Published: Active learning-assisted neutron spectroscopy with log-Gaussian processes
I am very pleased to announce that our paper on active learning-assisted experiments at three-axes spectrometers was published in Nature Communications. Our approach ARIANE, which was designed to assist researchers in the first hours of an experiment and thus to optimize the use of valuable beam time, was already mentioned here (v1) and here (v2, revised).
For a summary of our results prepared for a broader audience, we refer to our “Behind the Paper” blog post in the Nature Physics community.
Journal link: doi:10.1038/s41467-023-37418-8
arXiv link: arXiv:2209.00980
Abstract. Neutron scattering experiments at three-axes spectrometers (TAS) investigate magnetic and lattice excitations by measuring intensity distributions to understand the origins of materials properties. The high demand and limited availability of beam time for TAS experiments however raise the natural question whether we can improve their efficiency and make better use of the experimenter’s time. In fact, there are a number of scientific problems that require searching for signals, which may be time consuming and inefficient if done manually due to measurements in uninformative regions. Here, we describe a probabilistic active learning approach that not only runs autonomously, i.e., without human interference, but can also directly provide locations for informative measurements in a mathematically sound and methodologically robust way by exploiting log-Gaussian processes. Ultimately, the resulting benefits can be demonstrated on a real TAS experiment and a benchmark including numerous different excitations.