Programme

Continuously in contact with the Earth Observation data users, starting in the 1990’s with the pioneering use of the ERS satellites data, then as Envisat mission manager, Henri Laur is now responsible for the management of the Earth Observation missions operated by ESA, including the Copernicus Sentinel missions, the ESA Earth Explorer missions and the ESA Third Party missions with its growing availability of commercial data.
During those three decades of growth of the Earth Observation data user communities, both in quantity and diversity, Henri Laur gained experience with the continuous race between the increasing satellite data supply, in particular with SAR, and the equally increasing user demand, in particular from public services. 

He has been the Project Scientist for JPL’s satellite altimetry missions since 1988, including TOPEX/Poseidon, Jason-1, and Jason-2.  He is currently the Project Scientist for the Surface Water and Ocean Topography Mission (SWOT). He is a member of the U.S. National Academy of Engineering, and a Fellow of the American Geophysical Union, the American Meteorological Society, and the American Association for the Advancement of Science. He has received the COSPAR International Cooperation Medal for his leadership in the development and continuation of satellite altimetry missions.

The company provides timely and reliable Earth observation data as well as natural catastrophe solutions for companies and governments. ICEYE is the first company that has successfully miniaturized a SAR satellite, making it possible to launch more units to reliably image any location on Earth, every few hours, every day. With its growing SAR satellite constellation, ICEYE offers its partners a set of unprecedented satellite imaging capabilities, accessing any area of interest faster, more frequently, and at a lower cost.

Since co-founding the project in 2012, which became the company in 2014, with Pekka Laurila, Modrzewski is responsible for overseeing the organization’s growth and implementing ICEYE’s overall vision. Modrzewski brings with him deep domain expertise in SAR engineering, and he has received the 2018 Forbes 30 under 30 Technology award based on the world-first achievements of ICEYE.

Prior to co-founding ICEYE, Modrzewski researched innovative products at VTT (Technical Research Centre of Finland) in the RFID and wireless sensing group. He attended Warsaw University of Technology in Poland, where he studied Electrical Engineering and co-founded the Multimedia Technologies Science Group. Modrzewski continued his studies in Radio Science and Engineering at Aalto University where he led the on-board data handling team working on Aalto-1, Finland’s first nanosatellite.

09:00-10:30: Introduction into SAR Interferometry 
P. Prats (DLR e.V.)

10:30-11:00 Coffee/Tea Break

11:00-12:30 Differential SAR Interferometry
A. Ferretti (TRE ALTAMIRA)

12:30-14:00 Lunch Break

14:00-15:30 SAR at Scale: Working with Large Volumes of Synthetic Aperture Radar Data 
F. Meyer & J.H. Kennedy (University of Alaska Fairbanks)

Tutorial 1

Introduction into SAR Interferometry

Biography Pau Prats

Pau Prats-Iraola received the Ingeniero degree and the Ph.D. degree, both in telecommunications engineering, from the Universitat Politècnica de Catalunya (UPC), Barcelona, Spain, in 2001 and 2006, respectively. In 2001, he was a Research Assistant at the Institute of Geomatics, Spain. In 2002, he was at the Department of Signal Theory and Communications, UPC, where he worked in the field of airborne repeat-pass interferometry and airborne differential SAR interferometry. From December 2002 to August 2006, he was an Assistant Professor at the Department of Telecommunications and Systems Engineering, Universitat Autònoma de Barcelona, Barcelona, Spain. In 2006, he joined the Microwaves and Radar Institute, German Aerospace Center (DLR), Wessling, Germany, where, since 2009, he has been the Head of the Multimodal Algorithms Group. He is the responsible and main developer of the TanDEM-X Interferometric (TAXI) processor, an end-to-end processing chain for data acquired by the TerraSAR-X and TanDEM-X satellites, which has been used to demonstrate novel SAR acquisition modes and techniques. He is currently involved in the design and implementation of the ground processor prototypes and end-to-end simulators of ESA's BIOMASS and ROSE-L missions. His research interests include high-resolution airborne/spaceborne monostatic/bistatic SAR processing, SAR interferometry, advanced interferometric acquisition modes, Persistent Scatterer Interferometry (PSI), SAR tomography and end-to-end SAR simulation. He has co-authored more than 60 peer-reviewed journal papers in the field.

