About This Project

Domoic acid is a potent neurotoxin made by the microscopic diatom Pseudo-nitzschia. It builds up in shellfish, causing poisoning and fishery closures in California. Risk models call 10,000 cells per liter a bloom, counting every cell alike, though some species make far more toxin. Using weekly pier samples of cells and toxin since 2008, this project tests whether counting only the toxic seriata group, then adding silicate shortage, predicts toxicity better than that flat threshold.

Ask the Scientists

What is the context of this research?

Every few years, a microscopic alga called Pseudo-nitzschia blooms off California and makes domoic acid, a toxin that builds up in shellfish and fish. It sickens sea lions and seabirds, and closes crab and shellfish fisheries to keep people safe. Risk models such as California's C-HARM call it a bloom at 10,000 Pseudo-nitzschia cells per liter of seawater. But that number treats every cell the same, and they aren't: one group makes most of the toxin while another is mostly harmless, and cells short of silicate may make more toxin. Since 2008, the California Harmful Algal Bloom Monitoring and Alert Program (CalHABMAP) has sampled seawater weekly at piers, counting both groups and measuring the toxin in the same sample. Its data are public, published by the Southern California Coastal Ocean Observing System (SCCOOS) at erddap.sccoos.org. That gives a rare chance to check the bloom threshold directly against toxin.

What is the significance of this project?

If counting only the toxic group, or also accounting for nutrient stress, predicts toxin much better than counting every cell, monitoring programs could sharpen their warnings using data they already collect, without a single extra sample. That could mean fewer needless alarms and fewer missed toxic events for fisheries, wildlife rescuers and public health. If the simple count holds up, that is useful too: it confirms the current threshold with evidence. Either way, the project answers a question that reaches well beyond algae: how much biological detail does an environmental threshold need before it predicts real outcomes better? Everything will be released openly, so others can repeat the test on their own coasts or apply it to other thresholds.

What are the goals of the project?

The project builds an open, checked dataset of weekly pier samples (cell counts for both groups, toxin, nutrients and temperature), from Southern California's four monitored piers to all 16 California sites; the head-to-head test uses the six piers that record both groups and toxin. It tests three thresholds of rising detail: all Pseudo-nitzschia at 10,000 cells per liter, as the control; the toxic group alone; and the toxic group adjusted for silicate stress and temperature. Each is scored on how well it flags toxic samples, the same week and a week ahead, by hits, false alarms and overall skill, with one common toxin detection limit. The 2014–2016 marine heatwave, with the 2015 bloom, is held out as an independent test: the adjusted threshold is tuned on the other years only, then judged on those, week by week, including how early each threshold raises the alarm. The data, code and results will be published openly, with a free web-based tool for exploring them.