Structure of a physics-informed neural network (PINN) for solving the Schrödinger equation (top). Description of a quantum mechanical tunnelling effect at the example of the OH torsional mode in the phenol molecule (bottom).
Machine learning (ML) is a modern and powerful tool that is revolutionising quantum chemistry and materials science. By developing algorithms based on large amounts of data, material properties can be predicted efficiently and at high speed. For example, machine learning models can be used to calculate the energy of molecules, which contributes significantly to the understanding of chemical reactions. The integration of machine learning with traditional computational methods such as quantum mechanics enables a synergistic approach that combines the strengths of both techniques. As ML-based algorithms are constantly being improved, breakthroughs in the design and development of new functional materials can be expected already in the near future.