The first part of this tutorial will introduce the basic concepts of SAR interferometry. This technique exploits the combination of two or more SAR images in order to measure distances to the observed scene with sub-wavelength accuracy. This extremely accurate measurement of the distance can be exploited in different ways depending on the geometry of the interferometer. A first example is the generation of very accurate digital elevation models of the Earth surface with high spatial resolution, like the ones generated by the TanDEM-X mission. Other examples include along-track interferometry or differential SAR interferometry, both of which allow the measurement of velocities and surface deformation, respectively, with an accuracy, spatial resolution and coverage not possible with any other remote sensing technique. The details of these different methods, the signal processing and the quality metrics will be expounded, always accompanied by interferometric results of past and current spaceborne SAR missions.

Differential SAR Interferometry

Biography Alessandro Ferretti

Alessandro Ferretti graduated in electronic engineering at the Politecnico di Milano, he received his  MSc. In information technology in 1993 (CEFRIEL) and his PhD in electrical engineering in 1997 (POLIMI). Together with Fabio Rocca and Claudio Prati, developed the “Permanent Scatterer Technique” (PSInSAR), a technology patented in 1999 providing millimeter accuracy surface deformation measurements from satellite radar data. He is also co-inventor of the algorithm SqueeSAR® (2009), a second-generation PSInSAR analysis. In March 2000 he co-founded TRE, today TRE ALTAMIRA, the largest InSAR company worldwide, with >100 employees in various countries. Dr. Ferretti was one of the recipients of the ENI Awards 2012 and the 2016 Highest Impact Paper Award of the IEEE Geoscience and Remote Sensing Society. Today Alessandro Ferretti is acting as CEO of TRE ALTAMIRA, part of the CLS group.

InSAR data is becoming one of the most commonly used techniques based on satellite radar sensors. By comparing radar images acquired at different times, InSAR can retrieve surface deformation data, with millimeter accuracy, over a set of measurement points on ground, automatically detected by means of signal processing algorithms. Its unique technical features and the possibility to retrieve historical deformation data, due to the availability of historical archives of satellite radar images, make InSAR a powerful tool for a variety of applications, in particular over urban areas, where the number of radar targets suitable for InSAR surveys is extremely high.

This tutorial initiates with an exploration of the fundamentals of differential InSAR, subsequently delving into an in-depth analysis of major error sources, including phase decorrelation phenomena, atmospheric effects, and phase ambiguity. The tutorial also elucidates the rationale behind employing multi-interferogram approaches. An overview of current data sources and insights into evolving trends in the space segment are briefly examined.

Illustrated through a diverse gallery of examples, ranging from expansive regional mapping (e.g., InSAR analysis covering entire nations) to detailed single-building analysis, the tutorial aims to underscore the successful mitigation of operational challenges associated with InSAR data utilization. This progress positions InSAR as a standard tool within the geotechnical and civil engineering community, substantiated by tangible evidence derived from practical applications.

SAR at Scale: Working with Large Volumes of Synthetic Aperture Radar Data

Biography F. Meyer & Joseph H Kennedy

Dr. Joseph H. Kennedy; Staff Scientist, Alaska Satellite Facility Dr. Kennedy is a glaciologist by training and a lead developer of HyP3, ASF’s On Demand processing system. He specializes in multi-institution open-source software development, cloud and high-performance computing, and verification and validation of scientific models. He has extensive experience with developing end-to-end data science projects incorporating machine learning and statistical analysis of Big Data using the scientific python ecosystem.

Dr. Franz J. Meyer; Professor, University of Alaska Fairbanks (UAF) and Chief Scientist, Alaska Satellite Facility Dr. Meyer’s technical research interests include SAR image formation and analysis, ionospheric and atmospheric correction, and interferometric SAR (InSAR), and his applications research is focused on geo- and weather-related hazards. He is heavily engaged in capacity building in the field of radar remote sensing. His work at ASF is focused on engagement with the growing SAR user community and the development of new value-added products and services, as well as providing training to science and applications communities. He is also a science team member of the NASA/ISRO SAR mission (NISAR).

Dr. Forrest F. Williams; Research Software Engineer, Alaska Satellite Facility Dr. Forrest F. Williams is a Research Software Engineer at the Alaska Satellite Facility (ASF). His research interests include country-scale monitoring of landslide hazards, the use of time-series InSAR to monitor local deformation sources, and the creation of standard InSAR products that fit a wide variety of use cases. He is a core developer of HyP3, ASF’s On Demand processing system, and works to create and improve cloud-based scientific workflows.

