M.S. in Spatial Data Science

Print Friendly, PDF & Email

The Master of Science in Spatial Data Science is a cross-disciplinary joint degree program offered by the Viterbi School of Engineering and the Dornsife College of Letters, Arts and Sciences. Students must be admitted by both the Viterbi School of Engineering and the Dornsife College of Letters, Arts and Sciences.

Career Opportunities in Spatial Data Science

Geospatial data accessibility, spatial decision support systems, and geospatial problem solving environments are revolutionizing most industries and disciplines, including health care, marketing, social services, human security, education, environmental sustainability, and transportation. Spatial data science professionals draw upon engineering, computer science, math, and spatial sciences principles to solve data-intensive, large-scale, location-based problems.

Glassdoor users rated “data scientist” as the #1 most satisfying in data science and business analytics, with an average base pay of $121,000/yer and 4,100+ openings.

As an example of the growing importance of spatial data science, the Southern California Association of Governments (SCAG) is hosting data science students from regional universities to support a new region-wide initiative around open and big data in the coming years. Through a generous contribution by Randall Lewis, the fellows selected will play an important role in supporting governments across the region to become more data driven and effective in the provision of their services. For more information about the Randall Lewis Data Science Fellowship, click here.

 

MEET SOME SPATIAL DATA SCIENCE STUDENTS AND ALUMNI

Adam Vaccaro
Nandan Nayak
Tejal Patted
Seun Deleawe
Yuanchang Zhang
Yuqing Qian

Learning Objectives

The USC Master of Science in Spatial Data Science provides students with the knowledge and skills to:

  • Understand and contribute toward the significant technical and societal challenges created by large location-based data environments, including architecture, security, integrity, management, scalability;
  • Understand how spatial data can be acquired and used to support various forms of analysis, modeling and geo-visualization in large data environments; and
  • Understand how artificial intelligence, machine learning, and data mining can be used to augment the typical geographic information science (GIS) concepts and workflows to intelligently mine data to provide enterprise-centric solutions for a variety of societal challenges and issues spanning the public, private and not-for-profit sectors.

Upon graduation, students will have not only data science skills but will be uniquely qualified to lead data science teams in companies and organizations working with geolocated information, conducting data analytics in startups and tech companies with location-based data, and getting involved with emerging technologies revolving around spatial data.

Students complete a core set of courses to provide a foundation in information engineering, spatial analysis and thinking with their choice of electives to optimize their preparation for their preferred career path and unique professional opportunities.

Students will understand the overall field of data science, the role of the analyst and/or data scientist, and the domains where spatial data science skills can be applied to critical organization missions. They will understand how data management, data visualization and artificial intelligence techniques (specifically data mining and machine learning) are critical to the spatial analysis process and how these can be applied to real world challenges. Throughout their course work, students will assemble a digital portfolio of work product which is intended to help them demonstrate their capabilities and skills for the job market

 

Curriculum

A total of 32 units is required for the M.S. in Spatial Data Science. A minimum cumulative GPA of 3.00 is required for graduation.

Required Courses: (6 courses/24 units)

Foundation (take both courses):

Introduction to data analysis techniques and associated computing concepts for non-programmers. Topics include foundations for data analysis, visualization, parallel processing, metadata, provenance, and data stewardship.
The unique characteristics and importance of spatial information as they relate to the evolving science, technology, and applications of Geographic Information Systems.

Spatial Core (take both courses):

Theoretical foundations, methods, techniques, and software systems for spatial computing.
Provides the knowledge and skills necessary to investigate the spatial patterns which result from social and physical processes operating at or near the Earth’s surface.  Recommended preparation: SSCI 581.

Data Science Core (take both courses):

Programming in Python for retrieving, searching, and analyzing data from the Web. Programming in Java. Learning to manipulate large data sets.
Fundamentals of big data informatics techniques. Data lifecycle; the data scientist; machine learning; data mining; NoSQL databases; tools for storage/processing/analytics of large data set on clusters; in-data techniques.
Recommended Preparation: Basic understanding of engineering and/or technology principles; basic programming skills; background in probability, statistics, linear algebra and machine learning.

Spatial Elective Courses: (Take 4 units)

Design, implementation, and interrogation of relational, object-oriented and other types of geospatial databases. Recommended preparation: SSCI 581.
The use of spatial models to describe social and environmental processes, patterns and systems at multiple spatial and temporal scales.  Recommended preparation: SSCI 583.
Principles of remote sensing, satellite systems, and role of remote sensing data in GIS applications.  Recommended preparation: SSCI 581.
Principles of visual perception, spatial cognition and cartographic design and their contributions to the maps, animations, virtual reality and multimedia displays produced with modern GIS. Recommended preparation: SSCI 581.

