GEO-DEEP9508 ¨C Artificial Intelligence, Data Science and Geographic Information Systems (GIS)

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

Admission to the course

The course only admits PhD candidates enrolled in the Norwegian Research School for Dynamics and Evolution of Earth and Planets (DEEP). The potential participant is member of DEEP, and has submitted a project idea/motivation relevant to her/his research and related to the learning outcome workflow examples (3-4 sentences) with the course application.

Registration is done by filling out an online application form.

PhD candidates who are admitted to other education institutions than UiO must apply for visiting PhD status. This is easily done through the same online application form. Applicants must be able to present original documentation on request.

The course has a maximum capacity of 20 participants. If there are more than 20 eligible applicants, we will select applicants on a first-come-first-served basis.

Formal prerequisite knowledge

Basic familiarity with GIS systems and Python is a prerequisite.

Teaching

The course will take place during one week and consists of lectures, hands-on exercises and training sessions (about 40 h).

Attendance at the course activities is mandatory.

Course literature will be pre-selected and accessible to course participants in due time prior to the course.

Successful candidates will mandatorily present their preliminary results according to the project idea, which they have submitted for admittance.

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.

When writing your exercises, make sure to familiarize yourself with the rules for use of sources and citations. Breach of these rules may lead to suspicion of attempted cheating.

Language of examination

The examination text is given in English, and you submit your response in English.

Grading scale

Grades are awarded on a pass/fail scale. Read more about?the grading system.

More about examinations at UiO

• Use of sources and citations
• Special exam arrangements due to individual needs
• Withdrawal from an exam
• Illness at exams / postponed exams
• Explanation of grades and appeals
• Resitting an exam
• Cheating/attempted cheating

You will find further guides and resources at the web page on examinations at UiO.