Schedule: 22 November 2026 | 9:00 AM-1:00 PM

As part of the World Landslide Forum 7 (WLF7), this short course introduces participants to the principles, methods, and tools of Multi-Hazard Risk Assessment (MHRA), with a particular focus on landslide risk within multi-hazard environments and its applications in disaster risk reduction, climate adaptation, and resilience planning. This course is intended for researchers, disaster risk reduction professionals, GIS and remote sensing specialists, engineers, and students interested in understanding and managing risks arising from multiple interacting hazards.

Lead Instructors

Key Topics

1. Foundations of Multi-Hazard Risk Assessment
   • Multi-hazard concepts, terminology, and risk assessment frameworks
   • Hazards, exposure, vulnerability, loss, and damage
   • Impact chains, hazard interactions, and cascading effects
2. Data for Multi-Hazard Assessment
   • Data sources for hazard and risk analysis, including disaster databases and landslide inventories
   • Remote sensing and Earth observation applications
   • Data quality assessment, suitability analysis, and AI-based approaches for multi-hazard assessment
3. Exposure and Vulnerability Assessment
   • Asset classification, building characteristics, and exposure analysis
   • Population datasets and dynamic exposure mapping
   • Physical and indicator-based vulnerability assessment methods
   • Spatial Multi-Criteria Evaluation (SMCE) for risk analysis
4. Risk Assessment Approaches
   • Qualitative and quantitative risk assessment methodologies
   • INFORM Risk framework and other decision-support approaches
   • Project development – making a risk assessment for your own region
5. Practical Tools and Applications
   • Fast Flood and Fast Landslide modeling applications
   • RiskChanges Multi-Hazard Risk Assessment Platform
   • Online geospatial tools for hazard and risk analysis

Schedule: 22 November 2026 | 4:00 PM-5:30 PM

As part of the 7th World Landslide Forum (WLF7), this workshop provides a comprehensive introduction to the concepts, methodologies, and practical applications of landslide risk assessment. Reliable landslide risk assessment is fundamental for developing effective risk management, mitigation, preparedness, and adaptation strategies, particularly in areas where landslides threaten communities, infrastructure, cultural heritage, and economic activities.

This workshop is intended for researchers, practitioners, civil protection officers, planners, students, engineers, and decision-makers interested in understanding, assessing, and reducing landslide risk.

Lead Instructors

Key Topics

1. Foundations of Landslide Risk Assessment
   • Definitions and concepts of landslide risk & assessment frameworks
   • Hazard, exposure, vulnerability, and consequences
   • Current challenges and uncertainties in risk estimation
2. Data Requirements for Risk Assessment
   • Landslide inventories and event databases
   • Geomorphological and geological information
   • Triggering factors and susceptibility data
   • Population and infrastructure exposure datasets
   • Vulnerability information and historical damage records
3. Risk Assessment Methodologies
   • Geomorphological approaches
   • Statistical & probabilistic approaches
   • Individual and societal risk estimation
4. Risk Communication and Decision Support
   • Landslide risk perception
   • Communication of risk information
   • Supporting land-use planning and policy development
   • Emergency preparedness and civil protection applications
   • Long-term mitigation and adaptation strategies
5. Case Studies and Applications
   • Local and site-specific landslide risk assessments
   • Regional and national-scale assessments
   • Population exposure analysis
   • Applications from Italy and other international contexts

Schedule: 22 November 2026 | 9:00 AM-1:00 PM

As part of the 7th World Landslide Forum (WLF7), this workshop explores the opportunities, limitations, and future directions of satellite Synthetic Aperture Radar (SAR) and Interferometric SAR (InSAR) technologies for landslide detection and monitoring. Building on the success of the Sentinel-1 mission and the emergence of next-generation systems such as NISAR, the workshop will examine when radar-based monitoring works effectively, where its limitations lie, and how it can be integrated with optical imagery, LiDAR, and GNSS observations. Through practical examples and expert discussion, participants will gain insights into the evolving role of Earth observation technologies in landslide risk assessment, civil protection, and early warning applications.

