Article Content
From public health and environmental monitoring to urban planning and disaster response, organizations are looking to advanced analytics to transform location-based data into actionable insights. To help meet this growing demand, the School of UC San Diego Global Policy and Strategy (GPS) offers GPEC 447: Data Science Approaches to Spatial Analysis, a graduate course taught by Ilya Zaslavsky, director of the San Diego Supercomputer Center (SDSC) Spatial Information Systems Laboratory.
Developed in response to the need for a new generation of spatial data scientists, the course bridges traditional geographic information systems (GIS) training with modern machine learning and data science techniques. The class is the final course in the three-course GPS Spatial Analysis Certificate sequence, which begins with GPEC 443 – GIS and Spatial Data Analysis, then continues with GPEC 444 – Advanced GIS and Remote Sensing and ends with GPEC 447.
“A key motivation was to connect academic learning with real-world applications, allowing students to work with authentic datasets and applied problems in areas such as public health, urban planning, environmental analysis and international development,” said Zaslavsky, who also teaches courses through the Halıcıoğlu School of Data Science and Computing (HSDSC) Halıcıoğlu Data Science Institute (HDSI).
Throughout the quarter, UC San Diego students enrolled in Zaslavsky’s course work with geospatial datasets and tackle challenges involving international economics, migration, sustainable development, infrastructure conditions, risk forecasting and ecological systems. Through a series of coding projects, they learn how machine learning models can incorporate location-based information to identify patterns, improve predictions and support decision-making.
The course also challenges students to apply these methods to independent research projects. For instance, UC San Diego graduate students Dumas Zhong, Li Shen and Zilu Zhang developed a project examining environmental risks associated with industrial facilities across California. Using Environmental Protection Agency facility records, Toxic Release Inventory (TRI) data, CalEnviroScreen 4.0 metrics and American Community Survey socioeconomic indicators, the team created a facility-level dataset designed to evaluate how spatial context influences environmental risk assessment.