GSW

Tutorials

At ISPRS GSW 2025, we are excited to offer four tutorials carefully crafted to align with the conference theme, “Photogrammetry and Remote Sensing for a Better Tomorrow.” These tutorials will take place on Sunday, April 6th, 2025, providing a dedicated day for in-depth learning and skill development. Each tutorial will run for 3 hours, divided into two 1.5-hour sessions with a 30-minute break in between.

The tutorials will cover topics spanning photogrammetry, remote sensing, spatial sciences, and related technologies, ensuring participants gain a well-rounded understanding of the field. Designed to address recent advancements, methodologies, tools, and practical applications, these sessions will equip attendees with the knowledge needed to tackle current challenges and innovate for the future. Whether you are a researcher, practitioner, or student, these tutorials promise an engaging and enriching learning experience.

Agenda

Download Agenda
For more information about tutorials:
UAV‐based mapping with imaging and LiDAR systems: challenges, data processing, and applications

6th April 2025 | 09:00 – 12:30 | Hall A

Presented By: Ayman F. Habib, Thomas A. Page Professor in Civil Engineering, Lyles School of Civil and Construction Engineering, Purdue University, USA

Overview: The continuous developments in direct geo-referencing technology (i.e., integrated Global Navigation Satellite Systems – GNSS – and Inertial Navigation Systems – INS) and remote sensing systems (i.e., passive and active imaging sensors in the visible and infrared range – RGB cameras, hyperspectral push-broom scanners, and laser scanning) are providing the professional geospatial community with ever-growing opportunities to generate accurate 3D information with rich set of attributes. These advances are also coupled with improvement in the sensors’ performance, reduction in the associated cost, and miniaturization of such sensors. Aside from the sensing systems, we are also enjoying the emerging of promising platforms such as Uncrewed Aerial Vehicles (UAVs). The tutorial will involve two practical exercises. The first one deals with the interpretation of a quality report derived from a generic Structure from Motion (SfM) for a block of UAV images. The second exercise will deal with the inspection of point cloud data to infer the presence of random and systematic errors.

Objectives and Learning Outcomes: This tutorial will provide an overview of recent activities focusing on UAV-based mapping while highlighting:

  1. Algorithmic developments for improved system calibration of multi-sensor/multi-platform UAV-based mapping;
  2. Challenges facing UAV-based Structure-from-Motion strategies for deriving point clouds from imagery;
  3. Benefits of integrating imaging and LiDAR systems onboard UAVs;
  4. Applications of UAV-based remote sensing systems for a wide range of applications including precision agriculture, documentation of crash scenes, shoreline monitoring, digital forestry, and mapping of highway construction work zones;
  5. Interactive visualization of multisensor/ multi-platform/temporal geospatial data for improved comprehension of delivered products from UAV-based mobile mapping systems.

Target audience and prerequisites: The tutorial is targeted for researchers and practitioners interested in using uncrewed aerial vehicles for near proximal sensing using directly georeferenced imagery and/or LiDAR data for cost-effective mapping to address the needs of various applications (e.g., transportation, agriculture, forestry, public safety, and infrastructure monitoring). The basic principles of photogrammetric and LiDAR mapping will be covered. The audience should have some background in using geospatial data and products from imaging and ranging systems.

Technical requirements (software, hardware, etc.): Trial version of PIX4Dmapper for the first practical exercise and CloudCompare for the second one. A laptop with reasonable processing power will be sufficient. Wireless or wired internet connection is required.

Brief biography of the instructor: Dr. Habib is the Thomas A. Page professor of Civil and Construction Engineering at Purdue University and the Co-Director of the Civil Engineering Center for Applications of UAS for a Sustainable Environment (CE-CAUSE). He is also the Associate Director of Purdue University’s Joint Transportation Research Program (JTRP) and Institute of Digital Forestry (iDiF). His research interests span the fields of terrestrial and aerial mobile mapping systems. Over the last ten years, he has been involved in the development, integration, and utilization of wheel-based and UAV-based mobile mapping systems for a wide range of applications in precision agriculture, geometric documentation of transportation corridors, digital forestry, crash scene reconstruction, cultural heritage documentation, environmental management, and infrastructure monitoring.

Urban monitoring and analysis with remote sensing and spatial information technology

6th April 2025 | 09:00 – 12:30 | Hall B

Presented By: Prof. Maria Antonia Brovelli, Politecnico di Milano, Italy Prof. Jiang Jie, Beijing University of Civil Engineering and Architecture, China

Overview: This tutorial provides a hands-on approach to urban monitoring and analysis using remote sensing and spatial information technology. Participants will explore key concepts like urban heat islands, local climate zones, urban air quality, and spatial patterns. Through guided exercises and case studies attendees will learn practical techniques for urban data extraction, classification, and spatial analysis. The session is ideal for those with GIS skills, basic programming knowledge, and an active Google Earth Engine account.

