Drones, AI Data Could Aid Disaster Recovery

MONDAY, MAY 15, 2023

Research from the University of South Wales is utilizing artificial intelligence and drones to enhance structural health monitoring, with the hopes to help areas impacted by natural disasters.

USW reports that the work, conducted by Ph.D. student Mthabisi Adriano Nyathi, Associate Professor of Research and Development Jiping Bai and Associate Professor Ian Wilson, could also help cut the cost of monitoring vital infrastructure.

“In civil engineering, structures can deteriorate over time due to lack of maintenance, which can lead to a decrease in structural integrity and eventual failure,” said Nyathi.

“Through structural health monitoring (SHM), crucial inspection and evaluation of infrastructure systems—such as bridges, railways, tunnels, buildings and dams—is carried out to ensure their safety and reliability. This can prevent catastrophic failures which could result in environmental, societal and economic consequences, and even loss of life.”

According to the release, traditional SHM involves visual inspections to look for signs of deterioration or damage, followed by lab tests. However, these methods can reportedly be expensive, lack consistency and may not provide real-time data.

The USW project is looking to develop an “innovative approach” to the process by deploying AI techniques to quickly identify defects, damage or potential failures that may occur.

“By continuously monitoring and assessing structural integrity, we can make timely repairs and retrofitting existing infrastructure, and extend the lifespan of critical infrastructure to address the challenges posed by climate change and to create a more resilient future for our communities,” Bai said.

“When natural disasters, such as earthquakes, occur, being able to monitor infrastructure remotely could have a range of benefits,” Wilson added.

“The system can be deployed from a safe distance, specialists far from the area can gauge any damage and need for repair, or advise on the need to restrict access to any unsafe structures—the applications could be numerous.”

Nyahti told the university that he has had a “long-standing fascination” with the use of advanced computer application in civil and structural engineering. As a result, he wanted to use his Ph.D. to examine how AI can make the SHM process faster, safer and more robust.

“Beyond the buzz, mystery, and ethical concerns surrounding AI, if it is used responsibly it could have positive socio-economic impacts,” he said.

Recent Climate Resiliency Projects

In June last year, the United States Resiliency Council prepared a report evaluating the comparative seismic performance of four commonly used construction types in typical multifamily developments for the National Ready Mixed Concrete Association (NRMCA) and the RMC Research & Education Foundation.

Earthquake Performance Comparison of Multifamily, Multistory Apartment Building Constructed of Various Materials compared concrete framing using insulated concrete forms (ICF), traditional wood framing, cross laminated timber (CLT) and steel framing. The materials were tested for seismic performance found in Los Angeles, Seattle and Memphis, Tennessee.

The template applied to each method/material entailed a four-level apartment, 360 feet by 68 feet, totaling 98,000 square feet, and was assumed to have been designed to the most current edition of the International Building Code without any special seismic features beyond code requirements.

Then, in September, a team of civil and environmental engineers from the University of Notre Dame was working to make homes more resilient to climate change and worsening natural disasters. The study, led by professor of civil and environmental engineering and earth sciences and global affairs Tracy Kijewski-Correa, aims to create a new framework for community recovery, educate homeowners on risks and encourage incentives for residential upgrades.

To help make structures more climate-resilient, Kijewski-Correa, alongside co-principal investigator and associate professor of political science Debra Javeline and the survey research firm NORC, engaged with residents in Lake Charles, Louisiana—an area hit by five storms back-to-back in 2020.

The researchers believe that the insights and analysis collected from the survey could help inform solutions to flaws in insurance and regulatory systems outpaced by the current rate of climate change.

More recently, in April, researchers at the National Institute of Standards and Technology created a new method of digitally simulating hurricanes with the potential to develop improved guidelines for building designs.

The data was devised using 100 years of hurricane data alongside modern artificial intelligence techniques, demonstrating that simulations can accurately represent the trajectory and wind speeds of a collection of actual storms. NIST researchers used new AI-based tools and years of hurricane records to “tackle the issue from a different angle.”

Rather than having their model mathematically build a storm from the ground up, the team taught it to mimic actual hurricane data with machine learning. With enough quality information to study, machine-learning algorithms can reportedly construct models based on patterns they uncover within datasets that other methods may miss and then simulate specific behaviors, such as the wind strength and movement of a hurricane.


Tagged categories: Asia Pacific; Building science; Climate monitoring; Colleges and Universities; Disasters; Drones; EMEA (Europe, Middle East and Africa); Environmental Controls; Good Technical Practice; Health & Safety; Health and safety; Infrastructure; Infrastructure; Latin America; North America; Program/Project Management; Projects - Commercial; Research; Research and development; Safety; Technology; Z-Continents

Join the Conversation:

Sign in to our community to add your comments.