Recently, machine learning (ML) methods have gained popularity and have performed as powerfully predictive tools in various areas of academic and industrious activities. In comparison, their application in catalysis has been underdeveloped. Relying on the rapid development of different algorithms and their implementation, it is the right timing to harvest the potential of ML in catalysis across academy and industry spectra. Herein, we discuss the current applications in the field of homogeneous and heterogeneous catalysis by using various ML approaches. To the best of our knowledge, modern statistical learning techniques will be a strong tool for computational optimization and discovery. This in turn will accurately extract the underlying mechanism in the model that converts readily available data and precatalysts into their promising and useful ones.

Understanding the chirality induction and amplification processes, and the construction of globally homochiral surfaces, represent essential challenges in surface chirality studies. Here we report the induction of global homochirality in two-dimensional enantiomorphous networks of achiral molecules via co-assembly with chiral co-absorbers. The scanning tunnelling microscopy investigations and molecular mechanics simulations demonstrate that the point chirality of the co-absorbers transfers to organizational chirality of the assembly units via enantioselective supramolecular interactions, and is then hierarchically amplified to the global homochirality of two-dimensional networks. The global homochirality of the network assembly shows nonlinear dependence on the enantiomeric excess of chiral co-absorber in the solution phase, demonstrating, for the first time, the validation of the 'majority rules' for the homochirality control of achiral molecules at the liquid/solid interface. Such an induction and nonlinear chirality amplification effect promises a new approach towards two-dimensional homochirality control and may reveal important insights into asymmetric heterogeneous catalysis, chiral separation and chiral crystallization.

A series of nickel(II) dihalide complexes (C1–C10) bearing unsymmetrical α-diimine ligands of the type 2,4-dibenzhydryl-N-(2-phenyliminoacenaphthylenylidene)-6-methylbenzenamine (L1–L5) were synthesized and fully characterized. Single-crystal X-ray diffraction revealed a distorted tetrahedral geometry around the nickel center in the complexes C3, C5 and C9. Upon activation with modified methylaluminoxane (MMAO), all nickel pro-catalysts performed with high activities in ethylene polymerization, producing highly branched polyethylene products.

A series of cobalt(II) dichloride complexes ligated by 2-[1-(2,4-dibenzhydryl-6-methylphenylimino) ethyl]-6-[1-(arylimino)ethyl]pyridines was synthesized and characterized by FT-IR spectroscopy and elemental analysis. The molecular structure of the representative complex Co4 (R1 = Me, R2 = Me) was confirmed as pseudo square-pyramidal geometry at cobalt by single-crystal X-ray diffraction. Upon treatment with the co-catalysts MAO or MMAO, all cobalt pre-catalysts exhibited high activities up to 1.81 × 10⁷ g PE mol⁻¹(Co) h⁻¹ in ethylene polymerization, and produced polyethylene products with molecular weights in the tens of thousands and narrow molecular weight distributions. The influence of the reaction parameters and nature of the ligands on the catalytic behavior of the title cobalt complexes was investigated.