Abstract
Different techniques exist for determining chlorophyll-a concentration as a proxy of phytoplankton abundance. In this study, a novel method based on the spectral particulate beam-attenuation coefficient (cp) was developed to estimate chlorophyll-a concentrations in oceanic waters. A multi-layer perceptron deep neural network was trained to exploit the spectral features present in cp around the chlorophyll-a absorption peak in the red spectral region. Results show that the model was successful at accurately retrieving chlorophyll-a concentrations using cp in three red spectral bands, irrespective of time or location and over a wide range of chlorophyll-a concentrations.
Highlights
The chlorophyll-a pigment is common to all microscopic algae and its concentration (Chl-a) in natural waters is commonly used as a proxy for phytoplankton abundance
The phytoplankton cells from these samples are concentrated on filters, their pigments extracted using a solvent, and Chl-a quantified using techniques such as in-vitro fluorometry, spectrophotomery or high-performance liquid chromatography (HPLC) [1]
To train the deep neural network a large dataset of particulate beam attenuation coefficients and absorption-based chlorophyll-a estimates was used. cp and particulate absorption data collected during numerous expeditions and processed as previously described [9,11] were extracted from the NASA SeaBASS archive (Table 1, [25])
Summary
The chlorophyll-a pigment is common to all microscopic algae and its concentration (Chl-a) in natural waters is commonly used as a proxy for phytoplankton abundance. Chl-a can be measured in the laboratory on discrete water samples that are collected in the field. The phytoplankton cells from these samples are concentrated on filters, their pigments extracted using a solvent, and Chl-a quantified using techniques such as in-vitro fluorometry, spectrophotomery or high-performance liquid chromatography (HPLC) [1]. Of these laboratory methods, HPLC is currently considered as the gold standard for determining Chl-a (as well as other accessory pigments) on discrete samples and can reach a maximum accuracy of ∼10% and a reproducibility of ∼20% [2]. HPLC has some drawbacks (e.g., high costs both for collecting and analysing samples as well as increased uncertainty from handling samples in laboratories as compared to in-situ automatic methods), which limit the achievable accuracy and the number of samples that can be generated
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
