Data for "On the choice of training data for machine learning of geostrophic mesoscale turbulence". Contains qgm2 code (from James Maddison, University of Edinburgh) for generating the data codes to process data from qgm2 for machine learning, and train convolutional neural networks to use the data sample data processed data to reproduce plots in the paper Files collected in different zip files to avoid the need to download the whole pack in one go. See readme for data/folder structure.

Financial support from HK RGC General Research Fund 16304021 as well as the Center for Ocean Research in Hong Kong and Macau.