Onboard Processing of Hyperspectral Imagery: Deep Learning Advancements, Methodologies, Challenges, and Emerging Trends

Abstract

Recent advancements in deep learning techniques have spurred considerable interest in their application to hyperspectral imagery processing. This article provides a comprehensive review of the latest developments in this field, focusing on methodologies, challenges, and emerging trends. Deep learning architectures, such as convolutional neural networks (CNNs), autoencoders, deep belief networks, generative adverserial networks (GANs), and recurrent neural networks are examined for their suitability in processing hyperspectral data. Key challenges, including limited training data and computational constraints, are identified, along with strategies, such as data augmentation and noise reduction using GANs. This article discusses the efficacy of different network architectures, highlighting the advantages of lightweight CNN models and 1D-CNNs for onboard processing. Moreover, the potential of hardware accelerators, particularly field programmable gate arrays, for enhancing processing efficiency is explored. This review concludes with insights into ongoing research trends, including the integration of deep learning techniques into Earth observation missions, such as the Copernicus hyperspectral imaging mission for the environment mission, and emphasizes the need for further exploration and refinement of deep learning methodologies to address the evolving demands of hyperspectral image processing.