Machine learning using climate pattern data may help predict early harmful algal blooms

Machine learning using climate pattern data may help predict early harmful algal blooms

This satellite image shows a harmful algal bloom over Lake Erie in October 2011. Credit: Florida Institute of Technology

Harmful algal blooms (HABs) are phytoplankton colonies that may harm the aquatic ecosystem and human health. The fish depletion, shellfish shutdowns, and consumer reluctance to eat seafood often caused by these blooms cost the United States an average of $4.6 billion annually.

A new study involving Florida Tech showed that the novel machine learning An approach that uses global climate patterns can improve seasonal forecasting of HABs. The researchers reported that this improvement could mean more time for policy makers to consider and adopt appropriate planning and mitigation strategies, such as harvest restrictions, and help with poison control in shellfish to keep contaminated products out of the market.

“Improve seasonal forecasting for Harmful algal blooms using large-scale climate indicators”, published today in the journal Earth and Environment Communications, found that incorporating global climate patterns into a machine-learning-based framework improved the seasonal forecasting of harmful algal blooms over Lake Erie. The researchers also found that using climate pattern data allowed the improved seasonal forecasting to be completed earlier than usual.

said Pallav Ray, a meteorologist and associate professor of ocean engineering and marine sciences at Florida Tech and co-author of the study.

Traditionally, forecasting for HAB is made using information about chemicals from industries and Agricultural Land that are carried into water bodies through surface runoff. However, HAB predictions using this chemical data as a major driver were found to be less accurate during the extreme boom years. The new research found that when a combination of climate patterns were used in a new machine-learning approach in combination with that chemical data, the prediction accuracy of HAB over Lake Erie greatly improved.

An increasing number of water bodies, including the Indian River Lake, are severely affected by excessive nutrient loading. Lake Erie is affected at the watershed due to the presence of large manufacturing facilities and extensive agricultural land. This has led to an increasingly large and profound prosperity over the past decades.

The study also found that large-scale ocean and atmospheric structures differ significantly during moderate HAB years compared to severe HAB years, indicating the influence of large-scale circulation on the seasonal evolution of HABs over Lake Erie.

“These findings are expected to help extend the lead time and improve seasonal forecasting of HABs not only in Lake Erie but also in other water bodies around the world where chemical data may not be available,” Ray said.

Lead author Mukul Tiwari, an atmospheric scientist at the IBM Thomas J. Watson Research Center in Yorktown Heights, New York, said the research also highlights the importance and value of having a diverse research team. “Any major advances in the prediction of HABs will require a multidisciplinary collaboration among experts in HABs, climatologyand machine learning, computing and data sciences.”

Harmful algal blooms become detectable along western Lake Erie

more information:
Mukul Tewari et al, Improving the seasonal prediction of harmful algal blooms in Lake Erie using large-scale climate indices, Earth and Environment Communications (2022). DOI: 10.1038 / s43247-022-00510-w

the quote: Machine learning using climate pattern data may help predict harmful algal blooms earlier (2022, September 1) Retrieved September 1, 2022 from algal-blooms.html

This document is subject to copyright. Notwithstanding any fair dealing for the purpose of private study or research, no part may be reproduced without written permission. The content is provided for informational purposes only.

Leave a Reply

Your email address will not be published.