 Sparks is a new algorithm developed to accurately identify and classify clouds and cloud shadows in Landsat imagery. This algorithm uses a neural network approach to determine cloud, cloud shadow, water, snow slash ice and clear sky classification memberships of each pixel in a Landsat scene. It then applies a series of spatial procedures to resolve pixels with ambiguous membership by using information, such as the membership values of neighboring pixels and an estimate of cloud shadow locations from cloud and solar geometry. Compared to another existing algorithm, Fmask, Sparks has significantly lower error rates for both cloud and cloud shadow, 8% and 3.2% versus 14.5% and 7.1% and fewer errors of commission, 2.6% and 0.3% versus 4.3% and 2.9%. Additionally, it provides a measure of uncertainty in its classification that can be used by other algorithms requiring clear sky pixels. This article was authored by M. Joseph Hughes and Daniel J. Hayes. We are article.tv, links in the description below.