The geospatial landscape has experienced a significant transformation, with the volume of geolocated data expanding rapidly. However, data quality can vary widely. Key aspects such as accuracy, completeness, and consistency are critical for minimising errors and maximising the value of spatial data across various applications. For national mapping and cadastral agencies, maintaining high standards of spatial data quality is crucial for ensuring the dependability of the information used. To gain better insights into spatial data quality, EuroGeographics Quality KEN and EuroSDR organise a course that is dedicated to this topic. We will explore different data quality elements and methods, look into visualisation challenges, and explore innovative technologies to determine spatial data quality. The course has four modules:

Detailed course description: Spatial Data Quality 

In recent decades, Machine Learning (ML), particularly Deep Learning (DL), has achieved tremendous success across various domains. This course will begin with a general overview of ML, followed by an exploration of key DL applications in Earth Observation and Geoscience, such as semantic segmentation and change detection using aerial imagery. Step-by-step practical exercises will be provided using Python notebooks. The course is structured into four modules: (i) introduction to ML covering conventional classification methods such as Support Vector Machines (SVM) and Random Forest (RF), illustrated by land cover mapping; (ii) DL with an emphasis on Convolutional Neural Networks (CNNs), illustrated by CNN-based image classification model; (iii) advanced image analysis topics, including semantic segmentation, object detection, instance segmentation, panoptic segmentation, and polygonization; (iv) change detection with the application of neural networks for detecting changes over time.

Detailed course description: Machine Learning for Earth Observation

Basic skills in computer programming are getting ever more important. This specifically applies to geospatial data, which is handled, processed, and managed on a country-wide level by NMCAs. Profound knowledge of programming basics helps much in the daily routine, e.g., for evaluating the quality of geodata acquired from third-party data providers before release in official country-wide products and databases. The programming language Python is ideal in this respect. The course is based on the fully digitised MOOC (Massive Open Online Course) “Python for Natural Sciences,” which was developed at TU Wien. The course is divided into two parts: Part I (week 1), dedicated to the fundamentals: data types, operators, containers, loops, conditional expressions, functions, simple data analysis, and basic map visualisations. Based on that, specific programming tools for accessing and processing geodata will be explained and demonstrated in Part II (week 2). This includes basic operations such as intersecting vector data, working with different Web Map Services, and accessing global satellite images and regional 3D point cloud datasets.

Detailed course description: to follow

3D city models have become essential tools for spatial analysis, urban planning and smart city initiatives. Advances in geodata acquisition and processing have revolutionised how these models are generated enabling the automated creation of detailed 3D models for large regions for a wide range of applications. This course offers a comprehensive introduction to 3D city modelling, covering: (1) how 3D city models can be created by combining diverse data sources, including building footprints, LiDAR, and GIS datasets  (2) how 3D city models are structured using international standards like CityJSON, (3) how 3D city models are used in applications, such as solar potential analysis and wind/noise simulations, and (4) how they can be integrated with building information models (BIM). Participants will also get a chance to create their own models using open-source software developed at the Delft University of Technology.

Detailed course description: to follow  

Fees

Fee for pre-course seminar: €100 (the fee includes pre-course participation fee, lunches and social dinner)

Fee for e-courses:

• €400 for 1 or 2 e-courses 
• €500 for 3 or 4 e-courses

Discount for e-courses: When four participants register from the same organisation, one registration is free.  

Scholarships 

Up to five (5) scholarships will be available to fully cover the course fee (pre-course seminar and up to four e-courses). The scholarships are intended for PhD/Master's students and other applicants with no or very limited financial support from their university or public institution. Successful completion of at least two e-courses is expected from successful applicants.

In order to proceed with the application:

• Register below for EduServ.
• Fill in the application form that includes a motivation letter and information about professional experience. It is recommended to support the application with a reference letter. Both documents shall be submitted to EuroSDR@mu.ie  not later than January 23, 2026

Applicants will be informed about the acceptance/rejection of their application by January 30, 2026, at the latest. Successful applicants from previous years will be automatically excluded from the evaluation.

Registration

You can register >> here  << until February 13, 2026

Preliminary programme of the pre-course seminar

March 2, 2026 (time zone: CET)

 March 3, 2026  (time zone: CET)

* Each session includes a coffee break

For more information, please contact Ms Neasa Hogan at EuroSDR@mu.ie