Generation of 30 meter resolution global burned area product based on Landsat 8 images

Burned area (BA) is an important parameter in the field of global change and carbon cycle. Firstly, high quality global sample database was constructed, then Landsat 8 time series satellite data and several sensitive spectral parameters of burned area were inputted to the machine learning algorithm, and 30 meter resolution global burned area product was produced and released. This product is innovative in the world. The 30 meter resolution global BA product can effectively detect small burned patches, and has advantages in determining fire location and area of the burned patches. It can be applied to global fire monitoring and disaster assessment, carbon emission calculation, ecological environment protection and other fields.