Processes relevant to system Earth, whether natural or man-affected, commonly display variations in space and over time, yet our understanding of their behavior remains limited. The increase in available monitoring data provides handles for a detailed study of these processes. Unravelling the way these processes function and having a mechanism to test hypotheses as well as the possible impacts of interventions is key to contribute to more sustainable development. At course end, the student will have learnt to make use of the available data in process studies, by a variety of computational techniques.
In this course, we present various geo-computational approaches that help to improve our understanding of geographic processes and/or to extract actionable geo-information. Special attention will be paid to agent-based modelling and to data mining and machine learning analytical methods, and to the integration of different methods.
Agent-based models (ABMs) provide the opportunity to consider both natural and social components when modelling geographic phenomena.
Data mining and machine learning methods allow innovative uses of heterogeneous datasets and have proven their value to solving a variety of social, environmental and scientific problems that were deemed wicked or, even, intractable. Cloud computing is revolutionizing the way we perform spatiotemporal analysis. It allows scaling up our work and designing robust applications for real-life problems.