Lifelong Machine Learning Potentials for Chemical Reaction Network Explorations

Abstract

Recent developments in computational chemistry facilitate the automated quantum chemical exploration of chemical reaction networks for the in-silico prediction of synthesis pathways, yield, and selectivity. However, the underlying quantum chemical energy calculations require vast computational resources, limiting these explorations severely in practice. Machine learning potentials (MLPs) offer a solution to increase computational efficiency, while retaining the accuracy of reliable first-principles data used for their training. Unfortunately, MLPs will be limited in their generalization ability within chemical (reaction) space, if the underlying training data are not representative for a given application. Within the framework of automated reaction network exploration, where new reactants or reagents composed of any elements from the periodic table can be introduced, this lack of generalizability will be the rule rather than the exception. Here, we therefore evaluate the benefits of the lifelong MLP concept in this context. Lifelong MLPs push their adaptability by efficient continual learning of additional data. We propose an improved learning algorithm for lifelong adaptive data selection yielding efficient integration of new data while previous expertise is preserved. In this way, we can reach chemical accuracy in reaction search trials.

19 pages, 9 figures, 2 tables

References in corpus (30)

• Array Programming with NumPy
• A Universal Graph Deep Learning Interatomic Potential for the Periodic Table
• Machine learning for molecular simulation
• Less is more: sampling chemical space with active learning
• Machine Learning Unifies the Modelling of Materials and Molecules
• On-the-fly machine learning force field generation: Application to melting points
• Phase transitions of hybrid perovskites simulated by machine-learning force fields trained on-the-fly with Bayesian inference
• A Fourth-Generation High-Dimensional Neural Network Potential with Accurate Electrostatics Including Non-local Charge Transfer
• WACSF - Weighted Atom-Centered Symmetry Functions as Descriptors in Machine Learning Potentials
• Exploration of Reaction Pathways and Chemical Transformation Networks
• The Exploration of Chemical Reaction Networks
• Perspective on integrating machine learning into computational chemistry and materials science
• Heuristics-Guided Exploration of Reaction Mechanisms
• Fast and Accurate Uncertainty Estimation in Chemical Machine Learning
• Context-Driven Exploration of Complex Chemical Reaction Networks
• Neural Network Potentials for Chemistry: Concepts, Applications and Prospects
• Unified Graph Neural Network Force-field for the Periodic Table
• Performance Assessment of Universal Machine Learning Interatomic Potentials: Challenges and Directions for Materials' Surfaces
• Uncertainty estimation for molecular dynamics and sampling
• Error-Controlled Exploration of Chemical Reaction Networks with Gaussian Processes
• Autonomous Reaction Network Exploration in Homogeneous and Heterogeneous Catalysis
• Molassembler: Molecular graph construction, modification and conformer generation for inorganic and organic molecules
• Minimum Energy Paths and Transition States by Curve Optimization
• Lifelong Machine Learning Potentials
• Expansive Quantum Mechanical Exploration of Chemical Reaction Paths
• Enhanced sampling of transition states
• High-throughput ab initio reaction mechanism exploration in the cloud with automated multi-reference validation
• SCINE -- Software for Chemical Interaction Networks
• CoRe Optimizer: An All-in-One Solution for Machine Learning
• Uncertainty-aware First-principles Exploration of Chemical Reaction Networks