Dataset for Cloud Identification in Mars Daily Global Maps with Deep Learning

Overview:

This repository stores cloud masks and MDGMS for Martian Years (MYs) 28-33. MDGMs were obtained from Harvard Dataverse (https://doi.org/10.7910/DVN/U3766S), and cloud masks were created using the cloudmask model (https://github.com/03kalven/cloudmask). The cloud masks contained in the binary folders have already been binarized using the threshold of 0.912. This dataset is considerably smaller in size than the floating-point cloud mask dataset and is suited for researchers that prefer to use the default threshold of 0.912.

Quick breakdown of the files and folders:

phase folders contain the complete set of MDGMs and cloud masks for Mars Reconnaisance Orbiter mission phases P, B, G, D, F, and J (MYs 28-33)

phase_binary folders contain the complete set of binary MDGMs and cloud masks for Mars Reconnaisance Orbiter mission phases P, B, G, D, F, and J (MYs 28-33)

view_masks.ipynb has a few handy methods to plot cloud masks and MDGMs

Phase folders:

Each folder is organized based on phase (P, B, G, D, F, J) and subphase (_01 to _23). In each subphase, there are cloudmasks and mdgms folders, as well as a .txt file with MY and solar longitude (Ls) data for each day.

MDGM and cloud mask formats:

mdgm: JPEG, 3600x1801

cloudmask: (NETCDF4_CLASSIC data model, file format HDF5):

dimensions(sizes): x(3600), y(1801)

variables(dimensions): float32 longitude(x), float32 latitude(y), float32/int16 cloudmask(y, x)

The cloud masks' values for any pixel are -999 for NaN and a float from 0 to 1 reporting the model's confidence in that pixel being a cloud. The cloud masks can be binarized using get_cloudmask() included in view_masks.ipynb. A binarized mask would report -999 for NaN, 0 for no cloud, and 1 for cloud. The default threshold is 0.912, but this value can be adjusted if desired. The cloud masks' (0,0) coordinate is the lower left corner of the map, so it may be needed to flip the cloudmask vertically before plotting on a Martian map. The cloud mask NetCDF files are constructed the same way as Wang and González Abad's (https://doi.org/10.7910/DVN/WU6VZ8).