Multitemporal Earth Observation Image Analysis : Remote Sensing Image Sequences (Hardcover)

Foreword xi
Francesca BOVOLO

Chapter 1. Broader Application of the Time-SIFT Method: Proof-of-Concept of 3-D-Monitoring Study Cases with Various Spatiotemporal Scales 1
Denis FEURER, Sean BEMIS, Guillaume COULOUMA, Hatem MABROUK, Sylvain MASSUEL, Romina Vanessa BARBOSA, Yoann THOMAS, Jerome AMMANN and Fabrice VINATIER

1.1. Introduction 1

1.2. The Time-SIFT method 4

1.3. Case studies 8

1.4. Conclusion 34

1.5. References 35

Chapter 2. Hierarchical Crop Mapping from Satellite Image Sequences with Recurrent Neural Networks 41
Mehmet OZGUR TURKOGLU, Stefano D’ARONCO, Konrad SCHINDLER and Jan Dirk WEGNER

2.1. Introduction 41

2.2. Literature 44

2.3. Background: sequence modeling with recurrent neural networks 49

2.4. Hierarchical multi-stage convolutional recurrent network 54

2.5. Experiment 57

2.6. Summary and future outlook 69

2.7. References 72

Chapter 3. Exploiting Multitemporal Multispectral High-resolution Satellite Data toward Annual Land Cover and Crop Type Mapping: A Case Study in Greece 81
Christina KARAKIZI, Konstantinos KARANTZALOS and Zacharias KANDYLAKIS

3.1. Introduction 81

3.2. From raw data to analysis ready datasets 83

3.3. Classification and mapping 96

3.4. Data handling and computational challenges 110

3.5. Conclusions 112

3.6. Acknowledgments 114

3.7. References 114

Chapter 4. Irrigation Monitoring Using High Spatial and Temporal Resolutions Remote Sensing Time Series 123
Hassan BAZZI and Nicolas BAGHDADI

4.1. Introduction 123

4.2. Fundamentals behind remote sensing for irrigation mapping 125

4.3. New methodologies for irrigation mapping using S1 and S2 time series 131

4.4. Limits and perspectives 142

4.5. Conclusions 145

4.6. References 146

Chapter 5. Trends in Satellite Time Series Processing for Vegetation Phenology Monitoring 151
Santiago BELDA, Luca PIPIA and Jochem VERRELST

5.1. Introduction 152

5.2. Time series processing for gap filling 154

5.3. Time series processing for phenology indicators estimation 161

5.4. Fusion of time series products for improved gap filling 163

5.5. Time series processing toolbox: DATimeS 170

5.6. Discussion 173

5.7. Conclusions 176

5.8. Acknowledgments 177

5.9. References 177

Chapter 6. Data-Driven Spatio-Temporal Interpolation for Satellite-Derived Geophysical Tracers 185
Maxime BEAUCHAMP and Ronan FABLET

6.1. Notations 185

6.2. Introduction 186

6.3. Data assimilation 188

6.4. Data-driven methods 196

6.5. Application to satellite-derived ocean surface topography datasets 210

6.6. Conclusion and discussion 216

6.7. References 218

Chapter 7. Recent Advances in Tropical Cyclone Forecasting Using Machine Learning on Reanalysis and Remote Sensing 223
Sophie GIFFARD-ROISIN

7.1. Background 224

7.2. Handling spatiotemporal data for TC forecasting 229

7.3. Application 1: intensity forecasting from spatiotemporal reanalysis, a hackathon experiment 231

7.4. Application 2: trajectory forecasting using fused deep learning 236

7.5. Applications using recurrent neural networks?convolutional neural networks 242

7.6. Applications using remote sensing data 246

7.7. Conclusion, current limitations and open problems 247

7.8. References 248

List of Authors 253

Index 257