Fast Predictions of Reaction Barrier Heights: Toward Coupled- Cluster Accuracy

Quantitative estimates of reaction barriers are essential for developing kinetic mechanisms and predicting reaction outcomes. However, the lack of experimental data and the steep scaling of accurate quantum calculations often hinder the ability to obtain reliable kinetic values. Here, we train a directed message passing neural network on nearly 24,000 diverse gas-phase reactions calculated at CCSD(T)-F12a/ cc-pVDZ-F12//??B97X-D3/def2-TZVP. Our model uses 75% fewer parameters than previous studies, an improved reaction representation, and proper data splits to accurately estimate performance on unseen reactions. Using information from only the reactant and product, our model quickly predicts barrier heights with a testing MAE of 2.6 kcal mol???1 relative to the coupled-cluster data, making it more accurate than a good density functional theory calculation. Furthermore, our results show that future modeling efforts to estimate reaction properties would significantly benefit from fine-tuning calibration using a transfer learning technique. We anticipate this model will accelerate and improve kinetic predictions for small molecule chemistry.

Automated summary

Quantitative estimates of reaction barriers are crucial for development and prediction of reaction outcomes. However, lack of experimental data and limitations of accurate quantum calculations often impede the obtainment of reliable kinetic values. In this study, a directed message passing neural network is trained on diverse gas-phase reactions to accurately predict barrier heights based on reactant and product information. The model outperforms good density functional theory calculations and suggests the use of transfer learning for future modeling efforts. This model is expected to enhance and expedite kinetic predictions for small molecule chemistry.