Deep Learning for the Earth Sciences - A Comprehensive Approach to Remote Sensing, Climate Science

DEEP LEARNING FOR THE EARTH SCIENCES
 
Explore this insightful treatment of deep learning in the field of earth sciences, from four leading voices
 
Deep learning is a fundamental technique in modern Artificial Intelligence and is being applied to disciplines across the scientific spectrum; earth science is no exception. Yet, the link between deep learning and Earth sciences has only recently entered academic curricula and thus has not yet proliferated. Deep Learning for the Earth Sciences delivers a unique perspective and treatment of the concepts, skills, and practices necessary to quickly become familiar with the application of deep learning techniques to the Earth sciences. The book prepares readers to be ready to use the technologies and principles described in their own research.
 
The distinguished editors have also included resources that explain and provide new ideas and recommendations for new research especially useful to those involved in advanced research education or those seeking PhD thesis orientations. Readers will also benefit from the inclusion of:
* An introduction to deep learning for classification purposes, including advances in image segmentation and encoding priors, anomaly detection and target detection, and domain adaptation
* An exploration of learning representations and unsupervised deep learning, including deep learning image fusion, image retrieval, and matching and co-registration
* Practical discussions of regression, fitting, parameter retrieval, forecasting and interpolation
* An examination of physics-aware deep learning models, including emulation of complex codes and model parametrizations
 
Perfect for PhD students and researchers in the fields of geosciences, image processing, remote sensing, electrical engineering and computer science, and machine learning, Deep Learning for the Earth Sciences will also earn a place in the libraries of machine learning and pattern recognition researchers, engineers, and scientists.

List of contents

Foreword xvii
 
Acknowledgments xix
 
List of Contributors xxi
 
List of Acronyms xxvii
 
1 Introduction 1
Gustau Camps-Valls, Xiao Xiang Zhu, Devis Tuia, and Markus Reichstein
 
1.1 A Taxonomy of Deep Learning Approaches 2
 
1.2 Deep Learning in Remote Sensing 3
 
1.3 Deep Learning in Geosciences and Climate 7
 
1.4 Book Structure and Roadmap 9
 
Part I Deep Learning to Extract Information from Remote Sensing Images 13
 
2 Learning Unsupervised Feature Representations of Remote Sensing Data with Sparse Convolutional Networks 15
Jose E. Adsuara, Manuel Campos-Taberner, Javier García-Haro, Carlo Gatta, Adriana Romero, and Gustau Camps-Valls
 
2.1 Introduction 15
 
2.2 Sparse Unsupervised Convolutional Networks 17
 
2.2.1 Sparsity as the Guiding Criterion 17
 
2.2.2 The EPLS Algorithm 18
 
2.2.3 Remarks 18
 
2.3 Applications 19
 
2.3.1 Hyperspectral Image Classification 19
 
2.3.2 Multisensor Image Fusion 21
 
2.4 Conclusions 22
 
3 Generative Adversarial Networks in the Geosciences 24
Gonzalo Mateo-García, Valero Laparra, Christian Requena-Mesa, and Luis Gómez-Chova
 
3.1 Introduction 24
 
3.2 Generative Adversarial Networks 25
 
3.2.1 Unsupervised GANs 25
 
3.2.2 Conditional GANs 26
 
3.2.3 Cycle-consistent GANs 27
 
3.3 GANs in Remote Sensing and Geosciences 28
 
3.3.1 GANs in Earth Observation 28
 
3.3.2 Conditional GANs in Earth Observation 30
 
3.3.3 CycleGANs in Earth Observation 30
 
3.4 Applications of GANs in Earth Observation 31
 
3.4.1 Domain Adaptation Across Satellites 31
 
3.4.2 Learning to Emulate Earth Systems from Observations 33
 
3.5 Conclusions and Perspectives 36
 
4 Deep Self-taught Learning in Remote Sensing 37
Ribana Roscher
 
4.1 Introduction 37
 
4.2 Sparse Representation 38
 
4.2.1 Dictionary Learning 39
 
4.2.2 Self-taught Learning 40
 
4.3 Deep Self-taught Learning 40
 
4.3.1 Application Example 43
 
4.3.2 Relation to Deep Neural Networks 44
 
4.4 Conclusion 45
 
5 Deep Learning-based Semantic Segmentation in Remote Sensing 46
Devis Tuia, Diego Marcos, Konrad Schindler, and Bertrand Le Saux
 
