Spatial Computing

Overview

We develop computer algorithms and build intelligent applications that discover, collect, fuse, and analyze data from heterogeneous sources to solve real world problems.

Air Quality Modeling
Air quality models are important for studying the impact of air pollutant on health conditions. Existing work typically relies on area-specific, expert-selected attributes of pollution emissions (e,g., transportation) and dispersion (e.g., meteorology) for building the model for each combination of study areas, pollutant types, and spatiotemporal scales.

In this project, we are building a data mining approach, PRISMS-DA, that utilizes publicly available OpenStreetMap (OSM) data and the IMSC transportation data to automatically generate air quality model for the concentrations for any type of pollutants at various temporal scales. Currently, PRISMS-DA automatically generates (domain-) expert-free model for accurate PM2.5 concentration predictions in the Los Angeles Metropolitan Area. The automatically generated model can be used to improve air quality models that traditionally rely on expert-selected input.

The image below shows the PM2.5 AQI predictions from PRISMS-DA (left) and the traditional spatial interpolation method, IDW (right), for Dec 2016 (top) and Jan 2017 (bottom). As expected, IDW could not generate fine-scale predictions while PRISMS-DA successfully identified intra-city areas where the air quality is typically poor (e.g., the south part of the city near the port of San Pedro and downtown Los Angeles).

Selected Publications

VoPham, T., Hart, J. E., Laden, F., Chiang, Y.-Y. (2018) Emerging Trends in Geospatial Artificial Intelligence (geoAI): Potential Applications for Environmental Epidemiology. Environmental Health, (In press).

Uhl, J. H., Leyk, S., Chiang, Y.-Y., Duan, W., and Knoblock, C. A. (2018) Map Archive Mining: Visual-Analytical Approaches to Explore Large Historical Map Collections. ISPRS International Journal of Geo-Information, 7(4), 148. doi: 10.3390/ijgi7040148

Duan, W., Chiang, Y.-Y., Knoblock, C. A., Vinil, J., Feldman, D., Uhl, J. H., and Leyk, S. (November 2017) Automatic Alignment of Vector Data with Geographic Features for Feature Recognition in Historical Maps. In Proceedings of the First GeoAI Workshop, Redondo Beach, CA USA.

Lin Y., Pan F., Chiang Y.-Y., Stripelis D., Ambite J. L., Eckel S. P., and Habre R. (November 2017) Mining public datasets for modeling intra-city PM2.5 concentrations at a fine spatial resolution. In Proceedings of the 25th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL 2017), Redondo Beach, CA USA

Yao-Yi Chiang

Associate Professor (Research) in Spatial Sciences
USC

Spatial Computing Lab

We are a research lab at the University of Southern California, Spatial Sciences Institute. Since 2013, more than 50 students and 6 postdoctoral researchers have worked in the lab.

Visit Lab's Website

IMSC is a research center that focuses on data-driven solutions for real-world applications by applying multidisciplinary research in the area of data science.