Geospatial Analytics

Emphasis Area Overview

Geospatial data science meets a number of important emerging technology and economic development challenges.

Increasingly location-based data will continue to power the next generation of location-aware services, applications & insight. MU’s Data Science & Analytics graduates will become among the world’s leading geospatial and location-driven focused data scientists with cutting-edge knowledge of geospatial data strategies including geospatial Big Data, GIS, geostatistical analysis & remote sensing.

Courses

This course provides a deeper dive into the theoretical, conceptual, foundational, and practical issues encountered when working with geospatial data (both vector and raster). A focus on integrating and leveraging geospatial data into a data science database and project as well as the concept of ‘thinking spatially’. Data discovery, access, evaluation of use, retrieval, projection, datum, loading, and other technical and data carpentry concepts are investigated. Important aspects of geospatial database design and storage paradigms (enterprise versus desktop) are explored along with addressing Geospatial Big Data. Core issues in geospatial data storage, management, exploitation, feature engineering, multi-data set entity resolution / correlation, and dealing with special data types such as elevation (3D) and time-series are also examined.

3 Credit Hours

This course provides an overview of key issues encountered when working with and analyzing the various forms of spatial data (raster, vector, 3-D, temporal) as well as an overview of major spatial analysis tools, application areas, and analytical approaches. Simple geostatistical measures of centrality, advancing to spatial autocorrelation, geographic weighted regression, and various forms of interpolation. Laboratory, practice, and exercise work will focus on implementation, geostatistical analysis, and derived analytical spatial measures to inform context. Discussions will focus on interpretation issues given constraining factors that commonly arise in practice.

3 Credit Hours

This course provides an overview of key principles of Artificial Intelligence/Machine Learning (AI/ML) as applied to imagery analysis and advanced geospatial analytics. This will include classification of imagery (land cover), change detection, anomalies identification, and forecasting / prediction. The course also delves into and discusses both theoretical and practical issues associated with dynamic spatial systems and techniques such as digital twins, smart cities, as well as touching on spatial simulation methods (i.e., agent-based modeling and cellular automata). Labs, practices, and exercises cover standard geospatial AI processing techniques, including preprocessing and normalization, pixel-level feature extraction, information extraction, classification, data fusion, downscaling, and image understanding

3 Credit Hours

Outcomes

Graduates of the Master of Science in Data Science and Analytics who pursue the Geospatial Emphasis Area will achieve the following educational objectives, in addition to the core program objectives while becoming immersed in Geospatial Big Data computational ecosystems:

  • Students will have a firm understanding of the structure of spatial data and its integration with spatial analysis tools.
    Student will develop a robust understanding of the caveats that can be encountered in geospatial data structures and analysis.
  • Students will have a firm understanding of geospatial data structures such as vector and raster data and their use in data analytics.
  • Students will develop expertise in designing, managing, accessing, and manipulating geospatial data repositories.
  • Students will gain knowledge and experience with the exploitation of geospatial data that is stored in a variety of formats and source locations, as well as experience developing geospatial visualizations of data, blending multiple geospatial data layers as well as non-spatial data.
  • Students will have a solid understanding of the basic concepts, principles, and techniques in remote sensing.
  • Students will understand the spatial and spectral characteristics of remote sensing data for passive, active, thermal, and other sensor phenomenologies.
  • Students will have an ability to acquire and exploit remote sensing data using a variety of tools and techniques for real-world applications.