This 1.5-hour tutorial will introduce the community to working with large-volume InSAR data at scale using an ecosystem of cloud-computing resources available through the Alaska Satellite Facility (ASF). Attendees will explore efficient ways to data discovery and scientific use of SAR and InSAR data using freely-available open SAR data, services, and tools. Attendees will learn how to use OpenSARLab, ASF’s cloud-hosted JupyteHub computing environment, to perform InSAR analyses in a programmatic environment suited to big data analytics. This will include basics such as SAR data search and discovery, and how to interact with ASF’s on-demand SAR processing services. Attendees will use these tools to perform an SBAS-type InSAR time-series analysis that recreates the recent discovery of volcanic activity at the Mt Edgecumbe volcano in Alaska. The time-series analysis will utilize the Miami InSAR Time-series in Python (MintPy) package, an open-source tool that is quickly becoming a community standard. After attending this tutorial, attendees will have learned how to work within a cloud-hosted JupyterHub environment, use ASF’s open-source Python tools to obtain data, and perform SAR change-detection and time-series analyses.

09:00-10:30: Bistatic and Multistatic SAR
F. Lopez-Dekker (TU Delft)

10:30-11:00 Coffee/Tea Break

11:00-12:30 Digital Beamforming for SAR
M.Younis (DLR e.V.)

12:30-14:00 Lunch Break

14:00-15:30 SAR Concepts Based on Small Apertures
M. Villano (DLR e.V.)

Tutorial 2

Bistatic and Multistatic SAR

Biography Francisco López-Dekker

Paco López Dekker (Senior Member, IEEE) was born in Nijmegen, The Netherlands, in 1972. He received the Ingeniero degree in telecommunication engineering from Universitat Politècnica de Catalunya (UPC), Barcelona, Spain, in 1997, the M.S. degree in electrical and computer engineering from the University of California at Irvine, Irvine, CA, USA, in 1998, under the Balsells Fellowship, and the Ph.D. degree from the University of Massachusetts Amherst, Amherst, MA, USA, in 2003, with a focus on clear-air imaging radar systems to study the atmospheric boundary layer. From 1999 to 2003, he was with the Microwave Remote Sensing Laboratory, University of Massachusetts Amherst. In 2003, he was with Starlab, Barcelona, where he was involved in the development of GNSS-R sensors. From 2004 to 2006, he was a Visiting Professor with the Department of Telecommunications and Systems Engineering, Universitat Autonoma de Barcelona, Barcelona. In 2006, he joined the Remote Sensing Laboratory, UPC, where he conducted research on bistatic synthetic aperture radar (SAR) under a five-year Ramon y Cajal Grant. From 2009 to 2016, he lead the SAR Missions Group, Microwaves and Radar Institute, German Aerospace Center, Weßling, Germany. The focus of the SAR Missions Group was the study of future SAR missions, including the development of novel mission concepts and detailed mission performance analyses. Since 2016, he has been an Associate Professor with the Faculty of Civil Engineering and Geosciences, Delft University of Technology, Delft, The Netherlands. He is currently the Principal Investigator of Harmony, the ESA 10th Earth Explorer mission. His research interests include (In)SAR time series analysis, the use of SAR to study ocean processes, and the development of distributed multistatic radar concepts.

After the success of the TanDEM-X mission and the selection of Harmony as ESA’s 10th Earth Explorer mission, bistatic and multistatic SAR missions should be expected to become a common element in our Earth Observation mix. This first part of the tutorial will provide a quick introduction to bistatic and multistatic SAR concepts that exploit the resulting geometric diversity to enhance the geophysical information content, for example through the use of single-pass across-track interferometry, or directional scatterometry. Starting with a taxonomy of multistatic systems, we will introduce relevant flight configurations (formations) and touch on the most relevant technical challenges, notably time and phase synchronization. Then we will discuss the currently most relevant techniques and applications, including across-track interferometry for Digital Elevation Model generation, touching briefly on coherence-based tomography; multi-directional repeat-pass interferometry for 3-D deformation vectors; directional multistatic scatterometry, emphasizing its application to surface wind-stress retrieval over oceans. For each application, we will introduce the concept, discuss the main technical implications and trade-offs, and discuss the achievable performances.

Digital Beamforming for SAR

Biography Marwan Younis

Marwan Younis received his B.Sc in electrical engineering from the University of Baghdad, Iraq in 1992 and the Dipl.-Ing. (M.Sc.) and Dr.-Ing. (Ph.D.) degree in electrical engineering from the Universität Karlsruhe (TH), Germany, in 1997 and 2004, respectively. From 1998 to 2004, he was a research scientist with the Institut für Höchstfrequenztechnik und Elektronik, Universität Karlsruhe. Since 2005 he has been with the Microwaves and Radar Institute of the German Aerospace Center (DLR), Oberpfaffenhofen, Germany. He is currently Head of the SAR Techniques Group at the DLR and Professor for Spaceborne Radar Systems at the Karlsruhe Institute for Technology (KIT), Germany. He is the author and co-author of about 200 conference papers, 46 reviewed publications and holds 5 patents. He is DLR Senior Scientist and his research fields include synthetic aperture radar (SAR) systems and techniques, MIMO SAR, digital beamforming, SAR performance, calibration, and antennas. In 1996 he was an intern at the Jet Propulsion Laboratory (JPL), in 2013 and 2019 he spent research sabbaticals at JPL.

