|Course coordinator(s)||dr. ir. A Ligtenberg|
|dr. L Grus|
Language of instruction:
Assumed knowledge on:
Data Science Concepts or equivalent. Python knowledge is preferred
New sources of data available from all kind of ‘smart technologies’ such as sensors, tracking-devices, crowd sourcing and social media open possibilities to create information and gain knowledge about our environment beyond that what is possible with ‘traditional’ sources of data. Especially analyses of spatial-temporal processes and interactions between people and their environment are accelerated by these new sources of data. Examples are the movements of people (tourists) through a city and the consequences for its accessibility or the perception of people about certain places.
The drawback is that these data often comes in high volumes, are often ill structured, and often are collected with a different purpose than that of environmental analyses. This means that (pre) processing, analyses, and visualization of such data requires specific skills. This includes, for example skills to create meaningful patterns from the data by applying (spatial) classification and clustering techniques, or applying sentiment and topic analyses techniques on for example social-media data. Knowing how to visualize these often-complex type of data is essential to effectively share and communicate the outcomes of analyses.
Moreover, making sense of these data and transform it to information useful for design, participation, decision-making and governance processes requires a critical attitude and good knowledge about the quality of the data, as well as critical reflections on the social and political implications of using smart technologies in environmental policy and decision-making. This course will pay ample attention to societal aspects such as citizen engagement in data gathering, ethical questions around big data and automation, and implications of using smart technologies on social and power relation in (urban) environmental policy.
To successfully follow this course knowledge about modern data-science concepts and techniques such as treated in Data Science Concepts (INF-xxxxx) or a data science minor is assumed.
After successful completion of this course students are expected to be able to:
- understand the specific aspects of applying data-science for the environmental science domains;
- evaluate the quality and understand the limitations of data-sources from ‘smart technologies’;
- design procedures to solve an information need using data-science and visualization techniques;
- extract meaningful patterns/knowledge and synthesize it in an appropriate way such that is can be understood and used within an environmental design or planning process;
- apply appropriate data visualization techniques to complex environmental data. ;
- develop an attitude of responsibility by reflecting on the societal implications of using smart technologies and big data.
The course consists of two parts. A general part of and a project part each of four weeks. During the first part, students will learn the concepts, methods, and skills to deal with informal environmental data in 4 blocks:
- smart environmental data: what data sources are available, what is the value of informal data, how to acquire data (tracking/crowdsourcing/citizen science), how to deal with privacy issues?
- storing and retrieving data: how to harmonize data so it can be combined? How to store and link data using specific databases, how to harvest data using web services and social media platforms?
- from data to information: design a data analyses procedure that yields results useful for your design or research? What techniques should be applied to generate meaningful patterns out of the data?
- from information to design, decision and governance: how can you visualize and present (complex) information such that it is useful in a design, decision-making, or governance process? What data visualizations are effective?
The blocks will consist of lectures introducing main concepts and practical work. Students will practice with various cases illustrating a specific concept or technique, for example analyzing movements of people, combining sensor data to monitor air quality, getting insight in perceptions of people about their neighborhoods.
The second part of the course the students will work in groups on a specific project related to their interest. During the project, they set-up a work-plan, acquire and structure data, implement relevant data-science techniques, and verify if the results are useful for their purpose. The result of the project is a poster to be presented and a limited report/paper including a critical reflection on the value of their approach/results and the social, ethical, privacy and governance implications
- exam (40%);
- project (40%);
- paper (20%).
|Keuze voor:||MFN||Forest and Nature Conservation||MSc||5AF|
|MTO||Tourism, Society and Environment||MSc||5AF|