Electro Textures Dataset

This texture dataset is intended for training, testing and validation of a convolutional neural network used in the task of building cloud and snow cover masks using data received from a multi-zone scanning device used for hydrometeorological support (MSU-GS) and installed on the Russian satellite Electro-L No.2.All data is stored in an «HDF5» format file. The data is divided into three groups: «train», «test» and «val», respectively, for training, testing and validating the neural network. Each group contains a set of classes, these are «Surface», «Snow» and «Cloud». Each class consists of a set of texture blocks and has the dimension NxTxTxM. Where N is the number of samples of texture blocks for a given class and group, TxT is the spatial resolution of one texture from a block in pixels (in our case 11x11), M is the number of textures in a block (in our case 5: these are 3 textures with reflectance data of channels 0.6, 0.7 and 0.9 μm; 2 textures with temperature brightness data of channel 3.8 and 10.7 μm of the MSU-GS instrument).