LEI111 Geographic information science

Contents and structure

This course will give the student better understanding of methods and techniques for processing and modelling geographic information in the database. The course will in particular help the student develop skills to analyze and operate on spatial data by scripting and automation. The student will also gain knowledge in applied spatial data analysis, statistical methods, evaluation of accuracy and quality, and to present results using cartographic methods and techniques. In addition, the course will introduce the use of artificial intelligence and machine learning to enhance the analysis and modeling of geographic information.

Contents

Spatial concepts, import, export, structuring, topology and spatial relations, data quality, geoprocessing and analysis, presentation of data, correlation and regression, visualization and analysis by programming/scripting, introduction to artificial intelligence and machine learning (formulation, training, and validation of artificial neural networks (ANN)).

Learning Outcome

After completing this course the student should be able to:

Knowledge

• Explain principles for storing and accessing geographic data and attach tabular data to geographic data.
• Be able to recognize known spatial problems and to choose suitable solutions.
• Characterize essential techniques to process, analyze and to visualize geographic information.
• Be able to explain the basic principles behind artificial intelligence and machine learning techniques, as well as their applications within GIS.

Skills

• Process, couple, and present geographic data from various sources.
• Perform basic analysis on geographic data.
• Apply cartographic techniques to visualize results.
• Create models of the analyzation process and construct simple programs/scripts.
• Be able to apply machine learning techniques (ANN) to improve the analysis and modeling of geographic information.

General Competence

Demonstrate basic skills in processing, analyzation and visualization of spatial data using modern GIS software. "The candidate should also demonstrate competence in using machine learning techniques to analyze and model geographic data.

Entry requirements

See recommended prerequisite knowledge.

Recommended previous knowledge

Knowledge corresponding or similar to LEI200 Digital project execution and LEI117 Introduction to geomatics and geo-informatics.

Teaching methods

Lecturers, theory and data exercises.

Compulsory learning activities

Five mandatory assignments must be submitted within set deadlines and approved before examination can take place.

Approved assignments are valid in five subsequent semesters.

Assessment

4 hour written examination.

Time and place for the examination will be announced at Studentweb and digital assessment system.

The examination is digital and the students bring their own computer. The software used for the examination must be installed and tested by the student before the examination.

Grading scale is A-F where F is fail.

Examination support material

All physical printed and written aids are allowed.

All calculator models are allowed.

More about examination support material