Algorithmic advances: S&T researcher works to improve geospatial analytics

Newswise — ROLLA, Mo. – Imagine owning a library with every book imaginable — millions and millions of titles — but not having a way to organize the different texts or search for specific information.

This is essentially the scenario Missouri University of Science and Technology researcher Dr. Satish Puri works to fix, but instead of it being a brick-and-mortar library filled with books, he is working with petabytes of digital data — primarily geospatial information, such as maps — and finding the best ways to run queries and get useful results as quickly as possible.

To put the term “petabyte” into perspective, Puri, an associate professor of computer science, says one petabyte equals 1 million gigabytes. Each gigabyte is equivalent to 1 million kilobytes (KB). The first commercially available floppy disks, which can be considered a precursor to memory cards or USB flash drives, could store 80 KBs.

Puri says different types of maps often need to be combined to answer queries, and the map data he works with includes a collection of spatial shapes and location markers.

“The amount of spatially referenced data now available may be difficult for some people to fully conceptualize, especially when you consider the available sources, such as smartphones, drones and remote sensing satellites,” he says.

But with these massive datasets comes the need to be able to effectively use them, which is why Puri was awarded a grant from the National Science Foundation’s Faculty Early Career Development (CAREER) Program last year. His project, which is expected to receive over $500,000 over the course of five years, is titled: “Communication-efficient and topology-aware designs for geospatial analytics on heterogeneous platforms.”

Earlier this year, he was also awarded a $230,000 three-year NSF grant for a project titled “Approximate nearest neighbor similarity search for large polygonal and trajectory datasets.” Both projects focus on geospatial analytics.

For these projects, Puri is creating algorithms and using high-performance computing with graphics processing units and smart network interface cards that have advanced processing capabilities and allow searches to be conducted faster.

“Just think about some of the basic searches you may do while traveling,” he says. “Your phone can map out driving directions and show the top restaurants in your area, as well as the nearby cities, lakes, roads and different camera views, among other datasets. These basic examples fit with my research, but my projects are even more complex.”

Puri says he is developing algorithms that can use data for everything from geophysical trends and solar physics all the way to social issues that can be documented and analyzed in maps.

For example, climate scientists could potentially use his developments to more effectively monitor the melting of polar sea ice. During the COVID-19 pandemic, his algorithms could have provided more efficient ways to tie in multiple maps and determine disease hotspots related to the virus and its spread.

He says his work will eventually be incorporated into publicly available software for mapping and analytics, and it will most often be used by members of the scientific community and federal agencies.

“Working with big data can lead to some big challenges,” he says. “But my research should eventually make a big difference.”

For more information about Missouri S&T’s computer science department, visit cs.mst.edu.

About Missouri University of Science and Technology
Missouri University of Science and Technology (Missouri S&T) is a STEM-focused research university of over 7,000 students located in Rolla, Missouri. Part of the four-campus University of Missouri System, Missouri S&T offers over 100 degrees in 40 areas of study and is among the nation’s top public universities for salary impact, according to the Wall Street Journal. For more information about Missouri S&T, visit www.mst.edu.