Lead Instructor

Key Topics

1. Fundamentals of SAR and InSAR
   • Principles of Synthetic Aperture Radar (SAR)
   • Interferometric SAR (InSAR) techniques
   • Applications in landslide detection and monitoring
   • Factors affecting measurement accuracy
2. Sentinel-1 and a Decade of Systematic Monitoring
   • The impact of the Copernicus Sentinel-1 mission
   • Global monitoring capabilities
   • Advances enabled by open-access radar data
   • Lessons learned from operational applications
3. Understanding the Limitations
   • Vegetation effects and temporal decorrelation
   • Atmospheric disturbances and noise
   • Slope geometry constraints
   • Monitoring fast-moving landslides
   • Examples of successful and unsuccessful applications
4. Comparing Radar Frequency Bands
   • C-band, L-band, and X-band systems
   • Strengths, weaknesses, and complementary capabilities
   • Selecting appropriate systems for different landslide environments
5. Multi-Source Monitoring Approaches
   • Integration with optical remote sensing
   • LiDAR applications for terrain analysis
   • GNSS-based deformation monitoring
6. From Research to Operations
   • Operational landslide monitoring frameworks
   • Civil protection applications and Early warning systems
   • Challenges in implementing large-scale monitoring programs
7. NISAR and Future Perspectives
   • Overview of the NISAR mission
   • Expected advances in landslide monitoring
   • Remaining scientific and operational challenges
   • Future directions for satellite-based hazard assessment

Schedule: 25 November 2026 | 2:30 PM-6:00 PM

This half-day workshop introduces the concepts and practical methods for developing hydrometeorological thresholds for regional Landslide Early Warning Systems (LEWS). Participants will learn how to design a regional LEWS using available data through a combination of conceptual discussions and hands-on exercises.

The workshop begins by introducing the various regional landslide hazard assessment methods and explaining their conceptual foundations. It then discusses landslide databases and the challenges associated with developing reliable thresholds. Participants will work with rainfall time series and potential hydrological variables that are informative for hydrometeorological threshold development. These datasets will be used to derive different threshold approaches, followed by discussions on their strengths and limitations. Special attention will be given to the transient changes in thresholds resulting from land-use and climate change.

After the workshop and throughout the conference, participants will have the opportunity to discuss their own datasets and regional LEWS threshold challenges with the instructor.

Lead Instructor

Key Topics

Regional Landslide Hazard Assessment

• Regional landslide hazard assessment methods
• Conceptual foundations of hazard assessment

Landslide Databases

• Landslide databases
• Challenges associated with landslide databases

Hydrometeorological Threshold Development

• Preparing rainfall time series
• Hydrological variables informative for threshold development
• Deriving hydrometeorological thresholds
• Strengths and limitations of different threshold approaches

Climate Change and Land Use

• Transient changes in thresholds due to land-use change
• Transient changes in thresholds due to climate change

Hands-on Exercises

• Preparing rainfall time series
• Developing hydrometeorological thresholds using training datasets
• Discussion of participant datasets and regional LEWS threshold issues

Workshop Resources

A small training dataset and an ample set of key literature will be made available to all participants.

Schedule: 22 November 2026 | 9:00 AM-5:30 PM

Lead Instructors

Schedule: 22 November 2026 | 2:00 PM-5:30 PM

As part of the World Landslide Forum 7 (WLF7), this short course introduces participants to the principles, methodologies, and practical applications of satellite-based deformation monitoring and artificial intelligence (AI) for detecting, monitoring, and forecasting slow-moving landslides. The workshop focuses on integrating Interferometric Synthetic Aperture Radar (InSAR) observations with machine learning approaches to support landslide hazard assessment, early warning systems, infrastructure management, and risk-informed decision-making.

Slow-moving landslides often remain active for months or years following triggering events such as earthquakes and extreme rainfall, posing long-term threats to communities, transportation networks, critical infrastructure, and economic activities. Recent advances in satellite remote sensing have significantly enhanced our ability to measure ground deformation with millimeter-scale precision over large areas, while developments in AI have created new opportunities to forecast future slope behavior from large deformation datasets.

This course is intended for researchers, geohazard specialists, disaster risk reduction professionals, engineers, GIS and remote sensing practitioners, government agencies, infrastructure managers, and students interested in operational landslide monitoring and forecasting.

Lead Instructor

Key Topics

Fundamentals of Landslide Deformation Monitoring

• Mechanisms and evolution of slow-moving landslides
• Factors controlling slope instability and long-term deformation
• Earthquake- and rainfall-induced slope movements
• Monitoring requirements for hazard assessment and early warning

InSAR for Landslide Detection and Monitoring

• Principles of Interferometric Synthetic Aperture Radar (InSAR)
• Satellite missions and deformation monitoring capabilities
• Mapping active landslides using Sentinel-1 observations
• Generation and interpretation of deformation maps
• Applications in post-earthquake and rainfall-triggered landslide environments
• Limitations, uncertainties, and operational considerations

Deformation Time-Series Analysis

• Extraction and interpretation of displacement time series
• Identification of deformation trends and acceleration phases
• Detection of precursory signals and instability indicators
• Integration of environmental and geospatial datasets

Artificial Intelligence for Landslide Forecasting

• Introduction to machine learning and data-driven forecasting approaches
• Feature engineering and preparation of deformation datasets
• Forecasting future landslide behavior using historical displacement records
• Model validation, performance assessment, and uncertainty analysis
• Operational implementation of forecasting models

