IEEE GRSS-USC MHI 2023 Remote Sensing Summer School

Date: July 13-15, 2023 (Thursday to Saturday)
Venue:
University of Southern California
Hughes Aircraft Electrical Engineering Center (EEB)
3740 McClintock Ave, Los Angeles, CA 90089
Contact: summerschool@2023.ieeeigarss.org, uscieeegrssaps@gmail.com

Introduction

The summer school will include three courses: 1) Introduction to Geospatial Raster and Vector Data with Python, 2) Deep Learning for Remote Sensing Data Analysis, 3) Introduction to Radar Interferometry and Its Applications, and three invited lectures including space-based environmental monitoring, small satellite science and applications, and NASA-ISRO SAR (NISAR) mission.

The Summer School is open to both students and young professionals. Meals will be provided to all participants on all training days. If you need housing accommodation, please register by May 31, 2023. Due to limited funds, housing is not guaranteed and will only be provided to 30 participants by USC Housing for July 12–15 (4 nights). You will be notified by June 7, 2023 whether you have been selected to receive housing accommodation. If you are not selected for housing accommodation and as a result, decide not to attend the school, you will be refunded the registration fee in full.

The summer school, held in conjunction with IEEE IGARSS 2023, is sponsored jointly by the IEEE Geoscience and Remote Sensing Society (GRSS), the Ming Hsieh Institute of the University of Southern California (USC), and the IEEE Metropolitan Los Angeles Section GRSS Chapter. The school is hosted by the IEEE GRSS-APS-SSCS Joint Student Branch Chapter at USC.

Event Schedule

Overall schedule is provided below, the details will be posted online shortly.

Date Themes
July 12 Afternoon Housing Check-in
Day 1 July 13 Morning Welcome Package
Tutorial: Introduction to Geospatial Raster and Vector Data with Python [Part I]
July 13 Afternoon Tutorial: Introduction to Geospatial Raster and Vector Data with Python [Part II]
Lecture: Space-Based Environmental Monitoring
Day 2 July 14 Morning Tutorial: Deep Learning for Remote Sensing Data Analysis [Part I]
July 14 Afternoon Tutorial: Deep Learning for Remote Sensing Data Analysis [Part II]
Lecture: NASA-ISRO SAR Mission (NISAR)
Day 3 July 15 Morning Tutorial: Introduction to Radar Interferometry and Its Applications [Part I]
July 15 Afternoon Tutorial: Introduction to Radar Interferometry and Its Applications [Part II]
Lecture: Small Satellite Science and Applications
July 16 Morning Housing Check-Out

Registration

Registration is on a first-come, first-served basis, with a 50 USD registration fee. Please register here.

Course Description

Course I: Introduction to Geospatial Raster and Vector Data with Python

Overview:

Introduction to Geospatial Raster and Vector Data with Python is an interactive workshop designed to empower you with the skills to query, analyze, and visualize geospatial raster and vector data. In this hands-on session, you'll work with real-world remote sensing datasets and environmental data from Amsterdam using your own laptop and the Jupyter notebook programming environment.

Topics we’ll cover include how Python handles spatial data structures, coordinate reference systems, rasters, and vectors. Throughout we’ll use powerful geospatial libraries like pystac-client, rioxarray, and geopandas to fetch, open, and plot raster and vector datasets using Cloud Optimized Geotiffs (COGs). We’ll touch on how this enables accessing and processing large datasets from the cloud for big data workflows.

Additionally we’ll cover how to effectively manipulate raster data: managing missing data points, cropping to specific regions of interest, and computing zonal statistics with vector areas of interest.

Finally, you'll discover how to use xarray and dask to run computations lazily or in parallel on raster datasets. Join us to unlock the power of Python and harness the full potential of geospatial data for your research and projects!

Instructors:

Ryan Avery, Machine Learning Engineer, Development Seed

Ryan is a Machine Learning Engineer at Development Seed. He develops machine learning models to detect land-use and land cover change in medium and high resolution satellite imagery. He is passionate about helping organizations make sound decisions that improve environmental outcomes and livelihoods.

Previously, Ryan was a graduate student in the Water, Vegetation, and Society Lab (WAVES). While there, he created CropMask_RCNN, a project to train state of the art models to predict crop circle boundaries in drylands. Ryan previously worked with the Mapping Africa project, where he worked on mapping smallholder farms in Ghana using PlanetScope imagery to improve agricultural land use planning and food security in the region.

