Prinzipien räumlichen Data Minings und maschinellen Lernens

What it is about

You learn methods of Data Mining and machine learning with a focus on spatial and spatio-temporal data. By the end of the module you will be able to apply suitable model types (e.g., linear models, kNN, decision trees, Naive Bayes, SVMs) to spatial data types and address common problems such as missing values, spatial autocorrelation, model selection and data cleaning.

What you will be able to do

• Apply classification and regression methods to spatial data
• Use clustering and other unsupervised methods
• Handle missing values and uncertainty in spatial datasets
• Consider and treat spatial autocorrelation
• Model selection, model fusion and evaluation (e.g., cross-validation)
• Work with different spatial data types (point clouds, trajectories, networks, text, multimedia)

What the module consists of

• LectureDelivery of the fundamentals and methods of spatial data mining and machine learning
• TutorialConcrete examples and exercises for applying the methods

Teaching method

• PräsentationIntroduction and explanation of concepts
• HandoutSummary and reference work for the content
• BeispieleApplication of the methods on concrete datasets
• ScreencastsSupplementary demonstrations and explanatory videos