Electronic Configurations of 3d Transition-Metal Compounds Using Local Structure and Neural Networks

Machine Learning Prediction of the Experimental Transition Temperature of Fe(II) Spin-Crossover Complexes

Spin-crossover (SCO) complexes are materials that exhibit changes in the spin state in response to external stimuli, with potential applications in molecular electronics. It is challenging to know a priori how to design ligands to achieve the delicate balance of entropic and enthalpic contributions needed to tailor a transition temperature close to room temperature. We leverage the SCO complexes from the previously curated SCO-95 data set [Vennelakanti et al. J. Chem. Phys. 159, 024120 (2023)] to train three machine learning (ML) models for transition temperature (T1/2) prediction using graph-based revised autocorrelations as features. We perform feature selection using random forest-ranked recursive feature addition (RF-RFA) to identify the features essential to model transferability. Of the ML models considered, the full feature set RF and recursive feature addition RF models perform best, achieving moderate correlation to experimental T1/2 values. We then compare ML T1/2 predictions to those from three previously identified best-performing density functional approximations (DFAs) which accurately predict SCO behavior across SCO-95, finding that the ML models predict T1/2 more accurately than the best-performing DFAs. In addition, we study ML model predictions for a set of 18 SCO complexes for which only estimated T1/2 values are available. Upon excluding outliers from this set, the RF-RFA RF model shows a strong correlation to estimated T1/2 values with a Pearson's r of 0.82. In contrast, DFA-predicted T1/2 values have large errors and show no correlation to estimated T1/2 values over the same set of complexes. Overall, our study demonstrates slightly superior performance of ML models in comparison with some of the best-performing DFAs, and we expect ML models to improve further as larger data sets of SCO complexes are curated and become available for model training.

Analysis of the oxygen evolution activity of layered double hydroxides (LDHs) using machine learning guidance

Layered double hydroxides (LDHs) are excellent catalysts for the oxygen evolution reaction (OER) because of their tunable properties, including chemical composition and structural morphology. An interplay between these adjustable properties and other (including external) factors might not always benefit the OER catalytic activity of LDHs. Therefore, we applied machine learning algorithms to simulate the double-layer capacitance to understand how to design/tune LDHs with targeted catalytic properties. The key factors of solving this task were identified using the Shapley Additive explanation and cerium was identified as an effective element to modify the double-layer capacitance. We also compared different modelling methods to identify the most promising one and the results revealed that binary representation is better than directly applying atom numbers as inputs for chemical compositions. Overpotentials of LDH-based materials as predicted targets were also carefully examined and evaluated, and it turns out that overpotentials can be predicted when measurement conditions about overpotentials are added as features. Finally, to confirm our findings, we reviewed additional experimental literature data and used them to test our machine algorithms to predict LDH properties. This analysis confirmed the very credible and robust generalization ability of our final model capable of achieving accurate results even with a relatively small dataset.