Наука о геоданных

Магистратура 2021/2022

Лучший по критерию «Полезность курса для расширения кругозора и разностороннего развития»

Лучший по критерию «Новизна полученных знаний»

Статус: Курс по выбору (Науки о данных (Data Science))

Направление: 01.04.02. Прикладная математика и информатика

Кто читает: Департамент программной инженерии

Где читается: Факультет компьютерных наук

Когда читается: 1-й курс, 1, 2 модуль

Формат изучения: без онлайн-курса

Охват аудитории: для своего кампуса

Преподаватели: Родригес Залепинос Рамон Антонио

Прогр. обучения: Науки о данных

Язык: английский

Кредиты: 4

Контактные часы: 40

Full Syllabus

Abstract

About 80% of data has a location component [1]. Geospatial data are diverse and ubiquitous: GPS, maps, satellite imagery, to name a few. Apple [2], Uber [3], MasterCard [4], Google [5] and many other companies heavily utilize geospatial data. However, geospatial data are different from other data types and it is impossible to analyze geospatial data correctly without special knowledge. The “Geospatial Data Science” course gives core theory and algorithms to successfully work with geospatial data: Coordinates and Projections, Spatial Data Formats, Spatial Data Processing (including map algebra and topology), Spatial Data Algorithms, Spatial Data Mining, and other important topics. The course is beneficial for a Data Scientist as it gives expertise to solve practical tasks in public, business, private sectors as well as to do research in Geospatial Data Science. [1] https://www.forbes.com/sites/truebridge/2016/05/06/how-imaging-technologies-are-changing-the-world-part-2/ [2] https://www.cnbc.com/2017/08/02/apple-has-over-70-map-tech-job-openings.html [3] https://eng.uber.com/keplergl/ [4] https://carto.com/blog/carto-mastercard-partnering-location-intelligence-solution/ [5] https://www.google.com/maps

Learning Objectives

Have a strong understanding of key geospatial data types and formats
Have a strong understanding of cartographic projections
Know the structure of popular spatial data sources and formats used to store geospatial data
Acquire experience in spatial data processing
Acquire deep understanding of selected spatial data mining topics
Be able to use geospatial data visualization techniques
Form a deep understanding of selected spatial data structures and algorithms
Form a deep understanding of selected spatial network processing techniques
Know GPS, WiFi, cellular, indoor positioning techniques
Be aware of current R&D trends on the Geospatial Data Science

Expected Learning Outcomes

Acquire a deep understanding of spatial data mining foundations
Acquire experience in spatial raster data processing
Acquire experience in spatial vector data processing
Be able to graphically perform exploratory geospatial data analysis
Be able to visualize geospatial data on the Web using a Web mapping service
Be aware of current R&D trends in geospatial data science, geoinformatics, big spatial data and systems, novel spatial data applications
Be aware of key Spatial Data Structures and Algorithms
Form a deep understanding of selected spatial data mining techniques
Form a deep understanding of selected spatial data structures and algorithms
Form a deep understanding of selected spatial network processing techniques
Have a strong understanding of cartographic projections
Have a strong understanding of geospatial concepts and properties unique to geospatial data
Have a strong understanding of geospatial coordinate properties
Have a thorough understanding of key design challenges of spatial data structures and algorithms
Know concepts, foundations, and applications of spatial networks
Know differences between main spatial coordinate systems and their peculiarities
Know GPS, WiFi, cellular, indoor positioning techniques
Know key spatial data mining techniques and their applications
Know the structure of popular spatial raster data formats used to store raster geospatial data
Know the structure of popular spatial vector data formats used to store vector geospatial data
Thoroughly understand topological relationship types of spatial data objects
Describe the structure of popular spatial raster data forms and their applications

Course Contents

Introduction to Geospatial Data Science
Geospatial Coordinate Systems
Cartographic Projections
Spatial Vector Data Formats
Spatial Vector Data Processing
Algebraic Topology
Spatial Raster Data Forms
Spatial Raster Data Processing
Spatial Data Mining
Spatial Data Visualization
Spatial Data Structures and Algorithms
Spatial Networks
Positioning Systems and Algorithms
Geospatial Data Science: The Path Forward

Assessment Elements

EX (Exam)
CW (Control Work)
HA1 (Home assignment 1)
HA2 (Home assignment 2)

Interim Assessment

2021/2022 2nd module
0.25 * CW (Control Work) + 0.25 * EX (Exam) + 0.25 * HA2 (Home assignment 2) + 0.25 * HA1 (Home assignment 1)

Bibliography

Recommended Core Bibliography

An introduction to R for spatial analysis & mapping, Brunsdon, C., 2015
Applied spatial data analysis with R, Bivand, R., 2008
Benjamin S. Baumer, Daniel T. Kaplan, & Nicholas J. Horton. (2017). Modern Data Science with R. Chapman and Hall/CRC.
Bin Jiang, & Xiaobai Yao. (2010). Geospatial Analysis and Modelling of Urban Structure and Dynamics. Springer.
Cady, F. (2017). The Data Science Handbook. Hoboken, NJ: Wiley. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=1456617
Cartography : visualization of spatial data : Chinese edition. (2014). Pearson Education Asia.
Cartography: Visualization of spatial data. (2010). Guilford Publications.
De Miguel Gonzalez, Rafael, Donert, Karl, Koutsopoulos, Kostis. Geospatial Technologies in Geography Education. 2019. Springer International Publishing
Grus, J. (2019). Data Science From Scratch : First Principles with Python (Vol. Second edition). Sebastopol, CA: O’Reilly Media. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=2102311
He, X., Tao, Y., Wang, Q., & Lin, H. (2019). Multivariate Spatial Data Visualization: A Survey. https://doi.org/10.1007/s12650-019-00584-3
Hierarchical modeling and analysis for spatial data, Banerjee, S., 2015
Lansley, G., de Smith, M., Goodchild, M., & Longley, P. (2019). Big Data and Geospatial Analysis.
Matloff, N. S. (2020). Probability and Statistics for Data Science : Math + R + Data. Chapman and Hall/CRC.
Menno-Jan Kraak, & Ferjan Ormeling. (2020). Cartography : Visualization of Geospatial Data, Fourth Edition. CRC Press.
Qurban A Memon, & Shakeel Ahmed Khoja. (2019). Data Science : Theory, Analysis and Applications. [N.p.]: CRC Press. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=2198593

Recommended Additional Bibliography

Shashi Shekhar and Hui Xiong. 2017. Encyclopedia of GIS (Springer Reference)
Data science foundations : geometry and topology of complex hierarchic systems and big data analytics, Murtagh, F., 2018
Data science from scratch, Cooper, S., 2018
High-dimensional probability : an introduction with applications in data science, Vershynin, R., 2018
Morphism for quantitative spatial analysis, Griffith, D. A., 2018
R for data science : import, tidy, transform, visualize, and model data, Wickham, H., 2017
The data science handbook, Cady, F., 2017

Course Syllabus