Dr. Younis is an active member of the IEEE and GRSS. He chaired the Instrumentation and Future Technologies GRSS Technical Committee. He is reviewer of IEEE publications and was associate editor for the IEEE geoscience and remote sensing letter (2012-2019). He received the Hermann-Billing award for his Ph.D. thesis in 2005.

The course introduces the basic SAR instrument performance parameters which are then used to show the fundamental limitations of single channel SAR instruments. This motivates the use of multi-channel instruments and Digital Beamforming (DBF) techniques, which are shown to overcome the mentioned limitations and introduce new degrees of freedom in the SAR performance trade-space. The basic DBF techniques: Multiple Azimuth Channel systems (MACs) and SCan-On-REceive (SCORE) are explained. Moreover, multi-channel SAR facilitates the use of more advanced DBF imaging modes, which are covered in the course. It is shown how refelector-based SAR with a digital feed array may implement DBF techniques.

SAR Concepts Based on Small Apertures

Biography Michelangelo Villano

Michelangelo Villano is currently the Head of the NewSpace SAR research group at the Microwaves and Radar Institute of the German Aerospace Centre (DLR), Weßling, Germany, where he has been working since 2009, and a lecturer at the University of Ulm, Ulm, Germany. He obtained the B.Sc. (Hons) and M.Sc. (Hons) degrees in Telecommunications Engineering at Sapienza University of Rome, Rome, Italy, and the PhD (Hons) degree at the Karlsruhe Institute of Technology, Karlsruhe, Germany, in 2006, 2008 and 2016, respectively. From 2008 to 2009, he was a Young Graduate Trainee at the European Space Agency, Noordwijk, Netherlands. In 2017, he was a visiting scientist at the NASA Jet Propulsion Laboratory, Pasadena, CA, USA.

The third part of this tutorial starts from understanding the impact of antenna aperture size on SAR performance in terms of noise level and ambiguities and explores the opportunities for using small apertures both on a single satellite and in clusters of small satellites. Finally, recent advances and experimental demonstrations of novel techniques are presented.

09:00-10:30: Polarimetric SAR and Applications
L. Ferro-Famil (University of Rennes)

10:30-11:00 Coffee/Tea Break

11:00-12:30 Pol-InSAR and Applications
K. Papathanassiou (DLR e.V.)

12:30-14:00 Lunch Break

14:00-15:30 SAR Tomography
M. Pardini (DLR e.V.)

Tutorial 3

Polarimetric SAR and Applications

Biography Laurent Ferro-Famil

Laurent Ferro-Famil (Member, IEEE) received the Laurea degree in electronics systems and computer engineering and the M.S. and Ph.D. degrees in electronics from the University of Nantes, Nantes, France, in 1996, 1996, and 2000, respectively.,In 2001, he became an Associate Professor with the University of Rennes 1, Toulouse, France, where he has been a Full Professor, since 2011. He is also the Head of the IETR Laboratory, Waves and Signals Department, Rennes, France, and the CESBIO Laboratory, Radar Group, Toulouse. His activities in education are concerned with analog electronics, digital communications, microwave theory, signal processing, and polarimetric synthetic aperture radar (SAR) remote sensing. His research interests include radar signal processing for remote sensing applications, including radar polarimetry theory, electromagnetic imaging, and natural media remote sensing using radar multibaseline PolInSAR data, with application to classification, electromagnetic scattering modeling, physical parameter retrieval, and 3-D reconstruction of environments using tomography.

SAR polarimetry enables us to separate different scattering mechanisms within a resolution cell. This fact is important for a diversity of application and is at the same time extending the observations space for parameter retrieval. In this course you will learn how to generate a polarimetric scattering matrix for point and distributed scatterers and I will introduce several decomposition techniques. Each of the techniquie is associated with an application.