Landslide Early Warning and Risk Management Applications

• Integration of monitoring and forecasting systems
• Decision-support frameworks for landslide risk reduction
• Applications for infrastructure management and asset protection
• Emergency response planning and operational early warning systems
• Opportunities and challenges for operational deployment

Practical Exercises and Workflows

• Accessing and visualizing InSAR-derived deformation products
• Identification and mapping of active slow-moving landslides
• Processing displacement time-series datasets
• Preparing datasets for machine learning applications
• Developing and evaluating forecasting workflows
• Reproducible and scalable operational workflows

Learning Outcomes

By the end of the course, participants will:

• Understand the principles and applications of InSAR for landslide monitoring.
• Be able to identify and characterize slow-moving landslides using satellite-derived deformation data.
• Gain practical experience in extracting and interpreting displacement time series.
• Understand the fundamentals of AI-based deformation forecasting.
• Develop and evaluate forecasting workflows using real-world datasets.
• Understand opportunities, limitations, and uncertainties associated with operational forecasting systems.
• Learn how monitoring and forecasting outputs can support landslide early warning systems and risk management.

Schedule: 22 November 2026 | 9:00 AM-1:00 PM

Reliable prediction of rainfall-induced landslides requires two fundamental components: high-quality hydrometeorological data and systematic records of landslide occurrence. In many regions of the world, particularly in developing and data-scarce environments, limitations in monitoring infrastructure create significant challenges for landslide forecasting and early warning.

This workshop explores how satellite-derived rainfall and soil moisture products, landslide catalogs compiled from documentary sources, and modern digital twin technologies can be integrated to improve landslide prediction and risk assessment. Participants will gain insight into the scientific foundations of rainfall threshold modeling, the opportunities and limitations of satellite observations, and emerging approaches for building geospatial digital twins that support next-generation landslide early warning systems.

The workshop combines lectures, international case studies, and guided discussions to provide participants with both conceptual understanding and practical perspectives on operational landslide forecasting.

Lead Instructor

Key Topics

• Building landslide inventories from historical records, news archives, technical reports, and citizen science sources.
• Understanding reporting biases, data quality, and completeness in landslide catalogs.
• Satellite rainfall and soil moisture products for landslide applications.
• Strengths, limitations, validation approaches, and bias correction techniques.
• Rainfall threshold methodologies, including intensity-duration, cumulative rainfall, and antecedent rainfall approaches.
• Statistical approaches for threshold calibration and validation, including frequentist, Bayesian, and machine-learning methods.
• Integration of thresholds into operational early warning systems.
• Geospatial Digital Twins for landslide risk assessment, scenario analysis, and real-time decision support.

Learning Outcomes

Participants will be able to:

• Evaluate the suitability of satellite-derived hydrometeorological datasets for landslide forecasting.
• Understand how landslide occurrence databases are developed and used to calibrate thresholds.
• Describe major approaches for defining and validating rainfall thresholds.
• Identify uncertainties and research gaps in landslide prediction systems.
• Understand the emerging role of digital twin technologies in landslide hazard and risk management.

Interactive Component

A guided case study will demonstrate the complete workflow from assembling a landslide inventory and selecting satellite rainfall datasets to deriving and interpreting a rainfall threshold. The exercise is discussion-based and does not require participants to bring computers, ensuring accessibility for attendees from diverse backgrounds.

Who Should Attend?

The workshop is designed for MSc, PhD, and postdoctoral researchers, as well as professionals from geological surveys, civil protection agencies, disaster management authorities, and other organizations involved in landslide monitoring, forecasting, and risk reduction.

No advanced expertise in remote sensing or statistical modeling is required; a basic understanding of landslide processes and GIS concepts is recommended.

Schedule: 22 November 2026 | 2:00 PM-5:30 PM

Schedule: 22 November 2026 | 2:00 PM-5:30 PM

Lead Instructor

This workshop is largely inspired by the material presented in “Modelling Mass Movements and Landslide Susceptibility”, a chapter in the volume “Geomorphometry: Concepts, Software, Applications”, second edition. As landslide susceptibility and runout models use geomorphometric information to support disaster risk management, we outline selected state-of-the-art workflows in data-driven and process-based modeling, focusing on open-source implementations of slope unit delineation with the r.slopeunits toolset, generalized additive models (GAM) for statistically-based landslide susceptibility, and the 3D rockfall model r.stone. We illustrate the typical implementation in GRASS GIS of such methods, with minimal scripts covering the full modeling chain from data import, pre-processing, model run and analysis of the results.

