Application of a convolutional neural network to improve automated early warning of harmful algal blooms

• Published in: Environmental science and pollution research international Vol. 28; no. 22; pp. 28544 - 28555
• Main Authors: Henrichs, Darren W., Anglès, Sílvia, Gaonkar, Chetan C., Campbell, Lisa
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.06.2021; Springer Nature B.V
• Subjects: Algae; Algal blooms; Aquatic Pollution; Artificial neural networks; Atmospheric Protection/Air Quality Control/Air Pollution; Automation; Blooms (microorganisms); Classifiers; Data acquisition; Dinoflagellates; Dinophysis ovum; Early warning systems; Earth and Environmental Science; Ecotoxicology; Environment; Environmental Chemistry; Environmental Health; Environmental science; Eutrophication; Image acquisition; Lead time; Neural networks; Plankton; Research Article; Species classification; Toxicity; Waste Water Technology; Water Management; Water Pollution Control; HAB; CNN; Gulf of Mexico; Imaging FlowCytobot; Prorocentrum texanum; Dinophysis ovum; Karenia brevis
• ISSN: 0944-1344; 1614-7499
• DOI: 10.1007/s11356-021-12471-2

Continuous monitoring and early warning together represent an important mitigation strategy for harmful algal blooms (HAB). The coast of Texas experiences periodic blooms of three HAB dinoflagellates: Karenia brevis , Dinophysis ovum , and Prorocentrum texanum . A plankton image data set acquired by an Imaging FlowCytobot over a decade of operation was used to train and evaluate two new automated image classifiers. A 112 class, random forest classifier (RF_112) and a 112 class, convolutional neural network classifier (CNN_112) were developed and compared with an existing, 54 class, random forest classifier (RF_54) already in use as an early warning notification system. Both 112 class classifiers exhibited improved performance over the RF_54 classifier when tested on three different HAB species with the CNN_112 classifier producing fewer false positives and false negatives in most of the cases tested. For K. brevis and P. texanum , the current threshold of 2 cells . mL −1 was identified as the best threshold to minimize the number of false positives and false negatives. For D. ovum , a threshold of 1 cell . mL −1 was found to produce the best results with regard to the number of false positives/negatives. A lower threshold will result in earlier notification of an increase in cell concentration and will provide state health managers with increased lead time to prepare for an impending HAB.