Predicting Toxic Algae Blooms with AI Modeling

According to the Los Alamos Reporter, scientists from the Los Alamos National Laboratory plan to use artificial intelligence modeling to forecast toxic algal blooms, which “[f]ueled by climate change and rising water temperatures … have grown in intensity and frequency” and “have now been reported in all 50 U.S. states.” Perhaps the most well-known occurrence of these harmful algal blooms, or HABs, happened in 2014, when dangerous toxin levels in Lake Erie forced Toledo, Ohio, to shut down the drinking water supply of a half-million residents for three days. Just last month, Clear Lake in California was in the news for its own blue-green algal bloom, which some fear will impact summer tourism activities.

“For decades, scientists have understood that elevated water temperatures, combined with sudden infusions of nutrients (often phosphorous and nitrogen runoff from industrial farming), tend to precede a HAB event …. But what causes toxic cyanobacteria to prevail in these freshwater ecosystems has proved challenging to understand” because they are “complex ecosystems influenced by hundreds — sometimes thousands — of other microorganisms,” the Los Alamos Reporter article reads. Armed with masses of data on HABs collected since 1954 by a variety of organizations across the nation and the world, the scientists plan to feed existing yet disparate information into a data learning model and use AI to decipher and analyze it.

“Such a model could then be used to forecast algal blooms, and possibly even predict how climate change will alter their intensity and frequency in the future,” said Babetta Marrone, senior scientist at the LANL and the project’s team lead, in a press release.