Pol-InSAR and Applications

Biography Konstantinos Papathanassiou

Konstantinos P. Papathanassiou received the Dipl. Ing degree in 1994 and the Dr. degree in 1999 from the Technical University of Graz, Austria. He is a senior scientist leading the Information Retrieval research group at the Microwaves and Radar Institute (HR) of the German Aerospace Center (DLR), in Oberpfaffenhofen, Germany.

Polarimetric SAR interferometry (Pol-InSAR) extends the conventional polarimetric space by interferometric, e.g. coherent multi-angle acquisitions. The introduction of angular diversity provides sensitivity to the vertical distribution of scatterers and allows unique applications related to the vertical structure of natural and man-made volume scatterers. This part of the tutorial introduces the information content of Pol-InSAR data and discusses its potential and limitations, and how these affect established and potential applications. Examples and results from recent airborne and spaceborne experiments are presented and reviewed.

SAR Tomography

Biography Matteo Pardini

This tutorial aims at providing an understanding of basic principles and applications of SAR Tomography. Requirements on appropriate tomographic acquisition configurations for 3-D reflectivity reconstruction are addressed. Further, inversion approaches are compared highlighting their characteristics and limitations. The information content of the obtained reconstruction (depending on frequency, polarization, viewing geometry, and physical structure, distribution and dielectric properties of the scattering elements) and their ambiguities are discussed in the context of the definition and generation of (geophysical) information products. For demonstration and validation many results from relevant airborne campaigns on forest, ice and agricultural scenarios are used.

SAR Tomography allows the reconstruction of the 3-D radar reflectivity of natural and man-made volume scatterers relying on a set of images acquired under slightly different angular directions along displaced tracks or orbits. In the last years, this capability triggered the development of a wide range of unique products related to the 3D structure of volume scatterers, demonstrated in a number of successful airborne experiments. These results initiated the conceptualization of TomoSAR acquisition modes in future spaceborne SAR configurations.

09:00-10:30: Machine Learning for SAR Processing - SAR image despeckling by deep learning
Loïc Denis (Université de Saint-Etienne) and Emanuele Dalsasso (École Polytechnique Fédérale de Lausanne - EPFL)

10:30-11:00 Coffee/Tea Break

11:00-12:30 Machine Learning for SAR Analysis - From fully- to self-supervised deep learning
R. Hänsch (DLR e.V.)

12:30-14:00 Lunch Break

14:00-15:30 Machine Learning for SAR Applications - From SAR images to Earth observation products
M. Schmitt (University of the Bundeswehr Munich)

Tutorial 4

Machine Learning for SAR Processing - SAR image despeckling by deep learning

Biography Loïc Denis

Loïc Denis (M.Sc., CPE Lyon, 2003; Ph.D., Univ. Saint-Etienne, 2006; Habil., 2018) is full Professor at the Université Jean Monnet Saint-Etienne. His research interests include image denoising and reconstruction, robust signal processing, source detection, and machine learning with applications in remote sensing, diffractive microscopy, and astronomy. Dr. Denis was a co-recipient of the IEEE ICIP Best Student Paper Award in 2010, the EUSPICO Best Student Paper, the IEEE Geoscience and Remote Sensing Society 2016 Transactions Prize Paper Award in 2016, and the 2021 IEEE GRSS Symposium Prize Paper Award. He is an IEEE Senior Member and serves as an Associate Editor for the IEEE transactions on Image Processing.

Despeckling is a critical preprocessing step for Synthetic Aperture Radar images, as it reduces fluctuations and enhances image interpretation and downstream processing. This longstanding research topic has benefited from various advancements in image restoration techniques. However, the field has reached another milestone with the advent of deep learning methods. This presentation will explore different training strategies for despeckling networks, with a particular focus on the integration of speckle models in these approaches. Moreover, we will highlight the potential benefits of self-supervised despeckling beyond image restoration, such as learning relevant features from SAR images. By doing so, this presentation aims to provide a comprehensive understanding of the latest developments and trends in SAR despeckling research.

Machine Learning for SAR Analysis - From fully- to self-supervised deep learning

Biography Ronny Hänsch

Ronny Hänsch received the Diploma in computer science and the Ph.D. degree from the TU Berlin, Berlin, Germany, in 2007 and 2014, respectively. He is a scientist at the Microwave and Radar Institute of the German Aerospace Center (DLR) where he leads the Machine Learning Team in the Signal Processing Group of the SAR Technology Department. He continues to lecture at the TU Berlin in the Computer Vision and Remote Sensing Group. His research interest is computer vision and machine learning with a focus on remote sensing (in particular SAR processing and analysis). He served as chair of the GRSS Image Analysis and Data Fusion (IADF) technical committee and as editor of the GRSS eNewsletter, serves as co-chair of the ISPRS working group on Image Orientation and Sensor Fusion, editor in chief of the Geoscience and Remote Sensing Letters and associate editor of the ISPRS Journal of Photogrammetry and Remote Sensing, organizer of the CVPR Workshop EarthVision (2017-2024) and the IGARSS Tutorial on Machine Learning in Remote Sensing (2017-2024). He has extensive experience in organizing remote sensing community competitions, serves as the GRSS representative within SpaceNet and was the technical lead of the SpaceNet 8 Challenge.