We use case studies to illustrate the application of statistical susceptibility models operating on slope units and grid cells; specifically, we show the difference in susceptibility maps obtained within a generalized linear model and a generalized additive model, both in a grid-based and a slope unit-based approach. Next, we show applications of process-based, or physically-based models, featuring dynamic runout simulations incorporating interactions with runoff.

The processing chain is implemented in a Linux-like OS, (including emulators, e.g., the Windows Subsystem for Linux, WSL). We give minimal instructions on the installation of GRASS GIS in Ubuntu Linux and all subsequent operations are mostly illustrated as a combination of bash and R scripts, GRASS GIS modules. Prerequisites are close to none, but willingness to work in a Linux-like OS is a must.

• ⁠ The generalized additive model page on CRAN https://cran.r-project.org/package=gam.
• ⁠ A machine learning workflow for landslide susceptibility modelling including spatial cross-validation, https://r.geocompx.org/spatialcv.html.
• ⁠The r.learn.ml2 toolset for supervised classification/regression with the Python scikitlearn package in GRASS GIS, https://grass.osgeo.org/grass-stable/manuals/addons/r.learn.ml2.html.
• ⁠ ⁠The r.slopeunits toolset to delineate and optimize slope units in GRASS GIS: https://grass.osgeo.org/grassstable/manuals/addons/r.slopeunits.html.
• ⁠ ⁠The r.stone module to simulate rockfall trajectories in GRASS GIS: https://grass.osgeo.org/grass-stable/manuals/addons/r.stone.html

Schedule: 22 November 2026 | 9:00 AM-1:00 PM

Lead Instructor

Resource Persons

Learning Outcomes

By the end of this workshop, participants will be able to:

• Explain the significance of addressing mental health in the context of disaster preparedness and response.
• Illustrate examples of potential solutions to addressing mental health in both pre- and post-disaster contexts.
• Identify context-appropriate strategies for integrating mental health into disaster planning at the community level.

Summary of Workshop

This workshop will focus on mental health preparedness for natural disasters, and about the importance of addressing trauma and mental health outcomes among exposed population. Pre and post workshop survey will be conducted to collect evaluation feedback from the participants.

Workshop Format

The workshop will be in-person. All participants will be expected to attend in-person. We will use participatory methods to disseminate information. We will also use audio-visual aids. Participants are not expected to have access to any materials beforehand. All materials will be provided by the workshop organizers at the beginning of the workshop.

Schedule: 22 November 2026 | 2:00 PM-5:30 PM

As part of the 7th World Landslide Forum (WLF7), this 3.5-hour workshop explores how Earth observation and geospatial AI can strengthen disaster assessment, monitoring and response. It brings together optical, Synthetic Aperture Radar (SAR), hyperspectral imagery and GeoAI to show how different forms of geospatial information can move from observation to actionable insight.

Through focused technical sessions and live demonstrations, participants will examine optical imagery for flood, wildfire, earthquake damage and change detection; all-weather monitoring using SAR, including Sentinel-1, NISAR and interferometric approaches; hyperspectral analysis for environmental and urban insights; and GeoAI workflows using pretrained models, AI agents, embeddings and MCP. Demonstrations will include vision-language-model-based damage assessment, post-disaster route accessibility, flood simulation and AI-enabled mobile damage surveys.

Lead Instructors

Key Topics

• By the end of this workshop, participants will be abOptical imagery for disaster assessment: flood and inundation mapping; wildfire and burn-scar assessment; tropical cyclone impacts; post-disaster change detection; challenges, limitations and future opportunities.
• All-weather monitoring through SAR: the role of SAR in disaster management; Sentinel-1 and NISAR; SAR processing and intensity analysis; SAR interferometry; advanced time-series Interferometric SAR.
• Hyperspectral imagery for disaster insights: spectral signatures; PRISMA and ENVI-based tree species classification; urban material mapping and ward-level urban heat island analysis.
• Geospatial AI for disaster: GeoAI fundamentals; pretrained models, model development and inferencing; AI agents, embeddings and MCP.
• Use cases and demonstrations: damage assessment using Vision Language Models; accessible routes after disasters; flood simulation; rapid damage surveys with AI-enabled mobile applications.

Learning Outcomes

• Understand how optical, SAR and hyperspectral imagery can support different stages of disaster monitoring and assessment.
• Recognize the role of Sentinel-1, NISAR, InSAR and time-series analysis in all-weather monitoring.
• Understand core GeoAI concepts and how AI-enabled geospatial workflows can support disaster response.
• See practical examples of damage assessment, route accessibility, flood simulation and mobile field surveys.

Who Should Attend

Disaster management professionals, researchers, GIS and remote sensing practitioners, engineers, planners and students interested in applying Earth observation and GeoAI to disaster monitoring and response.