Graph neural network interatomic potential ensembles with calibrated aleatoric and epistemic uncertainty on energy and forces.

Inexpensive machine learning (ML) potentials are increasingly being used to speed up structural optimization and molecular dynamics simulations of materials by iteratively predicting and applying interatomic forces. In these settings, it is crucial to detect when predictions are unreliable to avoid wrong or misleading results. Here, we present a complete framework for training and recalibrating graph neural network ensemble models to produce accurate predictions of energy and forces with calibrated uncertainty estimates. The proposed method considers both epistemic and aleatoric uncertainty and the total uncertainties are recalibrated post hoc using a nonlinear scaling function to achieve good calibration on previously unseen data, without loss of predictive accuracy. The method is demonstrated and evaluated on two challenging, publicly available datasets, ANI-1x (Smith et al. J. Chem. Phys., 2018, 148, 241733.) and Transition1x (Schreiner et al. Sci. Data, 2022, 9, 779.), both containing diverse conformations far from equilibrium. A detailed analysis of the predictive performance and uncertainty calibration is provided. In all experiments, the proposed method achieved low prediction error and good uncertainty calibration, with predicted uncertainty correlating with expected error, on energy and forces. To the best of our knowledge, the method presented in this paper is the first to consider a complete framework for obtaining calibrated epistemic and aleatoric uncertainty predictions on both energy and forces in ML potentials.

Cheap Turns Superior: A Linear Regression-Based Correction Method to Reaction Energy from the DFT.

Workflows to predict chemical reaction networks based on density functional theory (DFT) are prone to systematic errors in reaction energy due to the extensive use of cheap DFT exchange-correlation functionals to limit computational cost. Recently, machine learning-based models are increasingly applied to mitigate this problem. However, machine learning models require systems similar to trained data, and the models often perform poorly for out-of-distribution systems. Here, we present a simple bond-based correction method that improves the accuracy of DFT-derived reaction energies. It is based on linear regression, and the correction terms for each bond are derived from reactions among the QM9 data set. We demonstrate the effectiveness of this method with three DFT functionals in three different rungs of Jacob's ladder. The simple correction method is effective for all rungs but especially so for the cheapest PBE functional. Finally, we applied the correction method to a few reactions with molecules significantly different from those in the QM9 data set that was used to fit the linear regression model. Once corrected by this method, we found that the DFT reaction energies for such out-of-distribution reactions are within 0.05 eV of the G4MP2 method.

Artificial Intelligence Applied to Battery Research: Hype or Reality?

This is a critical review of artificial intelligence/machine learning (AI/ML) methods applied to battery research. It aims at providing a comprehensive, authoritative, and critical, yet easily understandable, review of general interest to the battery community. It addresses the concepts, approaches, tools, outcomes, and challenges of using AI/ML as an accelerator for the design and optimization of the next generation of batteries─a current hot topic. It intends to create both accessibility of these tools to the chemistry and electrochemical energy sciences communities and completeness in terms of the different battery R&D aspects covered.

Deep Learning Spectroscopy: Neural Networks for Molecular Excitation Spectra.

Deep learning methods for the prediction of molecular excitation spectra are presented. For the example of the electronic density of states of 132k organic molecules, three different neural network architectures: multilayer perceptron (MLP), convolutional neural network (CNN), and deep tensor neural network (DTNN) are trained and assessed. The inputs for the neural networks are the coordinates and charges of the constituent atoms of each molecule. Already, the MLP is able to learn spectra, but the root mean square error (RMSE) is still as high as 0.3 eV. The learning quality improves significantly for the CNN (RMSE = 0.23 eV) and reaches its best performance for the DTNN (RMSE = 0.19 eV). Both CNN and DTNN capture even small nuances in the spectral shape. In a showcase application of this method, the structures of 10k previously unseen organic molecules are scanned and instant spectra predictions are obtained to identify molecules for potential applications.

Machine learning-based screening of complex molecules for polymer solar cells.

Polymer solar cells admit numerous potential advantages including low energy payback time and scalable high-speed manufacturing, but the power conversion efficiency is currently lower than for their inorganic counterparts. In a Phenyl-C_61-Butyric-Acid-Methyl-Ester (PCBM)-based blended polymer solar cell, the optical gap of the polymer and the energetic alignment of the lowest unoccupied molecular orbital (LUMO) of the polymer and the PCBM are crucial for the device efficiency. Searching for new and better materials for polymer solar cells is a computationally costly affair using density functional theory (DFT) calculations. In this work, we propose a screening procedure using a simple string representation for a promising class of donor-acceptor polymers in conjunction with a grammar variational autoencoder. The model is trained on a dataset of 3989 monomers obtained from DFT calculations and is able to predict LUMO and the lowest optical transition energy for unseen molecules with mean absolute errors of 43 and 74 meV, respectively, without knowledge of the atomic positions. We demonstrate the merit of the model for generating new molecules with the desired LUMO and optical gap energies which increases the chance of finding suitable polymers by more than a factor of five in comparison to the randomised search used in gathering the training set.