Data Science Elective Courses: (Take 4 units)

Techniques to efficiently store, manipulate, index and query geospatial information in support of real-world geographical and decision-making applications. Note: SSCI 582 meets the CSCI 585 prerequisite for CSCI 587 and must be taken before it.
Function and design of modern storage systems, including cloud; data management techniques; data modeling; network attached storage, clusters and data centers; relational databases; the map-reduce paradigm. Recommended preparation: INF 550 taken previously or concurrently; understanding of operating systems, networks, and databases; experience with probability, statistics, and programming.
Practical applications of machine learning techniques to real-world problems.  Uses in data mining and recommendation systems and for building adaptive user interfaces. Recommended preparation: INF 550 and INF 551 taken previously or concurrently; knowledge of statistics and linear algebra; programming experience.
Data mining and machine learning algorithms for analyzing very large data sets. Emphasis on Map Reduce. Case studies.
Recommended Preparation: INF 550, INF 551 and INF 552. Knowledge of probability, linear algebra, basic programming, and machine learning.
Graphical depictions of data for communication, analysis, and decision support. Cognitive processing and perception of visual data and visualizations. Designing effective visualizations. Implementing interactive visualizations.
 
Understand and apply user interface theory and techniques to design, build and test responsive applications that run on mobile devices and/or desktops. Recommended preparation: Knowledge of data management, machine learning, data mining, and data visualization.
 
Student teams working on external customer data analytic challenges; project/presentation based; real client data, and implementable solutions for delivery to actual stakeholders; capstone to degree. Recommended Preparation: Knowledge of data management, machine learning, data mining, and data visualization.

Requirements for graduation, course offerings, course availability, track offerings and any other degree requirements are subject to change.  Students should consult with an academic advisor in the Viterbi School of Engineering or in the Spatial Sciences Institute prior to registering for any classes.

Application criteria

  • An undergraduate degree in STEM (science, technology, engineering, and math) or related social science from a regionally-accredited university.
  • Satisfactory cumulative undergraduate GPA (grade point average).
  • Satisfactory GRE test scores. All scores must be officially reported to the University directly by ETS.

Programming experience or at least a year of calculus is required for admission.

The curriculum is designed to be accessible to students with any background, including students with a spatial sciences background and no computer science knowledge as well as students with a computer science background and no spatial sciences knowledge.  Students with undergraduate degrees in computer science, engineering, science or mathematics will acquire the necessary knowledge of spatial sciences through the curriculum, and can request to replace introductory data science courses with more advanced ones.  Students with undergraduate degrees in spatial sciences, geography, or social sciences will acquire formal and practical data science skills, and can request to substitute introductory courses in spatial sciences with more advanced ones.

Students must be admitted by both the Viterbi School of Engineering and the Dornsife College of Letters, Arts and Sciences.   Applications are accepted for admissions in the fall and spring semesters.

Application Materials

  • All applicants must complete and submit the USC Online Application.
  • Transcripts: Official transcripts from all colleges and universities attended, sealed by the institution. Mail transcripts to: USC Graduate Office of Admission University Park Campus Los Angeles, CA 90089-0915   If sending via a private carrier (e.g., UPS, FedEx, or DHL), send transcripts to: University of Southern California Office of Admission & Financial Aid 3601 South Flower Street Tyler 1 Los Angeles, CA 90089-0915
  • GRE General Test: Satisfactory scores less than five years old. Official scores must be reported from ETS directly to USC using ETS school code 4852. A department code is not required.
  • Letters of Recommendation (Optional): Letters of recommendation should be from faculty or others (supervisors, professional colleagues, etc.) qualified to evaluate your potential for graduate study. They should be submitted through the online graduate application.
  • Statement of Purpose (Optional): The statement of purpose should describe succinctly your reasons for applying to the proposed program, your preparation for this field of study, study interests, future career plans, and other aspects of your background and interests which may aid the admissions committee in evaluating your aptitude and motivation for graduate study.

Additional Application Materials for International Applicants
English Language Proficiency: In addition to the general admission criteria listed above, international students whose first language is not English are required to take the TOEFL or IELTS examination to be considered a candidate for admission.  There is no minimum TOEFL or IELTS score required for admission to the Viterbi School and Dornsife College. For possible exemption from additional language requirements, you must achieve an Internet Based TOEFL (iBT) score of 90, with no less than 20 on each section or an IELTS score of 6.5, with no less than 6 on each band score. For more details on English Proficiency Criteria for the University of Southern California, please visit USC Graduate Admission – Proficiency in English.

Questions? Email Art Perez, Assistant Director, Computer Science Student Affairs, at arturope@usc.edu.