A Comprehensive Survey of Deep Learning in Remote Sensing: Theories, Tools and Challenges for the Community

TL;DR

This comprehensive survey reviews the latest deep learning advancements relevant to remote sensing, highlighting theories, tools, challenges, and opportunities for future research in the field.

Contribution

It provides an extensive overview of state-of-the-art deep learning methods applied to remote sensing, focusing on theories, tools, and unresolved challenges specific to the community.

Findings

Identifies key challenges like data scarcity and heterogeneity.

Highlights recent developments in DL architectures for spectral, spatial, and temporal data.

Discusses opportunities for transfer learning and theoretical understanding of DL systems.

Abstract

In recent years, deep learning (DL), a re-branding of neural networks (NNs), has risen to the top in numerous areas, namely computer vision (CV), speech recognition, natural language processing, etc. Whereas remote sensing (RS) possesses a number of unique challenges, primarily related to sensors and applications, inevitably RS draws from many of the same theories as CV; e.g., statistics, fusion, and machine learning, to name a few. This means that the RS community should be aware of, if not at the leading edge of, of advancements like DL. Herein, we provide the most comprehensive survey of state-of-the-art RS DL research. We also review recent new developments in the DL field that can be used in DL for RS. Namely, we focus on theories, tools and challenges for the RS community. Specifically, we focus on unsolved challenges and opportunities as it relates to (i) inadequate data sets, (ii) human-understandable solutions for modelling physical phenomena, (iii) Big Data, (iv) non-traditional heterogeneous data sources, (v) DL architectures and learning algorithms for spectral, spatial and temporal data, (vi) transfer learning, (vii) an improved theoretical understanding of DL systems, (viii) high barriers to entry, and (ix) training and optimizing the DL.