NCSA-supported Ph.D. candidate successfully defends Ph.D. thesis

NCSA student researcher Ankit Rai, a Ph.D. candidate in Informatics at the University of Illinois at Urbana-Champaign, has just successfully defended his Ph.D. thesis.

Ankit’s research at NCSA was funded by Brown Dog, one of NCSA’s research projects aimed at developing a method for easily accessing historical research data stored in order to maintain the long-term viability of large bodies of scientific research. Ankit is one of about approximately a dozen Ph.D. and Masters students across the United States that are supported by Brown Dog. Each of these students are conducting research for Brown Dog’s different use cases to help drive activities within the supported scientific domains, such as geoscience, engineering, biology and social science.

Ankit, working with Brown Dog Co-PI Barbara Minsker, has assisted on the Designing Green Infrastructure Considering Storm Water and Human Requirements project. In this capacity, he found himself at the intersection of Informatics, Civil Engineering, and Social Science.

“My research for the Brown Dog project was very data-intensive and required applying state-of-the-art machine learning/computer vision models to varied data types to uncover hidden insights. My work primarily addressed the limitations of the current approach in studying landscape preferences by using advanced data science techniques.”

For this project, Ankit developed a novel framework for identifying urban green stormwater infrastructure (GI) designs—wetlands/ponds, urban trees, and rain gardens/bioswales—from high-resolution Google Earth images. This allowed them to create of a framework for collecting landscape preference data in order to better understand what specific features are most desired, as previous research has shown that high-preference green settings are correlated with improved human health and wellbeing.

As part of his research, Ankit developed a number of extractors to assign a green index to pedestrian routes based on given path coordinates, automatically estimate human preference of landscapes given either images or text describing those landscapes, and to detect green infrastructure types within aerial images.

Ankit’s team further curated social media data using Twitter, Flickr, and Instagram to analyze GI preferences using qualitative codebook analysis and natural language processing techniques. The models and findings are implemented as Brown Dog services allowing others to leverage these tools as opposed to having to re-implement these capabilities within their research when using similar datasets. (To learn more about Brown Dog and use these tools, simply sign up for a Brown Dog account.)

“I had a great experience working with the Brown Dog team,” Ankit said. “I learned a lot about building tools that can run in a distributed environment and are efficient in processing a significant amount of uncurated and/or unstructured data and provides reusability of the code for future work. Data collection and retrieval is one of the most critical parts of any data-intensive project, and I think Brown Dog provided me an opportunity to learn and become adept at it.”

Ankit will have the opportunity to put these skills to the test very soon, as following graduation, he will be working as a Data Scientist for an e-commerce company. Congrats, Ankit!

Disclaimer: Due to changes in website systems, we've adjusted archived content to fit the present-day site and the articles will not appear in their original published format. Formatting, header information, photographs and other illustrations are not available in archived articles.