Course content
This course explores state-of-the art principles, methods, and techniques related to applications of artificial intelligence and data science in relation to Earth and planetary remote sensing data processing. We intend to train the participants in open science and towards integrated solutions of data science and Geographic Information Systems (GIS). In this way the participant can give a new dimension to their research by adding the spatial component to their data and be able to process, analyse, combine, and visualise the data in time and space. The aim of this specific course is to familiarise the participants with the possibilities of applying AI (Artificial Intelligence) to data with a spatial component making use of Esri software (in this case ArcGIS Pro).
The participants will explore potential links between their own research questions and GIS using Earth and planetary remote sensing data or other image and spectra based information. This training will familiarize the participants using ArcGIS Pro and developing or integrating a project example or tool within ArcGIS Pro and Jupyter Notebook.Our focus will be as follows: We will start with understanding image data and image processing, which entails working with multispectral image data, extracting spectral profiles, or raster functions (like band arithmetic, band composition etc).
Next, we continue with machine learning (clustering, classification, and prediction) and deep learning (object detection, object tracking) involving different types of image data, and/or video or camera feeds. To this end, we will make use of the ArcGIS Pro integrated geoprocessing tools. Furthermore we will develop and/or integrate scientific algorithms directly on the ArcGIS platform using Jupyter Notebooks, a web application which is running under the Python environment of ArcGIS Pro and can make use of open science libraries and frameworks (other than the default ArcGIS Pro Python environment).
Learning outcome
After completing the course, the candidate will be able to
- perform the entire workflow of a deep learning object detection or object tracking with the existing tooling and data science frameworks of ArcGIS Pro from the beginning to the end
- use multispectral image data and supervised classification using the ArcGIS Pro classification wizard alone and integrated with the personal research
- understand the difference between object classification and pixel classification and relate one of the methods with the personal research
For the full course description follow the link.
Prior to the course
Prior to the course week the students will receive relevant information and course materials from lecturers in order for preparation.
Examination:
- A research project counts 100% towards the final grade. The project is to be submitted after the course and before a set deadline.
- A mandatory presentation must be approved before you can sit the final exam.
Registration and admission
Register within 18 April 2022!
This course is also open to registration for the international PhD applicants, but PhD candidates enrolled at the research school DEEP are the top priority group. We have 20 places in the course and DEEP members will have first priority.
Lecturer:
Gabriela Spakman: "Specialist Geodesy, Geo-information and Data Science with more than 28 years of work experience involved in: academic and applied science research, academic and higher professional education teaching in the field of Geodesy and Geo-Information.
In the current position, at Esri Nederland, as analytics consultant, I'm working especially on GeoAI Projects (projects where AI is applied on data with a spatial component). Would you like to know more about topics like prediction, classification, clustering, computer vision (object detection, object tracking, text recognition), image analysis, Jupyter Notebook integration in ArcGIS platform, integration, transformation, adjustment, and statistical testing of geodetic data? Of do you have a particular question about those topics? You can contact me directly via LinkedIn https://www.linkedin.com/in/gabispakman/ or through Esri Nederland."