5.1 Introduction 46
 
5.2 Literature Review 47
 
5.3 Basics on Deep Semantic Segmentation: Computer Vision Models 49
 
5.3.1 Architectures for Image Data 49
 
5.3.2 Architectures for Point-clouds 52
 
5.4 Selected Examples 55
 
5.4.1 Encoding Invariances to Train Smaller Models: The example of Rotation 55
 
5.4.2 Processing 3D Point Clouds as a Bundle of Images: SnapNet 59
 
5.4.3 Lake Ice Detection from Earth and from Space 62
 
5.5 Concluding Remarks 66
 
6 Object Detection in Remote Sensing 67
Jian Ding, Jinwang Wang, Wen Yang, and Gui-Song Xia
 
6.1 Introduction 67
 
6.1.1 Problem Description 67
 
6.1.2 Problem Settings of Object Detection 69
 
6.1.3 Object Representation in Remote Sensing 69
 
6.1.4 Evaluation Metrics 69
 
6.1.4.1 Precision-recall Curve 70
 
6.1.4.2 Average Precision and Mean Average Precision 71
 
6.1.5 Applications 71
 
6.2 Preliminaries on Object Detection with Deep Models 72
 
6.2.1 Two-stage Algorithms 72
 
6.2.1.1 R-CNNs 72
 
6.2.1.2 R-FCN 73
 
6.2.2 One-stage Algorithms 73
 
6.2.2.1 YOLO 73
 
6.2.2.2 SSD 73
 
6.3 Object Detection in Optical RS Images 75
 
6.3.1 RelatedWorks 75
 
6.3.1.1 S

About the author

Gustau Camps-Valls is Professor of Electrical Engineering and Lead Researcher in the Image Processing Laboratory (IPL) at the Universitat de València. His interests include development of statistical learning, mainly kernel machines and neural networks, for Earth sciences, from remote sensing to geoscience data analysis. Models efficiency and accuracy but also interpretability, consistency and causal discovery are driving his agenda on AI for Earth and climate.
Devis Tuia, PhD, is Associate Professor at the Ecole Polytechnique Fédérale de Lausanne (EPFL). He leads the Environmental Computational Science and Earth Observation laboratory, which focuses on the processing of Earth observation data with computational methods to advance Environmental science. Xiao Xiang Zhu is Professor of Data Science in Earth Observation and Director of the Munich AI Future Lab AI4EO at the Technical University of Munich and heads the Department EO Data Science at the German Aerospace Center. Her lab develops innovative machine learning methods and big data analytics solutions to extract large scale geo-information from big Earth observation data, aiming at tackling societal grand challenges, e.g. Urbanization, UN's SDGs and Climate Change. Markus Reichstein is Director of the Biogeochemical Integration Department at the Max-Planck- Institute for Biogeochemistry and Professor for Global Geoecology at the University of Jena. His main research interests include the response and feedback of ecosystems (vegetation and soils) to climatic variability with an Earth system perspective, considering coupled carbon, water and nutrient cycles. He has been tackling these topics with applied statistical learning for more than 15 years.

Summary

DEEP LEARNING FOR THE EARTH SCIENCES

Explore this insightful treatment of deep learning in the field of earth sciences, from four leading voices

Deep learning is a fundamental technique in modern Artificial Intelligence and is being applied to disciplines across the scientific spectrum; earth science is no exception. Yet, the link between deep learning and Earth sciences has only recently entered academic curricula and thus has not yet proliferated. Deep Learning for the Earth Sciences delivers a unique perspective and treatment of the concepts, skills, and practices necessary to quickly become familiar with the application of deep learning techniques to the Earth sciences. The book prepares readers to be ready to use the technologies and principles described in their own research.

The distinguished editors have also included resources that explain and provide new ideas and recommendations for new research especially useful to those involved in advanced research education or those seeking PhD thesis orientations. Readers will also benefit from the inclusion of:
* An introduction to deep learning for classification purposes, including advances in image segmentation and encoding priors, anomaly detection and target detection, and domain adaptation
* An exploration of learning representations and unsupervised deep learning, including deep learning image fusion, image retrieval, and matching and co-registration
* Practical discussions of regression, fitting, parameter retrieval, forecasting and interpolation
* An examination of physics-aware deep learning models, including emulation of complex codes and model parametrizations

Perfect for PhD students and researchers in the fields of geosciences, image processing, remote sensing, electrical engineering and computer science, and machine learning, Deep Learning for the Earth Sciences will also earn a place in the libraries of machine learning and pattern recognition researchers, engineers, and scientists.

Product details

• Authors: G Camps-Valls, Gusta Camps-Valls, Gustau Camps-Valls, Gustau (University of Valencia Camps-Valls, Gustau Tuia Camps-Valls, Markus Reichstein, Devi Tuia, Devis Tuia, Xiao Xiang Zhu, Xiao Xiang et Zhu
• Assisted by: Gustau Camps-Valls (Editor), Markus Reichstein (Editor), Devi Tuia (Editor), Devis Tuia (Editor), Tuia Devis (Editor), Xiao Xiang Zhu et al (Editor), Xiao Xiang Zhu (Editor)
• Publisher: Wiley, John and Sons Ltd
• Languages: English
• Product format: Hardback
• Released: 31.10.2021
• EAN: 9781119646143
• ISBN: 978-1-119-64614-3
• No. of pages: 432
• Subjects: Natural sciences, medicine, IT, technology > Technology > Electronics, electrical engineering, communications engineering; Geowissenschaften, Geographie, Geography, Deep Learning, Fernerkundung, Earth Sciences, Remote sensing, GIS u. Fernerkundung, GIS & Remote Sensing, GIS, Fernerkundung u. Kartographie, GIS, Remote Sensing & Cartography, Electrical & Electronics Engineering, Elektrotechnik u. Elektronik