Special Section: Distributed Computing for Remotely Sensed Big Data Processing
Volume 109, Issue 8
Guest Editors: Jón Atli Benediktsson and Zebin Wu
Special Section Papers
A comprehensive review of state-of-the-art methods for processing remotely sensed big data is given along with a thorough investigation of existing distributed and parallel approaches that are based on popular high-performance computing (HPC) platforms. Future directions for tackling challenging issues in distributed and parallel processing of remotely sensed big data are given.
Representative and recent advances in hyperspectral anomaly detection approaches are discussed along with their parallel and distributed implementations on graphic processing unit (GPU), cloud computing, and field-programmable gate array (FPGA) platforms.
A comprehensive review of the state-of-the-art in deep learning for remote sensing data interpretation is given. The pros and cons of the most widely used techniques in the literature are analyzed, as well as their parallel and distributed implementations. The article concludes with some remarks about future challenges in the application of deep learning techniques to distributed remote sensing data interpretation problems.
Distributed computing strategies in remote sensing techniques and applications that use various data sources are comprehensively reviewed. A new distributed fusion framework that can accelerate the fusion of heterogeneous remote sensing and social media data is proposed by decomposing large data sets into small ones and processing them in parallel.
This article summarizes progress in the development of such materials with a focus on developments that show promise for improved practical dielectrics.
This article reviews existing technology and provides a roadmap of spintronic devices for future energy-efficient computing and its relevant integration architectures.