Objectives and Learning Outcomes : The tutorial will focus on urban monitoring and analysis with remote sensing and spatial information technology, providing participants with a comprehensive understanding of the subject matter, including recent advancements, methodologies, tools, and practical applications. Attendees will learn about the urban heat island effect and the local climate zone classification system. They will learn how to conduct a local climate zone classification for urban environments. The tutorial will last 3 hours. A 10-minute brief introduction will be given at the beginning. Then four lectures will be arranged, each lasting about 30 minutes, and 10 minutes will be left for Q&A.

  • Urban information extraction from images (30 minutes + Q&A):
    Introduction to necessity and problem of urban information extraction, especially for urban infrastructure. The basic principles, technical methods, and application practices of urban information extraction are introduced using optical remote sensing and microwave remote sensing. Moreover, a High-speed videogramemtry is also introduced to obtain the 3D spatial information of infrastructure model for shaking table experiment.
  • Urban heat island and LCZ mapping (30 minutes + Q&A): Introduction to the urban heat island phenomenon and its impact on cities; overview of the local climate zone (LCZ) classification system and its real-world applications; presentation of data and methods used in LCZ mapping. A hands-on exercise is foreseen using data from Milan, Italy: participants will work with a Landsat 8 multispectral image and additional urban morphology data; they will learn to digitize training and testing samples, apply a classification algorithm, and assess the accuracy of the LCZ map; the result will be compared to air temperature data from local monitoring stations.
  • Air pollution (30 minutes + Q&A)：A general introduction to the problem of urban air quality and its analysis using remotely sensed data. We will introduce thematic satellite missions and explore data repositories for accessing and distributing their data through web platforms and APIs. An introduction to Copernicus services will also be provided, along with an overview of Sentinel-5P products. Hands-on examples of geospatial processing pipelines will be presented, focusing on tasks such as data collection, preprocessing and validation for air quality assessments, with a case study centered on Milan, Italy.
  • Analysis of urban spatial pattern (30 minutes + Q&A)：Introduction to urban spatial structure and methods for identifying urban spatial forms. A case study on the spatial evolution of a major metropolitan area. A hands-on exercise will engage participants in spatial pattern analysis using QGIS or Python, where they will apply spatial indices to assess the compactness, density, and connectivity of urban areas. The session will also include the use of urban sensing data and point-of-interest (POI) data to enhance understanding of urban function zones.

Target audience and prerequisites: Good GIS skills, and a basic understanding of remote sensing, image processing, and classification techniques. Basic programming skills (Python, JavaScript). Activated Google Earth Engine account.

Technical requirements (software, hardware, etc.): Projector, computer, microphone, laser pointer, and other essentials to have QGIS (long term release) installed to carry out the practical part.

Brief introduction of instructors:

  • Prof. Maria Antonia Brovelli, Politecnico di Milano (POLIMI), Italy, Moderator

    Maria Antonia Brovelli holds a Ph.D. in Geodesy and Cartography and serves as a Professor of GIS and The Copernicus Green Revolution for Sustainable Development at Politecnico di Milano (PoliMI). With a career spanning from researcher to Full Professor and Vice-Rector for the Como Campus at PoliMI, she also lectures at ETH Zurich and holds prominent roles in international organizations. As Vice President of the ISPRS Technical Commission on Spatial Information Science, co-chair of the United Nations Open GIS Initiative, chair of the UN-GGIM Academic Network, and curator of the GEO series at AI For Good Summit, she influences global spatial information science. Brovelli’s extensive publication record and involvement in national and European projects have earned her prestigious awards and editorial roles, highlighting her significant contributions and leadership in the field.

  • Prof. JIANG Jie, Beijing University of Civil Engineering and Architecture (BUCEA), China, Moderator

    Prof. Dr. JIANG Jie received her BSc. and MSc. degrees in Applied Geophysics from the Changchun University of Geology, China, and PhD in Surveying Engineering from China University of Mining and Technology (Beijing). She worked as a remote sensing and GIS specialist in National Geomatics Center of China. Since October 2018, she serves as full professor in School of Geomatics and Urban Spatial Informatics, BUCEA. Her recent research focuses on spatial-temporal modelling for smart city. She is now ISPRS Fellow, and the Secretary General of ISPRS (for term 2022-2026).