Machine and in particular deep learning has shown tremendous success in many application areas including remote sensing and Earth observation. Even for SAR imagery where the data poses significant challenges for automatic processing and analysis, models have been developed to address tasks ranging from image retrieval, semantic analysis, to the extraction of bio-/geo-physical parameters. The early success of such models was mostly driven by ever-growing training datasets. Providing such datasets for fully supervised learning was always a challenge for SAR applications where the creation of the required reference data is often extremely challenging. More recent approaches stir away from fully-supervised learning towards leveraging the large amount of unlabelled data. This talk will discuss challenges of modern approaches of machine / deep learning to analyze SAR data and possible ways to address them.

Machine Learning for SAR Applications - From SAR images to Earth observation products

Biography Michael Schmitt

Michael Schmitt received his Dipl.-Ing. (Univ.) degree in geodesy and geoinformation, his Dr.-Ing. degree in remote sensing, and his habilitation in data fusion from the Technical University of Munich (TUM), Germany, in 2009, 2014, and 2018, respectively. Since 2021, he has been a Full Professor for Earth Observation at the Department of Aerospace Engineering of the University of the Bundeswehr Munich (UniBw M) in Neubiberg, Germany. He is a also a member of the Research Center SPACE and the Institute of Space Technology & Space Applications of UniBw M. From 2020 to 2022, he additionally held the position of a Consulting Senior Scientist at the Remote Sensing Technology Institute of the German Aerospace Center (DLR). Before joining UniBw M, he was a Professor for Applied Geodesy and Remote Sensing at the Munich University of Applied Sciences, Department of Geoinformatics. From 2015 to 2020, he was a Senior Researcher and Deputy Head at the Professorship for Signal Processing in Earth Observation at TUM; in 2019 he was additionally appointed as Adjunct Teaching Professor at the Department of Aerospace and Geodesy of TUM. In 2016, he was a guest scientist at the University of Massachusetts, Amherst. His research focuses on technical aspects of Earth observation, in particular image analysis and machine learning applied to the extraction of information from multi-modal remote sensing observations. He is a co-chair of the Working Group ``Active Microwave Sensing'' of the International Society for Photogrammetry and Remote Sensing, and an active member of the Working Group ``Benchmarking'' of the IEEE-GRSS Image Analysis and Data Fusion Technical Committee. He frequently serves as a reviewer for a number of renowned international journals and conferences and has received several Best Reviewer awards. He is a Senior Member of the IEEE and an associate editor of IEEE Geoscience and Remote Sensing Magazine as well as a Co-Editor of the Springer Journal of Photogrammetry, Remote Sensing and Geoinformation Science (PFG).

In this part of the tutorial, the combination of SAR-specific domain expertise and modern deep neural network machine learning architectures will be discussed. For that purpose, application examples such as the reconstruction of high-resolution urban height models from single SAR intensity images or the SAR-based estimation of vegetation indices, which are usually derived from multi-spectral optical data, will be addressed.

09:00-10:30: Welcome, introduction, and overview
René Guenzkofer (NV5 Geospatial Solutions)

09:30-10:00 Setting the SAR benchmark with 24/7 global insights
Sybrand van Beijma (Capella Space)

10:00-10:30 SAR simulation – extending the reality
Giulia Tessari (sarmap) & Jürgen Schwarz (Capella Space)

10:30-11:00 Coffee/Tea Break

11:00-11:30 SAR for all - SAR solutions for all kind of users
Thomas Bahr (NV5 Geospatial Solutions)

11:30-12:00 ENVI Inform – SAR-based insights worldwide
David Burridge (NV5 Geospatial Solutions)

12:00-12:30 SAR for maritime - from worldwide monitoring to situational awareness
Emlyn Hagen (NV5 Geospatial Solutions)

12:30-14:00 Lunch Break

14:00-14:30 Operational applications of interferometric time-series analysis
Giulia Tessari (sarmap)

14:30-15:00 UAV based SAR solutions
Paolo Pasquali (sarmap)

