TimeSpec4LULC: A deep learning-oriented global dataset of MODIS Terra-Aqua multi-spectral time series measured from 2002 to 2021 for LULC mapping and change detection.

TimeSpec4LULC is archived in 30 different ZIP files owning the name of the 29 LULC classes (one class is divided into two files since it is too large). Within each ZIP file, there exists a set of seven CSV files, each one corresponding to one of the seven spectral bands. The naming of each file follows this structure: IdOfTheClass_NameOfTheClass_ModisBand.csv<br> For example, for band 1 of the Barren Lands class, the filename is: 01_BarrenLands_MCD09A1b01.csv<br> Inside each CSV file, rows represent the collected pixels for that class. The first 11 columns contain the following metadata:<br> - “IdOfTheClass”: Id of the class.<br> - “NameOfTheClass”: Name of the class.<br> - “IdOfTheLevel0”: Id of the FAO-L0 (i.e., countries).<br> - “IdOfTheLevel1”: Id of the FAO-L1 (i.e., departments, states, or provinces depending on the country).<br> - “IdOfThePixel”: Id of the pixel.<br> - “PurityOfThePixel”: Spatial and inter-annual consensus for this class across multiple land-cover products, i.e., Purity of the pixel.<br> - “DataAvailability”: percentage of non-missing data per band throughout the time series.<br> - “Index_GHM”: average of Global Human Modification index (gHM).<br> - “Lat”: Latitude of the pixel center.<br> - “Lon”: Longitude of the pixel center.<br> - “.geo”: (Longitude, Latitude) of the pixel center with more precision.<br> And, the last 223 columns contain the 223 monthly observations of the time series for one spectral band from 2002-07 to 2021-01. Along with the dataset, an Excel file named 'Countries_Departments_FAO-GAUL' containing the FAO-L0 and the FAO-L1 Ids and names (following the FAO-GAUL standards) is provided.