  • Alberto Vavassori (POLIMI), Instructor of Urban heat island and LCZ mapping
    Alberto Vavassori obtained his MSc degree with honours in Environmental and Land Planning Engineering in 2019 at Politecnico di Milano. From 2020 to 2021 he was a temporary research fellow at the GEOlab (the Geomatics and Earth Observation lab) of Politecnico di Milano. From 2021, he has been a PhD student in Environmental and Infrastructure Engineering at Politecnico di Milano. His research mainly focuses on urban climatology, crisis mapping, and environmental monitoring using free and open-source software. His research interests include data science, GIS, remote sensing and Earth Observation.
  • Vasil Yordanov (POLIMI), Instructor of Air pollution
    Following his MSc in Civil Engineering for Risk Mitigation he joined Politecnico di Milano’s GEOlab in 2019 as a research fellow in the domain of geospatial applications for environmental studies. In 2022 he obtained his PhD in National Security. His work has centered on applying GIS, remote sensing, and machine learning for environmental research. His areas of expertise include hazard assessment, environmental monitoring, and capacity-building initiatives for climate change resilience.
  • LIU Xianglei (BUCEA), Instructor of Urban information extraction from images
    He received his B.S. and M.S. degree in Geographic Information System from Shandong University of Science and Technology in 2005 and 2008, respectively. He received the Ph.D. degree in Photogrammetry and Remote Sensing from Tongji University in 2012. He is now the dean/professor of the school of Geomatics and Urban Spatial Informatics in Beijing University of Civil Engineering and Architecture. His research interests are deformation monitoring based on GBSAR, high-speed videogrammetric measurement and multi-modal data fusing for disaster monitoring.
  • GUO Xian (BUCEA) , Instructor of Analysis of urban spatial patterns
    Received his B.S. degree in Surveying and Mapping from Central South University, China, in 2010, and Ph.D. in Photogrammetry and Remote Sensing from Wuhan University, China, in 2015. He is a Lecturer at the School of Geomatics and Urban Spatial Informatics, BUCEA. His research interests focus on urban remote sensing, high-resolution image processing, and digital twin modeling. He serves as the Co-Chair of ISPRS Working Group V/2 for the 2022-2026 term.
Mastering Supervised Land Use Land Cover (LULC) Classification with Google Earth Engine: A Step-by-Step Guide Using JavaScript API
6th April 2025 | 13:30 – 17:00 | Hall A
 
Presented By: Rifaat Abdalla, Eltaib Saeed Ganawa , Mohammed Mahmoud Musa , Anwarelsadat Eltayeb Elmahal

Overview: Google Earth Engine (GEE) is a powerful cloud-based platform designed for geospatial processing, providing unmatched capabilities for analyzing and visualizing vast amounts of satellite imagery and spatial data. Its ability to process data at scale makes it an essential tool for Land Use and Land Cover (LULC) classification, a critical task for accurately mapping land types and supporting informed decision-making in fields such as urban planning, resource management, and environmental conservation.

In this tutorial, participants will explore GEE’s JavaScript interface (GEE JS) to conduct supervised LULCC, showcasing its analytical strength in spatial analysis. Through a hands-on exercise, participants will not only gain practical experience but also enhance their understanding of key concepts in remote sensing, spatial analysis, and cloud computing. By working with real-world examples, they will learn to apply these skills effectively in diverse contexts.

Objectives and Learning Outcomes: By the end of this tutorial, participants will:

  • Understand the principles of supervised classification in remote sensing, including the theoretical foundations and real-world applications.
  • Gain practical experience in using Google Earth Engine JavaScript (GEE JS) to import, process, and visualize satellite imagery for geospatial analysis.
  • Apply machine learning algorithms for training, validating, and refining Land Use and Land Cover (LULC) classifications within GEE.
  • Create thematic maps to represent various land cover types and learn how to export results for use in additional analyses or reports.

The tutorials’ outlines are listed below:

     1.  Introduction to Google Earth Engine (GEE)

  • Overview of GEE and its capabilities.
  • Introduction to the JavaScript code editor.
  • Accessing and managing Earth Engine assets.

     2. Accessing and preparing Satellite Imagery

  • Importing Landsat and Sentinel-2 imagery into GEE.
  • Preprocessing steps: cloud masking, region of interest (ROI) definition, and image composite creation.

     3.  Working with Training Data

  • Selecting land cover classes (e.g., water, vegetation, urban, barren land).
  • Creating regions of interest (ROI) for each land cover type using GEE’s interactive map.
  • Importing external shapefiles or creating custom polygons for training samples.

     4.  Supervised Classification Algorithms

  • Overview of supervised classification methods (e.g., Random Forest, SVM, CART).
  • Training the classifier with labeled data.
  • Classifying the image based on the trained model.

     5.  Validating and Evaluating the Classification

  • Splitting data into training and validation sets.
  • Accuracy assessment using confusion matrix and other statistical metrics.

     6. Visualizing and Exporting Results

  • Displaying the classified LULC map in GEE.
  • Exporting results to Google Drive or Earth Engine Asset for further use.

