Universität Wien FIND

290095 VU Big Data and Exploratory Spatial Data Analysis (2021W)

3.00 ECTS (2.00 SWS), SPL 29 - Geographie
Continuous assessment of course work


Note: The time of your registration within the registration period has no effect on the allocation of places (no first come, first served).


max. 20 participants
Language: English



Time: Mondays at 14:00-15:30 starting 04.10.2021
Room on-site: GIS-Lab, NIG, Stiege III, 1. Stock, C109


Aims, contents and method of the course

GIS, GPS, crowdsourced, and sensor data are massive and complex geodatasets that are stretching the limits of GIS packages, thus a real challenge is to develop innovative ways to deal with all the available data and datasets (i.e. Big Spatial Data). Nowadays, geodata analysts should be able to cure and manage both structured and unstructured data while at the same accomplish their tasks timely using computing architectures adequate for datasets of millions of spatiotemporal observations. Furthermore, demands on data exploration go beyond basic statistical measures, charts, and EDA techniques to spatial statistical methods that look at the global or local patterns of univariate-bivariate-multivariate geodata and various forms of cartographic visualization. An additional challenge is that although a significant percentage of big data can be characterized as big spatial data, at times the “spatial information” needs to be processed or even engineered. In this course, the students learn the fundamentals of big spatial data and exploratory spatial data analysis, and will also deepen their knowledge in various application domains such as health, natural disasters, crime analysis, agriculture, human mobility, or geodemographics.

The course has a fairly equal amount of both lectures and practical work. The practical work is either tutorials guided by the lecturer or exercises of multiple tasks to be solved/answered given sufficient support material. Most of the times learning of theory and methods precedes their application. There is also a rotational pattern in which topics/concepts of older lessons are re-used and tested within newer lessons. Game-based learning and other interactive learning approaches are regular activities during the lectures.

Entry requirements
Knowledge of basic Python scripting is a prerequisite for this course. Knowledge of descriptive statistics or spatial statistics would be advantageous but is not required.

Assessment and permitted materials

The assessment is conducted via three testing elements (T1-3). The first, a written test, is conducted at the very last session of the course. The test assesses the technical skills and the methodological concepts learned throughout the lessons. The second, an assignment, allows the students to deepen their knowledge into one choice topic. It is assessed via a presentation file and an oral presentation. The last one assesses the participation and contribution during in-class activities.

The weights of each element are:
- Test 50% (T1)
- Assignment 40% (T2)
- Contribution 10% (T3)

Minimum requirements and assessment criteria

-- A student shall attend at least 75% of the sessions.

-- T1 is an obligatory test to pass the course. It contains a multiple set of questions. The correct answers to the questions sum up to 50 scoring points. The structure/style of T1 test is practiced within in-class game activities.

-- T2 is not an obligatory test to pass the course. It is assessed via the presentation file and the live presentation in class. The maximum scoring points that can be achieved is 40.

-- T3 is not an obligatory test to pass the course. For T3 a conditional mark is given (or not) of 10 points.

Examination topics

Big Spatial Data, ESDA, Spatial Statistics, Python (geo)computation & visualization libraries, Application domains (e.g., social media, geohealth, crime, agriculture, mobility, distasters, etc.)

Reading list

- Eldawy, A., & Mokbel, M. F. (2015). The era of big spatial data. 2015 31st IEEE International Conference on Data Engineering Workshops, 42–49.
- Graham, M., & Shelton, T. (2013). Geography and the future of big data, big data and the future of geography. Dialogues in Human Geography, 3(3), 255–261.
- Kitchin, R. (2013). Big data and human geography: Opportunities, challenges and risks. Dialogues in Human Geography, 3(3), 262–267.
- Lee, J.-G., & Kang, M. (2015). Geospatial Big Data: Challenges and Opportunities. Big Data Research, 2(2), 74–81.
- Leszczynski, A., & Crampton, J. (2016). Introduction: Spatial big data and everyday life. Big Data & Society, 3(2), 2053951716661366.
- Liao, C., Brown, D., Fei, D., Long, X., Chen, D., & Che, S. (2018). Big data‐enabled social sensing in spatial analysis: Potentials and pitfalls. Transactions in GIS, 22(6), 1351–1371.
- Miller, H. J., & Goodchild, M. F. (2015). Data-driven geography. GeoJournal, 80(4), 449–461.
- Robertson, C., & Feick, R. (2018). Inference and analysis across spatial supports in the big data era: Uncertain point observations and geographic contexts. Transactions in GIS, 22(2), 455–476.

Association in the course directory

(MG-S3-PI.m) (MG-S4-PI.m) (MG-S5-PI.m) (MG-S6-PI.m) (MG-W6-PI) (MR1-a-PI) (MK2-PI) (MA UF GW 02)

Last modified: Fr 01.10.2021 16:10