Abstract
One of the major challenges in optical-based remote sensing is the presence of clouds, which imposes a hard constraint on the use of multispectral or hyperspectral satellite imagery for earth observation. While some studies have used interpolation models to remove cloud affected data, relatively few aim at restoration via the use of multi-temporal reference images. This paper proposes not only the use of image time-series, but also the implementation of a geostatistical model that considers the spatiotemporal correlation between them to fill the cloud-related gaps. Using Hyperion hyperspectral images, we demonstrate a capacity to reconstruct cloud-affected pixels and predict their underlying surface reflectance values. To do this, cloudy pixels were masked and a parametric family of non-separable covariance functions was automated fitted, using a composite likelihood estimator. A subset of cloud-free pixels per scene was used to perform a kriging interpolation and to predict the spectral reflectance per each cloud-affected pixel. The approach was evaluated using a benchmark dataset of cloud-free pixels, with a synthetic cloud superimposed upon these data. An overall root mean square error (RMSE) of between 0.5% and 16% of the reflectance was achieved, representing a relative root mean square error (rRMSE) of between 0.2% and 7.5%. The spectral similarity between the predicted and reference reflectance signatures was described by a mean spectral angle (MSA) of between 1° and 11°, demonstrating the spatial and spectral coherence of predictions. The approach provides an efficient spatiotemporal interpolation framework for cloud removal, gap-filling, and denoising in remotely sensed datasets.
Highlights
The reflectance of a material is defined by its capacity to return a proportion of the radiant energy incident upon it and represents a key parameter that provides insights into the surface physical and chemical constituents
The main goal of this study is to model the spatiotemporal correlation of surface reflectance to produce realistic predictions under cloud affected pixels in hyperspectral images
A general class of covariance functions was implemented to model the spatiotemporal features contained in a time series of hyperspectral imagery
Summary
The reflectance of a material is defined by its capacity to return a proportion of the radiant energy incident upon it and represents a key parameter that provides insights into the surface physical and chemical constituents. Within the wide variety of sensors available for remote observation [2,3], hyperspectral instruments provide a capacity to monitor hundreds of adjacent wavelengths across much of the visible and infrared spectrum [4]. In combination, these individual spectral features provide a dense record of reflectance behavior across spatial, temporal, and spectral dimensions. Removing cloud contaminated pixels in multi-spectral and hyperspectral imagery represents a particular challenge, since the predicted results should be visually or spatially coherent, and spectrally satisfactory
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
