Random forest and neural network algorithms are applied to identify cloud cover using 10 of the wavelength bands available in Landsat 8 imagery. The methods classify each pixel into 4 different classes: clear, cloud shadow, light cloud, or cloud. The first method is based on a fully connected neural network with ten input neurons, two hidden layers of 8 and 10 neurons respectively, and a single-neuron output for each class. This type of model is considered with and without L2 regularization applied to the kernel weighting. The final model type is a random forest classifier created from an ensemble of decision trees acting on a randomized subset of 6 wavelengths. The best performing classifier is the random forest, with an overall accuracy of 77% across the 4 classes. Cloud mask statistics could be incorporated in searchable metadata so that an imagery analyst can apply their subject matter expertise to advanced analytical techniques, rather than searching for cloud-free image sets.
89th Military Operations Research Society Symposium, Virtual
Carrasco, Salome E. [*]; Wagner, Torrey J.; and Langhals, Brent T., "Per-pixel Cloud Cover Classification of Multispectral Landsat-8 Data" (2021). Faculty Publications. 1410.