15:00-15:15 Results from today´s SAR tasking
Jürgen Schwarz (Capella Space)

15:15-15:30 Summary & outlook
René Guenzkofer (NV5 Geospatial Solutions)

Tutorial 5

Welcome, introduction, and overview

Biography René Guenzkofer (NV5 Geospatial Solutions)

Rene is Managing Director of NV5 Geospatial Solutions GmbH in Germany and Sales Director for Europe. He is holding commercial positions within the earth observation domain for more than 20 years. Working in leading IT organizations and their software, hardware, and services business for more than 30 years are providing him a wealth of market overview. His specific and long termed experiences with airborne and spaceborne SAR acquisition and data processing are making him an insider and well known advocate within the SAR community.

Setting the SAR benchmark with 24/7 global insights

Sybrand van Beijma (Capella Space)

(not available)

SAR simulation – extending the reality

Giulia Tessari (sarmap) & Jürgen Schwarz (Capella Space)

(see below)

SAR for all - SAR solutions for all kind of users

Biography Thomas Bahr (NV5 Geospatial Solutions)

As a Sr. Solutions Engineer at NV5 Geospatial, Thomas is a technical point of contact for ENVI customers across Europe. Diploma degree in 1992 and the Dr.rer.nat. degree in 1997 at the University of Munich (Germany) in Geology, with since then 30+ years of experience in remote sensing and 20+ years in the company. Main interest is in latest advancements in SAR data analytics, Hyperspectral Imaging, and Deep Learning applications.

Historically, the analysis of Synthetic Aperture Radar (SAR) data was predominantly the domain of highly specialized experts, primarily researchers, as well as basic visual interpretation by some analysts. However, the landscape of SAR data utilization is rapidly changing, necessitating a broad spectrum of solutions that cater to the evolving needs of a diverse user base. This transformation encompasses the development of fully automated systems, incorporating advanced deep learning techniques, that offer straightforward representations for decision-makers, alongside the creation of intuitive interactive tools designed for operators with minimal SAR experience. Furthermore, the progression extends to the provision of user-friendly yet sophisticated analysis tools for intermediate users, culminating in the delivery of cutting-edge SAR analytics solutions for the expert community.

In this presentation, NV5 will delineate its comprehensive approach to addressing the varied requirements of this expanding user base. We will explore the significance of developing tailored SAR solutions, emphasizing the importance of such diversity for the SAR community's growth and the enhancement of its operational capabilities. The primary aim is to enlighten the expert SAR community about the range of options now available, fostering a deeper understanding and appreciation of the potential applications and benefits of SAR data across different sectors. NV5 aspires to highlight the critical role of adaptable SAR analytics in meeting the demands of all SAR users, from novices to seasoned professionals, thereby ensuring that SAR technology becomes an indispensable tool for a wide array of applications.

NVI Inform – SAR-based insights worldwide

Biography David Burridge (NV5 Geospatial Solutions)

David is the Director of Enterprise Services at NV5 Geospatial. He has worked in the data analytics software business for over 25 years, including over 17 years in image analysis and exploitation and most recently the automation of image analytics in the cloud. He currently leads the team delivering ENVI Insight, which delivers image-derived information at scale using ENVI’s proven analytics hosted in a scalable cloud environment.

SAR for maritime - from worldwide monitoring to situational awareness

Biography Emlyn Hagen (NV5 Geospatial Solutions)

Dr. Emlyn Hagen is a Senior Manager at NV5 Geospatial and he is responsible for the Defense and Intelligence portfolio. Emlyn’s passion for remote sensing started 20 years ago at the DLR in Germany and CRISP in Singapore, and uses his skills today to provide innovative, realistic and focused remote sensing solutions to clients.

Before joining NV5, Emlyn was CTO of iMMAP and leading the USAID funded Disaster Risk Reduction Program in Afghanistan (2015-2018). For 8 years Emlyn supported the NATO CI Agency as a geospatial expert. He worked in theater support for Bosnia, Kosovo and Afghanistan as on various NATO GIS/RS research projects. The execution of the “Afghanistan Flood Hazard Map” project was highly visible, and it was nominated for the World Future Foundation (WFF) award.

Emlyn was the Lead Geographic Information Manager for the Shell Oil operations in Jordan (2010-2015). His work on "Communication Access and Proximity Maps" was nominated for the Shell CEO Global HSSE Award. It resulted into effective and safe operations for the 300 staff exploring a 20.000 km² hostile desert environment. Additionally, he was the Geomatics Technical Adviser of a 1.2 Billion US$ project.

