Artificial intelligence can be used to improve the research method of Quantum Mechanics.

Searching for different uses of artificial intelligence has always been a successful journey and among its numerous uses, quantum mechanics stands in a vital position. Artificial Intelligence can be used to predict molecular wave functions and the electronic properties of molecules. The behavior of the electron in the molecule can be observed and the data can be fed to AI algorithm, which would further predict the future behaviors of the electrons in the molecules. The researchers of University of Warwick, the Technical University of Berlin and the University of Luxembourg have together come up with such innovative ways of using AI. Using quantum mechanics, the behavior of an electron in a molecule is still described by a wave function, analogous to the behavior in an atom. Just like electrons around isolated atoms, electrons around atoms in molecules are limited to discrete (quantized) energies. The region of space in which a valence electron in a molecule is likely to be found is called a molecular orbital. Like an atomic orbital, a molecular orbital is full when it contains two electrons with opposite spin.

Making a difference

In general, artificial intelligence can be used in observing and predicting any consistent common behavior. For example, AI is used in predicting the shopping behavior of people and it is done by observing the way the person shops on a regular basis. In a similar way, AI can be used for predicting the quantum states of molecules, so-called wave functions, which determine all properties of molecules. AI is capable of doing this by learning to solve fundamental equations of quantum mechanics. Doing it in the conventional way requires massive high-performance computing resources, which is typically the bottleneck to the computational design of new purpose-built molecules for medical and industrial applications. However, this newly developed AI algorithm will be able to supply accurate predictions within seconds on a laptop or mobile phone.

Details of Research

Dr. Reinhard Maurer from the Department of Chemistry at the University of Warwick stated while talking about this research, "This has been a joint three year effort, which required computer science know-how to develop an artificial intelligence algorithm flexible enough to capture the shape and behavior of wave functions, but also chemistry and physics know-how to process and represent quantum chemical data in a form that is manageable for the algorithm." The research shows that AI methods can efficiently perform the most difficult aspects of quantum molecular simulations. Within the next few years, AI methods will establish themselves as an essential part of the discovery process in computational chemistry and molecular physics. The team has been brought together during an interdisciplinary 3-month fellowship program at IPAM (UCLA) on the subject of machine learning in quantum physics.