Principal component analysis applied to muon spectroscopy experiment

Machine learning (ML) methods have proved to be a very successful tool in physical sciences, especially when applied to experimental data analysis. Artificial intelligence is particularly good at recognizing patterns in high dimensional data, where it usually outperforms humans. Here we applied a simple ML tool called principal component analysis (PCA) to study data from muon spectroscopy. The measured quantity from this experiment is an asymmetry function, which holds the information about averaged intrinsic magnetic field of the sample. Change in the asymmetry function might indicate phase transition; however, changes can be very subtle, and existing methods of analyzing the data require knowledge about the physics of the material. PCA is an unsupervised ML tool, which means that no assumption about the input data is required, yet we found that it still can be successfully applied to asymmetry curves, and the indications of phase transitions can be recovered. The method was applied to a range of magnetic materials with different underlying physics. Additionally, we discovered that performing PCA on all those materials simultaneously has no major effect on phase transition indicators, but can improve on detection of most important variations of asymmetry functions.