The devastating floods in Italy and recent floods in southern Florida, Appalachia and California are stark proof that it is not just developing countries that are unprepared to deal with the effects of climate change.
Auroop Gangulydistinguished professor of civil and environmental engineering at Northeastern, recently traveled to the United Nations in New York with a team of eight students and researchers to address the gaps in disaster risk reduction—and possible ways to address them.
Upon his return, Ganguly spoke to Northeastern Global News about the complexities of building resilience locally and globally, what has worked so far — and why
Northeastern is well positioned to find solutions with social impact.
Reducing the risk of catastrophic events in a time of extreme weather, aging infrastructure, vulnerable social networks and varying degrees of government responsiveness is one of the greatest challenges facing humanity.
“We call this the convergence of complexities in climate resilience,” says Ganguly, who presented a brief opening comment and an analytical one statement on the subject at a risk reduction hub Event May 17 at UN headquarters—one day before the review of the historic 2015 Sendai Agreement.
A big issue is a gap in data that can inform engineering, urban infrastructure and hydrological responses, Ganguly says.
The data gap
Satellites and other sensors have amassed a huge amount of “big data” from around the world, but data from more localized sensors in urban areas “is relatively small,” he says.
And yet this data is extremely important for understanding how extreme weather and other disasters can affect an area's roads, buildings, bridges and disaster response services.
Historical, pre-satellite information that can help understand climate trends is also missing, Ganguly says.
“If you go far enough back in time, you have almost nothing, except proxies,” he says.
Ganguly says he knows a fellow student and her advisor who went to Egypt and found that the pharaohs had kept records of the Nile River's flow for centuries, but that was an exception to the historical record.
Another issue is that traditional models of land and infrastructure and social systems are often based on imperfect physics and were typically developed when the world was data-poor compared to now, Ganguly says.
Northeast leader in hybrid physics AI
“We don't want to throw everything out there and say, 'This doesn't solve the problem,' because process knowledge and human intelligence built up over decades and even centuries are still very useful,” says Ganguly, who participated in the UN Roundtable with eight students and researchers from the Sustainability and Data Sciences Lab he directs at Northeastern.
“At the same time, we don't want to hold our models hostage” to a time period that had less data than is available now, he says.
One solution is to develop a hybrid physical AI modeling approach that integrates artificial intelligence, machine learning, nonlinear dynamics, and extreme value theory with model simulations based on physics, biogeochemistry, engineering, and social principles “as appropriate and it is valid,” Ganguly told NGN. .
He says Northeastern is well-positioned to engage in this kind of hybrid research because the university has developed a culture of creating interdisciplinary solutions—often with industry, government and business partners—developing cross-cutting expertise in artificial intelligence, earth sciences and engineering.
“We cannot solve the grand challenges of the 21st and 22nd centuries and beyond by remaining in traditional disciplinary silos,” says Ganguly.
What works
While the challenges presented by a rapidly warming planet may seem overwhelming, doing nothing is not an option, at the local, national or global UN level, says Ganguly, co-author of the handbook, “Critical Infrastructure Resilience”.
“We cannot let uncertainty become an excuse for inaction or doom,” he says.
“There are things you can do in a region, within a country, to strengthen your infrastructure, to make your communities more resilient.”
Ganguly, who is co-directing it Global Resilience Institute as well as directing a climate and sustainability focus area within the Institute for Institute of Experiential Intelligencepoints out how India saved an estimated 1 million people in one of its poorest areas from a devastating cyclone in 2019 with a plan that used text messages, police, buses, sirens and volunteers to evacuate people to simple shelters.
He says Northeastern-trained researchers have created startups tackling some of the grand challenges of artificial intelligence and climate change, such as meteorologist Zeus AI, started by former students Thomas Vandal and Kate Duffy, and risQ, risQ. former student Evan Kodra, recently acquired by Fortune 500 company Intercontinental Exchange;
One of his Ph.D. students, Puja Das, presented a case study to the United Nations regarding the use of a NASA grant to develop short-term precipitation forecasting using artificial intelligence and remote sensing technology.
The goal is to improve emergency management and power preparedness in the Appalachian Valley, but the information could also be tailored for the flood-prone regions of Bangladesh and Indonesia, Das said in her report.
In addition to Das, the SDS Lab students and researchers who accompanied Ganguly to the United Nations are: Dian Indrawati, Rachindra Mawalagedara, Aayushi Mishra, Ashis Pal, Arnob Ray, Rishi Sahastrabuddhe and Jack Watson.
Cynthia McCormick Hibbert is a reporter for Northeastern Global News. Email her at c.hibbert@northeastern.edu or connect with her on Twitter @HibbertCynthia.