TACLS, a new flood-detection system, could give communities faster warnings before flash floods strike. Known as the Transient Artifact and Continuous Learning System, the software uses satellites and machine learning to identify areas at risk of flooding sooner, helping the National Weather Service (NWS) make quicker decisions about issuing flash flood alerts.
The threat is significant. Floods are the second-deadliest type of weather event in the United States and the deadliest globally. Just 6 inches of fast-flowing water can knock an adult off their feet, 12 inches can lift a car, and 2 feet can move larger vehicles such as trucks and SUVs. A warming climate is producing more instances of extreme rainfall across the US, creating further opportunities for floods to occur. The deadly flash flooding in Nepal in August, caused by a glacier collapse, underlined the power of water to devastate communities worldwide.
When minutes matter
The danger of slow warnings became clear in Lanesville, a rural town in southern Indiana about 15 miles from the Kentucky border. On the morning of 9 June, resident Laura Lin was on a video call at home when heavy rain began flooding her yard. She spotted pieces of her wooden barn floating in the water, closed her laptop, gathered her children and left. The family reached a neighbour’s house safely, but Lanesville received over 8 inches of rain within a few hours that day, well above the threshold for what is considered heavy rainfall. The water had receded a few hours later.
Lin says the urgent alerts arrived far too late. By the time messages advising people to get on their roofs were sent out, with boats being dispatched, residents were already flooded. TACLS has the potential to change that timeline.
How flood alerts work
Weather forecast offices are responsible for issuing severe weather alerts, including flash flood warnings. There are 122 of them throughout the US and its territories, according to Jayme Laber, senior service hydrologist for the NWS Weather Forecast Office in Oxnard, California, which oversees the Los Angeles area. Currently, staff use a variety of tools to monitor flood conditions, relying on rain and stream gauges to indicate how much water is in a given location at any moment.
Laber worked closely on the TACLS project alongside Ivory Small, science and operations officer at the NWS San Diego Weather Forecast Office, and a broader team of scientists and researchers. They hope the system will streamline weather alerts and improve the speed and accuracy of warnings.
Small describes the potential impact in stark terms. Without TACLS, a storm moving into an area could prove fatal. With TACLS, forecasters can issue warnings earlier, giving people the time they need to respond. The system is designed to spot flood-prone areas sooner than existing methods, addressing one of the central weaknesses in current flash flood forecasting: warnings that arrive after water has already reached homes and roads.
Source
Image: theverge.com
