 Sparks is a new algorithm developed to accurately detect and classify clouds and cloud shadows in Landsat imagery. This algorithm uses a combination of spatial procedures and a neural network to reduce the number of false positives and negatives, resulting in more accurate cloud and cloud shadow identification than existing methods. Additionally, it provides a measure of uncertainty in its classification which can be used by other algorithms requiring clear sky pixels. This article was authored by M. Joseph Hughes and Daniel J. Hayes.