Virtual Experiments combined with Machine Learning to improve Data Evaluation of SANS measurements

In this work we present our research line that has begun as part of the “Global Neutron Scientist” (GneuS) call N.º 1 this year. We present our strategy to combine virtual experiments with Machine Learning (ML) techniques to improve the data evaluation procedure in Small Angle Neutron Scattering (SANS) experiments. In particular, we describe the virtual experiments we are planning to do at a SANS instrument at MLZ with the VITESS software [1] to create a training database for ML algorithms, and we discuss aproposed first step exploratory analysis to the generated data using Multivariate Statistical methodologies. This analysis will give insight to the adequate ML algorithms that we will explore. [1] C. Zendler, K. Lieutenant, D. Nekrassov, M. Fromme, Vitess 3 – Virtual Instrumentation Tool for the European Spallation, J. Phys. Conf. Ser. 528 (2014) 012036