When he’s not coding or teaching coding workshops, he enjoys climbing boulders in the Bay Area, learning strategy games, and practicing jiu-jitsu. Ryan received a Masters in Geography from UC Santa Barbara.

Chuck Daniels, Cloud Engineer, Development Seed

Chuck is a data engineer at Development Seed. He builds flexible data-driven systems and is an advocate of using open data to solve environmental and social issues. He works with our team that builds infrastructure for data providers like NASA to innovate new ways to distribute data on the cloud. He builds core infrastructure for Cumulus, which helps to better leverage cloud computing for data processing, storage, and retrieval of NASA’s Earth observation data.

Chuck is an experienced engineer with a background in cloud operations and software architecture. He has worked across several industries, including e-commerce and wellness, and has served in roles ranging from e-commerce architect to director of IT.

Chuck holds a B.S. with a dual-major in Computer Science and Mathematics, and a minor in Physics. He received a Master’s Degree in Computer Science with a concentration in massively parallel algorithms from the University of Maryland, College Park.

Course II: Deep Learning for Remote Sensing Data Analysis

Overview:

This course will explore the application of deep learning techniques for remote sensing data analysis. The curriculum will include an introduction to machine learning, focusing on different learning architectures, problem types, data types, and challenges, as well as mathematical aspects such as optimization, regression vs. classification, objectives, and losses functions. Participants will gain an understanding of various deep learning architectures, including CNNs, RNNs, LSTMs, ConvLSTMs, and state-of-the-art transformers, which are becoming essential for the effective analysis of spatio-temporal data.

The course will cover both discriminative models for tasks like classification, detection, and regression in remote sensing, as well as generative models for image enhancement and forecasting. Furthermore, the application in decision-making will also be presented through topics such as Markov decision processes and deep reinforcement learning. Last, an overview of additional subjects will be presented including topics like uncertainty, expandability, physics-informed DNNs, and foundational models.

Instructor:

Grigorios Tsagkatakis, Associate Professor, University of Crete and Institute of Computer Science, and affiliated researcher, Foundation for Research and Technology - Hellas (FORTH)

Grigorios Tsagkatakis is an associate professor at the Computer Science Department of the University of Crete and an affiliated researcher at the Institute of Computer Science of the Foundation for Research and Technology – Hellas (FORTH) in Greece. He received his BE and MS degrees in Electronics and Computer Engineering from the Technical University of Crete, Greece in 2005 and 2007 respectively, and his Ph.D. in Imaging Science from the Rochester Institute of Technology, New York, in 2011. Between 2019 and 2021, he was a Marie Skłodowska–Curie fellow at the Department of Electrical and Computer Engineering of the University of Southern California with Prof. M. Moghaddam. His research focuses on topics related to signal/image processing and machine learning with applications in remote sensing and astrophysics.

Course III: Introduction to Radar Interferometry and Its Applications

Overview:

Radar interferometry is one of the most powerful remote sensing techniques with applications to such diverse areas as topography measurement, geophysics of the solid earth and cryosphere and to ecosystems. This one-day course will provide an introduction to radar interferometry and its applications. We will begin with a brief review of radar and SAR imaging principles followed by the basics of interferometry for both topography measurement and of differential interferometry for measuring surface change and deformation. We will cover interferometric measurement techniques, interferometric phase and correlation, interferometric sensitivity equations for topography and deformation, error sources and limitations of the techniques. Principles and applications will be illustrated with examples from both spaceborne and airborne systems. Finally, advanced concepts such as polarimetric interferometry and tomography will be briefly introduced.

Instructor:

Scott Hensley, Senior Research Scientist, NASA Jet Propulsion Laboratory

Scott Hensley received his BS degrees in Mathematics and Physics from the University of California at Irvine and the Ph.D. in Mathematics from Stony Brook University where he specialized in the study of differential geometry. In 1991, Dr. Hensley joined the staff of the Jet Propulsion Laboratory where he is currently a Senior Research Scientist studying advanced radar techniques for geophysical applications. He has worked on the Magellan and Cassini radars, was the GeoSAR Chief Scientist, lead the SRTM Interferometric Processor Development Team, lead a team using GSSR data to generate topographic maps of the moon and was Principal Investigator and is currently the Project Scientist for the NASA UAVSAR program which is an airborne electronically scanned L-band radar designed for repeat pass applications. Most recently he has been very active in developing proposals for exploring the solar system that require radar observations.

