UMass Amherst Finance Professor Co-Leading Effort to Use Big Data to Combat Catastrophes

Image
Mila Getmansky Sherman
Mila Getmansky Sherman

AMHERST, Mass. – A University of Massachusetts Amherst researcher is co-leading a multi-disciplinary team from around the United States to use big data to identify risk factors across systems for catastrophic events such as major power outages and natural disasters.

Mila Getmansky Sherman, a finance professor in the Isenberg School of Management, and a team she is co-leading recently received a $2.42 million National Science Foundation (NSF) grant under the auspices of the NSF’s Harnessing the Data Revolution Big Idea program.

The Predictive Risk Investigation System for Multilayer Dynamic Interconnection Analysis (PRISM) is a three-year study that aims to harness data in order to look at worst-case scenarios in a catastrophe, the risks associated with them and measure their likelihood. With a team of experts in fields including data science, statistics, computer science, finance, energy, agriculture, ecology, hydrology, climate and space weather, PRISM will integrate data across different areas to improve risk prediction.

“Our hope is that by identifying systemically important critical risks – those that tie together different domains and have the biggest spillover potential – we will have the most widespread impact in terms of controlling those risks,” Getmansky Sherman said. “The multidisciplinary approach is essential, because today’s world is composed of highly interconnected and interdependent systems, and no single expert is equipped to identify the signs of risk or the full impact of catastrophes. Data scientists will help integrate information to find patterns.”

As an example, Getmansky Sherman points to March 1989, when three catastrophic events impacted the same region of the world. A tripped circuit in the Hydro-Quebec power grid left six million people without electricity. A week earlier, an unusually harsh snowstorm crippled the region, and the day before a solar flare and accompanying release of plasma and magnetic field sent a large amount of energy toward the Earth at a million miles an hour.

The complex interactions of these interconnected systems – environmental science, space weather and solar activity – pushed the electric power grid to a tipping point that could not be understood within any single one of those systems, Getmansky Sherman said.

“If systems had been in place to recognize the heightened risks caused by the snowstorm and the solar flare, the 1989 power outage may have been averted or at least minimized,” Getmansky Sherman said. “Similarly, understanding the ways it affected systems such as health care and transportation could help policymakers plan a more effective response.”

 We want to pull information from these diverse domains and put them together, to quantify when critical systems are stressed and strained, and figure out how to prepare,” Getmansky Sherman said.

The researchers plan to assemble large datasets across sectors such as agriculture, climate and energy to create an interactive data library. Once the library is developed, it will use cutting-edge data analysis to identify critical risk factors or quantifiable information associated with risk exposure, particularly for potential catastrophes. The team will also employ machine learning to look for anomalies in the data that might lead to new insights.

The researchers will then focus their efforts on identifying risk interconnections, and systemically important risk indicators across the different domains, in order to both predict potential hazards and to lessen the possible system-wide losses once they’ve occurred. They plan to examine known risk indicators and apply data science to identify new ones.

As part of the project, the researchers will work with stakeholders in the relevant fields, in hopes that policymakers would incorporate their findings. The goal is to help create early warnings for catastrophes and improve preparedness for devastating events worldwide.

“Ultimately we hope to use this information to identify systemically important risk indicators as holistic targets for risk mitigation and in identifying these we hope that policymakers would incorporate them into their planning,” Getmansky Sherman said.

The collaborators on this project in addition to Getmansky Sherman are: Judy Che-Castaldo of the Lincoln Park Zoo; Rémi Cousin of Columbia University’s Earth Institute; Rajesh Gupta of the University of California, San Diego; Ryan McGranaghan of Atmosphere Space Technology Research Associates; Wei Ren of the University of Kentucky; Chaopeng Shen of Pennsylvania State University; and Deborah Sunter of Tufts University.