About Aiman Soliman
Aiman Soliman
Aiman Soliman, Ph.D., is a Research Assistant Professor and a Research Scientist at the National Center for Supercomputing Applications (NCSA). Aiman is trained as a spatial data scientist and specializes in applying quantitative and computational methods, spatial analysis, and machine learning to spatial information. His research examines the form and structure of urban fabric through the lens of big data. He focuses on studying feedback patterns between natural and urban systems and investigating connections between urban heterogeneity and a variety of outcomes, including public health. In his publications, he leverages data-driven approaches to analyze regional dynamics, such as the impact of collective human mobility patterns on the outbreak of diseases and the effects of climate change on urban settlements.
Aiman received a Ph.D. in Environmental Sciences and Remote Sensing (2010) from the University of Guelph, a master’s degree in Geographic Information Science from the University of Twente (2004), and a bachelor’s degree in Land Resources from Ain Shams University (1999).
Education
- PhD, Environmental Science, University of Guelph, 2010
- MS, Geographic Information Science, University of Twente, 2004
- BS, Land Resources, Ain-Shams University, 1999
Research and publications
Ongoing and upcoming research
Ongoing and upcoming research
- Coupled dynamics of tourism and mosquito-borne disease transmission in the Americas. Spatial big data and machine learning are used to investigate the impact of global travel patterns on the spread of pathogens in the Americas and the reciprocal feedback of outbreaks on the collective risk perception of tourists and their travel decisions in a series of recent outbreaks, namely Chikungunya virus outbreak of 2013 and Zika virus outbreak of 2015.
- The Permafrost Discovery Gateway. Indicators of changes in the Urban environment across Alaska and the Arctic region are extracted from collections of high-resolution satellite imagery with the aid of deep learning and cyber-infrastructure.
- Reducing racial disparities in lung cancer outcomes by decoding contextual environments of neighborhoods. Spatial heterogeneity is studied and contrasted to the ecological phenotypes of lung cancer within neighborhoods.
- Aiman also is a practicing data scientist, where he works with NCSA’s industrial partners on developing data solutions in the energy, finance, and agriculture sectors. Many of his data solutions are currently in production.
Selected publications
Soliman, A., Chen, Y., Luo, S., Makharov, R., & Kindratenko, V. (2022). Weakly Supervised Segmentation of Buildings in Digital Elevation Models. IEEE Geoscience and Remote Sensing Letters.
Lieberthal, B. A., Soliman, A., & Gardner, A. M. (2020). Statistical decomposition of cumulative epidemiological curves into autochthonous and imported cases. Letters in biomathematics.
Soliman, A., & Terstriep, J. (2019). Keras Spatial: Extending deep learning frameworks for preprocessing and on-the-fly augmentation of geospatial data. In Proceedings of the 3rd ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery (pp. 69-76).
Soliman, A., Mackay, A., Schmidt, A., Allan, B., & Wang, S. (2018). Quantifying the geographic distribution of building coverage across the US for urban sustainability studies. Computers, Environment and Urban Systems, 71, 199-208.
Soliman, A., Soltani, K., Yin, J., Padmanabhan, A., & Wang, S. (2017). Social sensing of urban land use based on analysis of Twitter users’ mobility patterns. PloS one, 12(7), e0181657.
Soliman, A., Yin, J., Soltani, K., Padmanabhan, A., & Wang, S. (2015). Where Chicagoans tweet the most: Semantic analysis of preferential return locations of Twitter users. In Proceedings of the 1st international ACM SIGSPATIAL workshop on smart cities and urban analytics (pp. 55-58).
Soliman, A., Duguay, C., Saunders, W., & Hachem, S. (2012). Pan-arctic land surface temperature from MODIS and AATSR: Product development and intercomparison. Remote Sensing, 4(12), 3833-3856.
Teaching and advising
Classes taught
Prior teaching includes courses on Remote Sensing and Geospatial Analysis, including lecturing on the application of Machine Learning to Spatial Big Data.