Invited Lectures

Lecture I: Space-Based Environmental Monitoring

Lecturer:

David Kunkee, Associate Director, The Aerospace Corporation

David Kunkee received the Ph.D. degree in electrical engineering from the Georgia Institute of Technology, Atlanta, in 1995. He joined The Aerospace Corporation in 1995 and is currently a Principal Engineer/Scientist within the Sensor Systems Subdivision. From 2010 to 2014 he was a member of the Environmental Satellite Systems Division as part of the Defense Weather Satellite System (DWSS) and Weather System Follow-on (WSF) program offices. From 2006 to 2010 he was a member of the National Polar-orbiting Operational Environmental Satellite System (NPOESS) Integrated Program Office (IPO), and led the Aerospace Microwave Sensors and Data Products Department within the NPOESS IPO. From 2002 to 2005 he was the Associate Director of the Radar and Signal Systems Department at Aerospace. Dr. Kunkee has served on several review boards supporting space-based sensors and technology for environmental monitoring and associated mission development.

Dr. Kunkee is Past President of the IEEE Geoscience and Remote Sensing Society (GRSS) and Technical Program Committee Co-Chair for IGARSS 2023. He was General Co-Chair of the 2017 International Geoscience and Remote Sensing Symposium (IGARSS) and served as Co-Chair of the Technical Program Committee for IGARSS 2010. From 2007 to 2009 he was Editor-in-Chief of the GRSS Newsletter. Dr. Kunkee is currently an Associate Editor of the IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS) and has served as Guest Editor for past special issues of the IEEE Transactions on Geoscience and Remote Sensing (TGRS), and a special section of the IEEE Transactions on Antennas and Propagation. Dr. Kunkee is Vice-Chair of USNC-URSI Commission F and has served on the U.S. National Academies’ Committee on Radio Frequencies (CORF) including its Committee on Scientific Use of the Radio Spectrum.

Lecture II: NASA-ISRO SAR Mission (NISAR)

Lecturer:

Marco Lavalle, Scientist and Group Supervisor, NASA Jet Propulsion Laboratory

Marco Lavalle received the M.Sc. degree in Telecommunication Engineering from the University of Rome Tor Vergata (Rome, Italy) in 2006, and the Ph.D. degree from the University of Rennes 1 (Rennes, France) and from the University of Rome Tor Vergata (Rome, Italy) in December 2009. From 2006 to 2008, he was Visiting Scientist at the European Space Agency (ESRIN) where he supported ESA’s activities on polarimetric radar calibration and polarimetric radar interferometric algorithm development. From January 2010 to December 2011, he was NASA Postdoctoral Fellow at the Jet Propulsion Laboratory (JPL), California Institute of Technology. He has been permanent scientist in the Radar Science and Engineering Section at JPL since January 2012. He has been Principal Investigator and co-Investigator for several NASA programs. He is the lead for the 2020 NASA Distributed Aperture Radar Tomographic Sensors (DARTS) project, and member of the ESA ROSE-L, NISAR and UAVSAR Project Science Teams. He is currently Group Supervisor for the SAR Algorithms and Processing Group at JPL. His research interests include retrieval algorithm development, physical and statistical model formulation, electromagnetic propagation, scattering theory, SAR tomography, polarimetric SAR interferometry, ecosystem modeling and surface parameter estimation. Dr. Lavalle is the recipient of the 2019 NASA Early Career Public Achievement Medal, the 2020 JPL Lew Allen Award for Excellence, and the Student Prize Paper Award at the EUSAR 2008 Conference (Friedrichshafen, Germany).

Lecture III: Small Satellite Science and Applications

Lecturer:

Charles D. Norton, Deputy Chief Technologist, NASA Jet Propulsion Laboratory

Charles D. Norton is the Deputy Chief Technologist at NASA JPL/Caltech responsible for JPL’s technology strategic planning, research, and infusion into flight missions. Across his career he has led and performed research spanning high-performance computing, advanced information systems technology, and small satellite science and technology mission development. He has developed and managed multiple CubeSat flight projects for NASA and has co-authored numerous National Academies reports on remote sensing with small satellites. Charles is a recipient of numerous awards for new technology and innovation, including the JPL Lew Allen Award, NASA Exceptional Service Medal, and the NASA Outstanding Public Leadership Medal. He holds a B.S.E. in electrical engineering and computer science from Princeton University and an M.S and Ph.D. in computer science from Rensselaer.

GRSS