Emlyn has published two books and multiple peer reviewed scientific papers. He was born in Belgium and currently lives in Augsburg, Germany; he acquired his PhD at the NUS Singapore and MSc at the University of Munich.

The advent of high-resolution SAR satellites has revolutionized maritime domain surveillance, offering enhanced planning, tasking, and frequent revisits. Despite these advancements, the challenge lies in effectively deploying these assets, particularly outside known maritime hotspots. The NV5 global ship detection and classification system is pivotal in addressing this gap, extending its utility to offshore asset monitoring, such as wind turbines and oil rigs. Anomaly detection triggers a coordinated response from various high-resolution satellites, emphasizing the need for advanced ATR/SAR Simulator capabilities. Additionally, the system can filter out Radio Frequency Interference in SAR imagery, providing additional waveform characteristics and the geolocation of RF emitters. Concurrently, it employs automated tidal height coastline extraction from SAR imagery, offering insights into coastal features at different tidal stages, crucial for comprehensive maritime surveillance.

Operational applications of SAR time-series analysis

Biography Giulia Tessari (sarmap)

PhD in Earth Sciences and master`s degree in Environmental Engineering, Giulia currently works as a Senior Remote Sensing Specialist at sarmap SA, following a PostDoc Marie Skłodowska Curie fellowship at sarmap and a PostDoc at the Geosciences Department of the University of Padova. Her main research interests concern the use of Remote Sensing Techniques, particularly space-borne SAR Interferometry, to monitor geological hazards and instability phenomena such as landslides, subsidence, sinkholes and even man-made structures, buildings and infrastructures affected by possible damages. Furthermore, she is interested on modelling the sources that cause these events to understand their triggering factors.

In the last decades, SAR data proved their power as a tool for continuous monitoring of the Earth’s surface. The recent mission enhanced the data capabilities, guaranteeing a global coverage in case of Sentinel-1 and increasing the SAR temporal sampling thanks to small satellite constellations. Several parameters can be extracted from SAR data, such as backscatter, interferometric phase and interferometric coherence. The analysis of temporal series of such parameters allows monitoring a wide range of natural and human driven processes.

Several examples of SAR time series analysis are presented, from changes occurring in the surface, such as floods, deforestation, agriculture monitoring, illegal activities, to surface deformations, infrastructure stability, etc., highlighting the importance of extracting relevant synthetic indicators simplifying the interpretation of the dramatic amount of information that can be extracted from a stack of SAR data.

UAV based SAR solutions

Biography Paolo Pasquali (sarmap)

Paolo received the M.Sc (1990) and Ph.D. (1995) in electrical engineering and telecomunication , Politecnico di Milano in the domain of SAR processing and interferometry. Postdoc (1995-1999) at University of Zurich in the remote sensing laboratories. He is co-founder, President and Technical Director of sarmap. From 2003 to 2008 Contracted professor at Trento University. Remote Sensing specialist with particular expertise in SAR signal processing, InSAR, DInSAR processing, polarimetry, and tomography. He is principal and co-investigator of several ESA, EC, and Swiss Innovation Promotion projects. Reviewer of various journals in remote sensing and in the scientific committee of several ESA conferences.

The recent wide availability of SAR data from public as well as private providers, with different characteristics as spatial and temporal resolution, operating frequency and others, might give the impression that more than enough SAR imagery is available to develop techniques and provide numerous services.

On the other hand, real data bring along the complexity of the reality of the scenarios over which they have been acquired, where not all components of the scene and parameters can be completely controlled and known, making in most of the cases very difficult the developments and accurate testing of new approaches and applications. The possibility of exploiting precise simulation approaches can therefore be very beneficial for being able of fully understanding the information content of SAR data and making the extraction of most of the contained information possible.

Examples will be shown to demonstrate how the availability of accurate SAR simulations can very well complement and extend the exploitation of modern SAR real imagery.

SAR images are not necessarily very easy to analyze and visually interpret, and these difficulties can even increase in case of images of man-made objects and infrastructures.

The recent developments in the domains of Artificial Intelligence and Deep Learning methods may significantly contribute to simplifying these tasks, providing approaches to Automated Target Detection and Classification that can reach high levels of accuracy and robustness. These methods, very often derived from approaches originally developed for handling optical imagery, shall be carefully adapted to the new domain of application but, when the nature of the SAR data is kept into consideration, can reach very high performances also in this case.

After introducing the peculiarities of these approaches, a number of examples will be shown concerning the exploitation of these techniques on VHR SAR data derived from different spaceborne and airborne platforms for different applications.