Automated Detection of Cloud and Cloud Shadow in Single-Date Landsat Imagery Using Neural Networks and Spatial Post-Processing

Abstract

The use of Landsat data to answer ecological questions is greatly increased by the effective removal of cloud and cloud shadow from satellite images. We develop a novel algorithm to identify and classify clouds and cloud shadow, SPARCS: Spatial Procedures for Automated Removal of Cloud and Shadow. The method uses a neural network approach to determine cloud, cloud shadow, water, snow/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. In a comparison with FMask, a high-quality cloud and cloud shadow classification algorithm currently available, SPARCS performs favorably, with substantially lower omission errors for cloud shadow (8.0% and 3.2%), only slightly higher omission errors for clouds (0.9% and 1.3%, respectively) and fewer errors of commission (2.6% and 0.3%). Additionally, SPARCS provides a measure of uncertainty in its classification that can be exploited by other algorithms that require clear sky pixels. To illustrate this, we present an application that constructs obstruction-free composites of images acquired on different dates in support of a method for vegetation change detection.

Patch-Based Forest Change Detection from Landsat Time Series

“…Pixels contaminated with clouds and their shadows, as well as with any lingering or early snow or ice, were identified using the neural network and spatial post-processing approach in Spatial Procedures for Automated Removal of Clouds and Shadow (SPARCS) [33]. SPARCS provides continuous-valued memberships of cloud, cloud-shadow, water, snow/ice, and clear-sky classes.…”

“…Multiple images from the same year were combined by taking a weighted average to construct an obstruction-free summertime composite for each year in a method similar to that described in [33]. The weights used in the average are a function of both q, from the cloud-detection, and of the distance from a target day in order to reduce noise introduced via phenology, w. For this study, the 200th day of the year (July 18 or 19, depending on leap years) was selected for the target day and the weight was calculated as:…”

A Comparison of Haze Removal Algorithms and Their Impacts on Classification Accuracy for Landsat Imagery

“…Therefore, the landscape analysis and ecological modeling of regional area representing the internships between natural conditions and human impacts across time and space are particularly important, which are based on the data of land cover categories frequently. The use of land cover data to answer ecological questions could be greatly increased by the effective removal of haze from satellite images (Hughes and Hayes, 2014).…”

Cloud-Sourcing: Using an Online Labor Force to Detect Clouds and Cloud Shadows in Landsat Images

“…In recent years, strides have been made towards the development of automated, computer-based methods to accomplish this task (e.g., [1][2][3]). While these automated algorithms have been shown to process Landsat scenes with high levels of speed and accuracy, there remains room for human CCS interpretation in various stages of the analysis.…”