A normal beach day can quickly turn into a public health concern when harmful algae blooms occur in large numbers. Some flowers kill fish and marine mammals, while others make it difficult to breathe air.
A severe outbreak could also shut down shellfish harvesting, tourism, and other coastal businesses that depend on clean water.
The difficult part is timing. By the time people see discolored water or dead fish, the bloom may already be widespread.
Water testing still requires boats, sample collection, lab work, and often a day or more of waiting.
This leaves coastal communities with tough questions. Where should I look first?
The need for early detection
NASA scientists have built an artificial intelligence tool that may help answer that question.
The tool combined data from multiple satellites to detect harmful algal blooms in western Florida and southern California.
Severe bloom events pose health risks and can cost the U.S. coastal economy tens of millions of dollars each year.
Florida communities such as Tampa Bay and Sarasota have been suffering from harmful algae blooms for decades.
Gulf of Mexico algae species Karenia brevis It can cause red tide outbreaks, kill wildlife, pollute beaches, and cause respiratory illnesses for beachgoers and bathers.
On the west coast, False Nichea In recent years, the bloom has poisoned hundreds of dolphins, California sea lions and other marine animals.
Some algae toxins can also become airborne and cause respiratory illnesses in people.
Satellites are already helping track flowers from orbit, but coastal waters are dirty. Sediment, runoff, vegetation, shallow bottoms, and changing light can disrupt visibility.
One satellite may catch one clue. Another person might catch another. The important thing is to put these clues together.
The research team included Michelle Gierach of NASA’s Jet Propulsion Laboratory in Southern California, Kelly Lewis of NASA JPL, and Nick LaHaye of the Spatial Informatics Group.
They compiled findings from five space missions and space instruments, including NASA’s PACE satellite and TROPOMI.
PACE can identify algal communities by characteristics such as size, shape, and pigmentation. TROPOMI can capture the faint red glow that some algae emit during photosynthesis.
Together, these tools can show not only that there is something in the water, but also what type of bloom is forming.
Training AI systems
The team used a self-supervised machine learning system. This means that humans don’t have to label every example first, and the AI learns patterns from large streams of satellite data.
Field and laboratory measurements then helped connect those patterns to real-world situations.
The system was trained on satellite data from 2018 and 2019. Scientists tested in subsequent periods in the same region.
Initial results show that the tool can accurately identify and map harmful blooms containing specific species such as K. brevis, even in complex coastal waters.
“At the very least, tools like this can help us know when and where to collect water samples when an algal bloom outbreak is starting,” Gierach said.
“It can also foster collaboration between experts and encourage new ways to conduct science and deliver decision support products.”
Better warning, fewer blind spots
Health authorities are already testing waters and issuing warnings and beach closures as necessary. NOAA also works with state and local partners to develop forecasts for harmful algal blooms during the bloom season.
AI will not replace these efforts. It might help point them in the right direction faster.
“Applying self-monitoring AI to large streams of satellite data is becoming a powerful tool for generating actionable ocean intelligence,” said Nadia Vinogradova Schiffer, chief program scientist at NASA Headquarters in Washington.
Our goal is to create a map with no gaps. A single satellite can’t see everything, and boat crews can’t test the entire stretch of coastline.
But a combination of space-based observations and water sampling could give authorities a clearer picture of harmful blooms before they develop into a larger crisis.
Broader impact of the research
The team is refining the tool with more data from more coastlines. They also plan to test it in other bodies of water, including lakes.
This research has implications far beyond ocean beaches for drinking water, fisheries, aquaculture and local economies.
“The aim of this initiative is to begin bridging technologies to better serve end users and their needs, from aquaculture to tourism,” Lewis said.
“We’re going to use all of NASA’s assets to do that.”
For coastal communities, the goal is simple. Know faster, respond faster, and waste less time guessing where problems are starting.
The entire study was published in the journal AGU Earth and Space Science.
Image credit: NASA/USGS
—–
Like what you read? Subscribe to our newsletter for fascinating articles, exclusive content and the latest updates.
Check us out on EarthSnap, the free app from Eric Ralls and Earth.com.
—–
