Coast Guard computer models aid search, rescue

PURDUE (US) — Computer modeling will help the U.S. Coast analyze past Great Lakes search-and-rescue operations and plan for possible future risks related to closures and shifting resource allocations.

The agency is required to stand watch and supervise search-and-rescue cases for mariners in distress. Some of the stations are staffed by volunteers in the Coast Guard Auxiliary, and due to attrition of the volunteer service, it is important for officials to understand the potential impact of closing units, says Coast Guard Lt. Comdr. Ben Maule.

The visualization was designed to help assess the effects of hypothetical small-boat station closures on response time, potential lives saved, and property lost, while highlighting regions that would be exposed to greater risk.


It also enables a thorough assessment of all search-and-rescue operations conducted by each Coast Guard station in the Great Lakes region, says David S. Ebert, professor of electrical and computer engineering at Purdue University.

Ebert presented a research paper on the system during IEEE VisWeek this month.

“You can simulate who would respond, whether the responding station has enough capacity, and visualize the data with color-coded maps,” says Ebert, director of Visual Analytics for Command, Control and Interoperability Environments, or VACCINE, a U.S. Department of Homeland Security Center of Excellence.

“Using visualizations we can see where there is excess capacity and the best resource allocation based on historical search-and-rescue data from the past three years,” Ebert says.

The program, “Coast Guard Search and Rescue Visual Analytics,” runs on an ordinary computer or laptop and is being used by the Coast Guard’s Atlantic Area and Ninth District commands, which are responsible for the agency’s oversight on the Great Lakes.

“The Coast Guard came to us with five questions,” Ebert says. “Instead of just answering those questions, we gave them a system that allows them to continuously ask questions and add new data.”

The ongoing project currently combines advanced visualization methods showing patterns regarding seasonal search-and-rescue patterns and for specific days of the week, time of day, and holidays.

“Our results show how our system can be used as an effective risk-assessment tool when examining various mitigation strategies to a known or emergent problem,” Ebert says. “Before this system was developed, Coast Guard officials explored possible mitigation strategies, including the implementation of seasonal or weekend-only auxiliary duty stations, but the sheer volume of data and information inhibited the efficient processing of the data.”

The work is funded by the Coast Guard and U.S. Department of Homeland Security.

More news from Purdue University: