NIGK22000U Satellite Image Processing and Analysis in the Big Data Era

Volume 2022/2023

MSc Programme in Geography and Geoinformatics


We live in exciting times with a rapidly expanding number of earth observation products being available for better understanding global environmental and socio-economic changes. However, this development poses a number of challenges:


- How to process large remote sensing data sets efficiently?

- Which approaches are suitable for time-series analysis?

- How to extract and analyze patterns and trajectories of land change?


Through this course, the principles of big data analysis will be introduced, including cloud computation, API-driven image processing and specific image formats that are efficient to store and analyze large data sets. We will work with cloud-image processing platforms like Google Earth Engine, FAO Sepal to process and analyze various optical and microwave data sets. Specific attention will be on the use of very-high-resolution data for advanced machine-learning pattern recognition techniques, such as convolutional neural networks, and how to assess model performance and accuracy. Machine learning techniques (e.g., Boosted Regression Trees) using all sorts of geospatial data will be taught for understanding the drivers of environmental change. The course welcomes those who would like to advance their knowledge in remote sensing of the environment and socio-economic footprint, pattern recognition and spatial data analysis or apply gained skills in programming to remote sensing of the environment. It is expected the students will progress their scripting skills in Python/Javascript environment. At the same time, we also expect that students have prior experience in satellite image analysis.

Learning Outcome


  • Sources of data; currently operating non-commercial and commercial platforms in Earth Observation, with a specific focus on very-high-resolution imagery,
  • Principles of pattern recognition, classification and segmentation using convolutional neural networks (CNNs),
  • Advanced time-series analysis and machine learning in a cloud environment,
  • Land-use modeling,
  • Python Application Programming Interface (API); API-based computation with Python for big data processing.



  • Ability to download, pre-process, and analyze large amounts of satellite imagery with a focus on remote sensing of the geobiosphere and land system science,
  • Progression of skills on python-based analysis of satellite data using machine learning,
  • Hands-on experience on parameterization, running and evaluation of the performance of convolutional neural networks for pattern recognition tasks using e.g., Google Colab and TensorFlow,
  • Advanced use of cloud-based time-series methods, such as LandTrendr/ BFAST using e.g., Googe Earth Engine (GEE), Copernicus Data and Information Access Services (DIAS), System for earth observations, data access, processing & analysis for land monitoring (SEPAL FAO),
  • Setting up and evaluation of machine-learning approaches in land-use modeling.
  • Integrating knowledge gained from lectures, hands-on exercises and independent readings of up-to-date publications to perform a course project of your choice.



  • Ability to process and analyze various types and a large amount of remote sensing data sets using advanced cloud-based methods and state-of-the-art machine learning.

Please see Absalon course page.

BSc in Geography and Geoinformatics or equivalent. Prior experience in satellite remote sensing processing and analysis is expected. Experience in scripting is welcomed.

The course builds on prior knowledge of working with satellite imagery, such as passing via Bachelor level classes such as Introduction to Remote Sensing, Classification of Spatial Data, as well as some Master-level remote sensing classes, such as Remote Sensing of Geobiosphere, Remote Sensing in Land Science Studies, Spatial pattern analysis. However, we will try to accommodate the students without prior experience in remote sensing but with solid experience in programming. If you dit not take remote sensing classes, please contact the course responsible prior to enrolling in the class.
The form of teaching is theory exercises combined with lectures and various forms of activation of learning. For the teaching plan, please see Absalon.
  • Category
  • Hours
  • Preparation
  • 171
  • Theory exercises
  • 35
  • Total
  • 206
Continuous feedback during the course of the semester
Peer feedback (Students give each other feedback)
7,5 ECTS
Type of assessment
Written assignment, During course
Oral examination, 20 minutes
Type of assessment details
The written assignment is prepared during the course and must be handed in prior to the exam week. The oral exam uses the written assignment (course project) as its point of departure. There is no preparation for the oral exam. It includes the titles listed in the officially approved reading list. A combined grade is given after the oral exam.
Exam registration requirements



All aids allowed
Marking scale
7-point grading scale
Censorship form
No external censorship
Several internal examiners

Identical to the ordinary exam.

If the quality of the written assignment is not acceptable, the student can choose to either hand in a new or revised report.

Is the quality of the written assignment is acceptable, the student can choose to either hand in a revised report or resubmit the original report from the ordinary exam.

The written assignment must be handed in prior to the re-examination week. The oral exam uses the written assignment as its point of departure. It includes the titles listed in the officially approved reading list.

Criteria for exam assesment

See learning outcome.