Authors: Samuel Fordin (University of Delaware),Michael Shay (University of Delaware),Lynn B. Wilson III (NASA GSFC),Bennett Maruca (University of Delaware),Barbara Thompson (NASA GSFC)

26 years of observations by the Wind spacecraft at 1 AU has yielded a rich array of high-resolution magnetic field data, where a large fraction displays small-scale structures. In particular, the solar wind is full of circularly-polarized fluctuations such as magnetosonic-whistler waves and kinetic Alfven waves that appear in both the field magnitude and its components. The nature of these fluctuations can be tied to the properties of other structures in the solar wind, such as shocks, that have implications for the time evolution of the solar wind. As such, having a large collection of wave events would facilitate further study of the effects that each type of fluctuation has on solar wind dynamics. Given the breadth of magnetic field data available, machine learning is the most practical approach to classifying the myriad small-scale structures observed in the magnetic field data. To this end, a subset of current Wind data is labeled and used as a training set for a 1D convolutional neural network aimed at differentiating between wave and nonwave events. As a first step, this algorithm is used to identify waves in one year of magnetic field data, with the eventual goal of classifying the entire Wind dataset.