The Imaging FlowCytobot (IFCB) takes water samples around the clock and photographs phytoplankton cells floating within. “It’s got a huge amount of potential for figuring out what plankton is in the water column and monitoring for HABs,” says Alexis Fischer, a postdoctoral fellow at the University of California, Santa Cruz with Raphael Kudela. Fischer and colleagues are building a phytoplankton image classifier already capable of identifying more than 90 percent of cells photographed by IFCB at the Santa Cruz Wharf. The bad actors really stand out in the crowd, Fischer says. “Many of the harmful algal bloom species tend to be larger and more uniquely shaped, which fortunately makes it easier for our classifier to distinguish them.” Phytoplankton from San Francisco Bay are more problematic. “There’s a lot of small, rare freshwater phytoplankton that we can’t identify at this point, so we’re going to need to build even larger training sets,” Fischer says. The robots demand intensive oversight to keep running, and cost more than $130,000 a pop. Even so, the IFCBs promise to revolutionize the study of how ocean conditions contribute to phytoplankton blooms. And once Fischer has finished the analysis software, Californians should be able to view the types of algae in offshore waters—plus any brewing blooms—online and in real-time.
Above: FlowCytobot
 
Pearls in the ocean of information that our reporters didn’t want you to miss
 

A marriage of robotics and artificial intelligence promises to automate the detection of harmful algal blooms, which can trigger shellfish harvesting bans and fill wildlife rescue centers with sickened animals.

The Imaging FlowCytobot (IFCB) takes water samples around the clock and photographs phytoplankton cells floating within. “It’s got a huge amount of potential for figuring out what plankton is in the water column and monitoring for HABs,” says Alexis Fischer, a postdoctoral fellow at the University of California, Santa Cruz with Raphael Kudela. Fischer and colleagues are building a phytoplankton image classifier already capable of identifying more than 90 percent of cells photographed by IFCB at the Santa Cruz Wharf. The bad actors really stand out in the crowd, Fischer says. “Many of the harmful algal bloom species tend to be larger and more uniquely shaped, which fortunately makes it easier for our classifier to distinguish them.” Phytoplankton from San Francisco Bay are more problematic. “There’s a lot of small, rare freshwater phytoplankton that we can’t identify at this point, so we’re going to need to build even larger training sets,” Fischer says. The robots demand intensive oversight to keep running, and cost more than $130,000 a pop. Even so, the IFCBs promise to revolutionize the study of how ocean conditions contribute to phytoplankton blooms. And once Fischer has finished the analysis software, Californians should be able to view the types of algae in offshore waters—plus any brewing blooms—online and in real-time.
Above: FlowCytobot
 

About the author

Bay Area native Kathleen M. Wong is a science writer specializing in the natural history and environment of California and the West. With Ariel Rubissow Okamoto, she coauthored Natural History of San Francisco Bay (UC Press, 2011), for which she shared the 2013 Harold Gilliam Award for Excellence in Environmental Reporting. She reports on native species, climate change, and environmental conditions for Estuary, and is the science writer of the University of California Natural Reserve System.

Related Posts

subisdence on 4 delta islands map

Asked to suggest an appropriate future for four Delta islands owned by the Metropolitan Water District, it’s difficult not to want the moon.

Why not richer rice fields, more wetlands, better boat launches, extended trails, even eco-tourism? ? A new survey for the Delta Islands Adaptation Project, funded by a Prop 1 Watershed Restoration Grant, wants the public’s opinion on the importance of 10 possible land-use objectives leading to the selection of one...
chart by Hutton

An examination of 50 years of records reveals an apparent seasonal bias in estimates of freshwater flow from the Delta to the San Francisco Estuary.

The seasonal bias suggests flows were overestimated during the summer months and underestimated during the winter. Estimates of Delta outflow use a measurement called net Delta outflow index (NDOI), which is determined by taking the amount of Delta inflow, from sources such as the Calaveras, Sacramento, and San Joaquin rivers,...
diagram of fish net trawl

Fish monitoring surveys in the San Francisco Estuary net different numbers of different fish species depending upon when and how they sample.

According to a new study published in San Francisco Estuary and Watershed Science, even surveys that target the same part of the water column can come up with significantly different catches. The study’s authors analyzed decades worth of data from the California Department of Fish and Wildlife (CDFW) Fall Midwater...