Lesson 1 – Introduction and basic concepts
Lesson 2 – Representations and feature design in EO
Upon completion of this lesson, you should understand how Earth observation data can be represented in ways that support analysis and interpretation. You should be familiar with different forms of describing spectral, spatial, and temporal information, and understand how data representation influences subsequent analytical steps.
Lesson 3 – Hyperspectral image analysis
Upon completing this lesson, you should be able to explain the principles of hyperspectral remote sensing, analyse high-resolution spectra, and understand the importance of sensor characteristics and data quality. You should also be familiar with common approaches for processing and interpreting hyperspectral data, and know the role of current missions such as EnMAP in providing spaceborne imaging spectroscopy data.
Lesson 4 – Thermal remote sensing
By the end of this lesson, you should understand the basic physical principles of thermal remote sensing and how thermal information can be used to characterise surface properties and processes. You should be aware of key application areas, data characteristics, and challenges in the interpretation of thermal signals.
Lesson 5 – Radar remote sensing
By the end of this lesson, you should understand the observation geometry and physical principles of microwave remote sensing. You should be aware of different acquisition modes, understand the relevance of backscatter and related signal properties, and have gained first practical experience in handling microwave or SAR data.
Lesson 6 – Object-based image analysis (OBIA)
By the end of this lesson, you should understand the concept of object-based image analysis and the role of segmentation in structuring image data. You should be able to explain core principles of object-based approaches, recognise their advantages and limitations, and reflect on their suitability for different remote sensing tasks.
Lesson 7 – Time series analysis
By the end of this lesson, you should understand the principles of remote sensing time series and how temporal information can be used to analyse environmental dynamics and change. You should be familiar with selected algorithms and approaches for trajectory analysis, change detection, and the use of image data cubes, which will be a key topic in lesson 7.
Lesson 8 – Big EO data
By the end of this lesson, you should understand key challenges and opportunities associated with large-scale Earth observation data. You should be aware of how increasing data volume, variety, and complexity influence remote sensing workflows, and understand data cubes as a central paradigm for organizing and analysing big EO data.
Lesson 9 – Machine Learning in Earth observation
By the end of this lesson, you should understand the conceptual foundations of machine learning in remote sensing. You should be familiar with central terminology, typical workflow components, and the distinction between different learning paradigms. You should also understand the basic mathematical and statistical concepts underlying traditional machine learning algorithms and be able to relate these principles to Earth observation problems.
Lesson 10 – Neural networks, CNN and foundation models in EO
By the end of this lesson, you should understand the core principles of neural networks, foundation models, and their use in remote sensing. You should be familiar with key components such as layers, weights, activation functions, loss functions, backpropagation, and training processes, and understand how these models learn patterns from data. You should also be able to critically assess their potential and limitations for Earth observation.
Lesson 11 – Advanced accuracy and uncertainty assessment
By the end of this lesson, you should understand why uncertainty and validation are central to robust remote sensing analysis. You should be aware of different sources of uncertainty arising from data, reference information and model design. You should also understand the purpose of advanced validation strategies, including the careful design of training and test data, the choice of suitable evaluation metrics, and the interpretation of model performance beyond a single summary accuracy value.
Lesson 12 – Responsible and resource-aware AI in Earth Observation
By the end of this lesson, you should be able to reflect on broader questions arising from the growing role of AI in remote sensing. This includes ethical, societal, and economic aspects, as well as critical consideration of responsibility, bias, resource use, and the practical consequences of increasing automation.
Lesson 13 – Future trends
By the end of this lesson, you should have developed a perspective on current developments and possible future directions in advanced remote sensing. You should be able to reflect on trends such as increasing automation, larger and more generalisable models, multi-modal data integration, and the growing importance of scalable and transferable analysis frameworks and critically assess what these developments may mean for research and practice.
