The present study explored machine learning methods to predict the catalytic activities of a dataset of 165 α-diimino nickel complexes in ethylene polymerization. Using 25 descriptors as the inputs, the XGBoost model presented the optimal performance among six different algorithms (R2 = 0.999, Rt2 = 0.921, Q2 = 0.561). The results of the analysis indicate that high activity is related to the presence of polarizable atoms and less bulky substituents within the N-aryl group. This approach offers valuable insights on the variation principle of catalytic activity as a function of complex structure, helping to effectively design and optimize α-diimino Ni catalysts with desirable performance.
Ethylene oligomerization catalysts have been extensively studied in both experimental and simulation contexts, yet a molecular-level understanding of structure-property relationship remains far from full understanding. Herein, an applicable strategy for the design of ligand of ethylene oligomerization catalysts was proposed. The density functional theory (DFT) and 3D graph networks (3D GNNs) have been combined to establish the relationship between catalyst structure and its property. A series of titanium-based metallocene catalysts with different ligand were designed and calculated using DFT to establish a dataset. The catalyst prediction model was constructed using 3D GNNs, and a weighted removal approach was used to compare output results and study the impact of different ligand structures on the oligomerization selectivity represented by the energy barrier difference between β-hydrogen transfer and the fourth ethylene insertion. The R2 values of the energy barrier difference predictions by four 3D GNNs were 0.93~0.96, indicating good predictive accuracy of the graph network models. Using the graph networks explanation algo-rithms, we investigated the influence of different substructures within the ligands on trimerization selectivity Based on the training and explanation results of the model, an external validation set is designed, and the R2 is 0.92, suggesting the generalization ability of the model. This enabled a molecular-level study of the relationship between the structure of titanocene catalyst and its property, providing guidance for the design of new catalyst structures.
In anticipation of the correlations between catalyst structures and their properties, the catalytic activities of 2-imino-1,10-phenanthrolyl iron and cobalt metal complexes are quantitatively investigated via linear machine learning (ML) algorithms. Comparatively, the Ridge Regression (RR) model has captured more robust predictive performance compared with other linear algorithms, with a correlation coefficient value of R2= 0.952 and a cross-validation value of Q2= 0.871. It shows that different algorithms select distinct types of descriptors, depending on the importance of descriptors. Through the interpretation of the RR model, the catalytic activity is potentially related to the steric effect of substituents and negative charged groups. This study refines descriptor selection for accurate modeling, providing insights into the variation principle of catalytic activity.
In this study, density functional theory (DFT) was employed to investigate the copolymerization mechanism of ethylene with tert-butyl acrylate (tBA) catalyzed by neutral nickel enolate complexes featuring distinct substituents. It is computationally found that [2,6-(PhO)2C6H3]2PCHC(Ph)O-Ni (A) is more active than [2,6-(MeO)2C6H3]2PCHC(Ph)O-Ni (B), which is in line with experimental observation. Based on this agreement, it is demonstrated that the ethylene insertion into the tBA chain-end is the rate-determining step and the activity discrepancy between A and B is closely associated with the electronic effects of the substituents rather than the difference in sterics between the PhO group in A and the MeO in B. The natural population analysis (NPA) indicates that the phenoxy substituent can more effectively increase the positive charge on the Ni center, thereby enhancing its copolymerization activity. The influence of the labile ligand (L) (L = pyridine, PEt3 and PPh3) on the copolymerization activity of the more active A has been further investigated. The coordination strength of the labile ligand was found to significantly influence the catalytic performance. Specifically, a weaker coordinating labile ligand facilitates the ligand exchange between L and monomer (tBA and ethylene) and enhances the efficiency of chain propagation. These mechanistic insights are helpful for the molecular design of copolymerization catalysts with high performance.