     7. Case Study: LULC Classification of a Specific Region

  • Application of the learned techniques to a real-world case study (e.g., a selected area in Sudan or another region).
  • Comparison of classification results with known data.

     8. Q&A and Troubleshooting

  • Application of the learned techniques to a real-world case study (e.g., a selected area in Sudan or another region).
  • Comparison of classification results with known data.

Target audience and prerequisites: This tutorial is ideal for environmental scientists, practitioners, and researchers involved in Land Use and Land Cover (LULC) analysis, as well as students and professionals in GIS, remote sensing, data science, and spatial data analysis. It is also suitable for those with basic programming skills who wish to expand their knowledge of Google Earth Engine (GEE) and LULC classification techniques. Participants should have a Google Earth Engine account, a foundational understanding of remote sensing and geographic information systems (GIS), and familiarity with basic programming skills

Technical requirements (software, hardware, etc.): Participants need an activated Google Earth Engine (GEE) account, a stable internet connection, a modern web browser, and a computer with 8 GB RAM. Basic programming skills and access to external GIS data files are also recommended.

Brief biography of the instructor:

Dr. Rifaat Abdalla is a faculty member in the Department of Earth Sciences at the College of Science, Sultan Qaboos University. With expertise in geospatial science and environmental analysis, Dr. Abdalla has contributed extensively to research in Earth sciences, specializing in remote sensing and land use classification.

Dr. Eltaib Saeed Ganawa is a professor at the Faculty of Geographical and Environmental Sciences at the University of Khartoum, Sudan. Dr. Ganawa’s work focuses on GIS, spatial data analysis, and environmental management, with a strong background in integrating geospatial technology into environmental research.

Dr. Mohammed Mahmoud Musa is a member of the Faculty of Computer Science and Information Technology at Alzaiem Alazhari University, Sudan. His research spans GIS applications, data processing, and remote sensing, applying computational techniques to environmental and geographical studies.

Dr. Anwarelsadat Eltayeb Elmahal also serves at the Faculty of Geographical and Environmental Sciences, University of Khartoum. With a background in geospatial analysis, Dr. Elmahal specializes in environmental assessment and spatial data applications, contributing valuable insights into regional land use and environmental policy.

 
Using LLMs for U nderstanding and Developing Surface Motion Estimation Methods with SAR
6th April 2025 | 13:30 – 17:00 | Hall B
 
Presented By: Prof. Timo Balz, Assoc. Prof. Bahaa Mohamadi

Overview: In this course, different methods for using SAR systems for surface motion estimation are introduced. Students will learn how to develop code for using these methods further by using large language models (LLM). It is designed for graduate students in Geographic Information Sciences and Remote Sensing. The course includes the following topics:

  1. Introduction SAR remote sensing
  2. SAR image processing
  3. Introduction into differential SAR interferometry
  4. PSInSAR processing chain

Objectives and Learning Outcomes:

  • Develop foundational and advanced knowledge in SAR remote sensing techniques through an Introduction to SAR Remote Sensing module.
  • Gain an in-depth understanding of Differential SAR Interferometry (D-InSAR) and Permanent Scatterer Interferometry (PSInSAR).
  • Learn to utilize Large Language Models (LLMs) and prompt engineering techniques for SAR-related code development, with practical exercises in Using LLMs for Basic InSAR Processing Development.
  • Acquire hands-on experience in PSInSAR processing, with guidance on building Python code for advanced SAR applications.
  • Establish a base for further development of SAR processing techniques through Advanced PSInSAR Processing with LLMs.

Target Audience and Prerequisites: This course is designed for graduate students in Geographic Information Sciences, Remote Sensing, or related fields who have a foundational understanding of SAR remote sensing and image processing. Participants should be comfortable with Python programming, as coding for SAR methods is a core component of the course. Prior exposure to differential SAR interferometry (D-InSAR) and Permanent Scatterer Interferometry (PSInSAR) is helpful but not required. An interest in using large language models (LLMs) for coding support and processing chain development will also be beneficial.

Technical requirements (software, hardware, etc.): Participants need a stable internet connection, a modern web browser (preferably Chrome or Firefox), and a computer with at least 8 GB of RAM. Python programming environment set up is also required for hands-on coding exercises.

Brief introduction of instructors:

Prof. Timo Balz is an expert in remote sensing and Geographic Information Sciences, with a focus on synthetic aperture radar (SAR) technology for environmental monitoring and surface motion estimation. He has published extensively and contributed to significant research projects in advanced remote sensing methodologies.

Assoc. Prof. Bahaa Mohamadi specializes in remote sensing and geospatial analysis, particularly in differential SAR interferometry (D-InSAR). He is known for developing innovative techniques for analyzing SAR data and integrating machine learning into remote sensing research, with numerous publications and collaborative contributions to the field.