors, numeric derivatives are now available in DSribe. For the many-body tensor representation (MBTR) and the Smooth Overlap of Atomic Positions (SOAP), we have also implemented analytic derivatives. We demonstrate the effectiveness of the descriptor derivatives for machine learning models of Cu clusters and perovskite alloys.

arXiv commentThe following article has been submitted to The Journal of Chemical Physics. After it is published, it will be found at https://aip.scitation.org/toc/jcp/current

References in corpus (14)

• Adam: A Method for Stochastic Optimization
• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• Array Programming with NumPy
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• SchNet - a deep learning architecture for molecules and materials
• DScribe: Library of Descriptors for Machine Learning in Materials Science
• Comparing molecules and solids across structural and alchemical space
• Unified Representation of Molecules and Crystals for Machine Learning
• Efficient global structure optimization with a machine learned surrogate model
• Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
• Chemical diversity in molecular orbital energy predictions with kernel ridge regression
• Global optimization of atomistic structure enhanced by machine learning

Cited by in corpus (18)

• Decoding the Competing Effects of Dynamic Solvation Structures on Nuclear Magnetic Resonance Chemical Shifts of Battery Electrolytes via Machine Learning
• Automatic feature selection and weighting in molecular systems using Differentiable Information Imbalance
• Augmentation of Universal Potentials for Broad Applications
• Grain boundary interstitial segregation in substitutional binary alloys
• Efficient dataset generation for machine learning perovskite alloys
• Relevant, hidden, and frustrated information in high-dimensional analyses of complex dynamical systems with internal noise
• Interstitials as a key ingredient for P segregation to grain boundaries in polycrystalline $\alpha$-Fe
• Guest Editorial: Special Topic on Software for Atomistic Machine Learning
• A data driven approach to classify descriptors based on their efficiency in translating noisy trajectories into physically-relevant information
• Structural Descriptors and Information Extraction from X-ray Emission Spectra: Aqueous Sulfuric Acid
• DeFecT-FF: a machine learning force field framework for high throughput defect modeling in CdTe-based solar cells
• Spectral Operator Representations
• k-Means Clustering in Fingerprint-Based Configuration Selection for Fitting Interatomic Potentials
• From Local Atomic Environments to Molecular Information Entropy
• Unsupervised Machine-Learning Pipeline for Data-Driven Defect Detection and Characterisation: Application to Displacement Cascades
• Active Δ-learning with universal potentials for global structure optimization
• Predicting co-segregation in alloys with solute-solute interactions
• Macro-Dipole-Constrainted Learning of Atomic Charges for Accurate Electrostatic Potentials at Electrochemical Interfaces