1
|
Fournier C, Quesada A, Cirés S, Saberioon M. Discriminating bloom-forming cyanobacteria using lab-based hyperspectral imagery and machine learning: Validation with toxic species under environmental ranges. THE SCIENCE OF THE TOTAL ENVIRONMENT 2024; 932:172741. [PMID: 38679105 DOI: 10.1016/j.scitotenv.2024.172741] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/07/2023] [Revised: 03/28/2024] [Accepted: 04/22/2024] [Indexed: 05/01/2024]
Abstract
Cyanobacteria are major contributors to algal blooms in inland waters, threatening ecosystem function and water uses, especially when toxin-producing strains dominate. Here, we examine 140 hyperspectral (HS) images of five representatives of the widespread, potentially toxin-producing and bloom-forming genera Microcystis, Planktothrix, Aphanizomenon, Chrysosporum and Dolichospermum, to determine the potential of utilizing visible and near-infrared (VIS/NIR) reflectance for their discrimination. Cultures were grown under various light and nutrient conditions to induce a wide range of pigment and spectral variability, mimicking variations potentially found in natural environments. Importantly, we assumed a simplified scenario where all spectral variability was derived from cyanobacteria. Throughout the cyanobacterial life cycle, multiple HS images were acquired along with extractions of chlorophyll a and phycocyanin. Images were calibrated and average spectra from the region of interest were extracted using k-means algorithm. The spectral data were pre-processed with seven methods for subsequent integration into Random Forest models, whose performances were evaluated with different metrics on the training, validation and testing sets. Successful classification rates close to 90 % were achieved using either the first or second derivative along with spectral smoothing, identifying important wavelengths in both the VIS and NIR. Microcystis and Chrysosporum were the genera achieving the highest accuracy (>95 %), followed by Planktothrix (79 %), and finally Dolichospermum and Aphanizomenon (>50 %). The potential of HS imagery to discriminate among toxic cyanobacteria is discussed in the context of advanced monitoring, aiming to enhance remote sensing capabilities and risk predictions for water bodies affected by cyanobacterial harmful algal blooms.
Collapse
Affiliation(s)
- Claudia Fournier
- Departamento de Biología, Universidad Autónoma de Madrid, 28049 Madrid, Spain
| | - Antonio Quesada
- Departamento de Biología, Universidad Autónoma de Madrid, 28049 Madrid, Spain.
| | - Samuel Cirés
- Departamento de Biología, Universidad Autónoma de Madrid, 28049 Madrid, Spain
| | - Mohammadmehdi Saberioon
- Section 1.4 Remote Sensing and Geoinformatics, German Research Centre for Geosciences (GFZ), Telegrafenberg, 14473 Potsdam, Germany
| |
Collapse
|
2
|
Santos-Silva RDD, Severiano JDS, Chia MA, Queiroz TM, Cordeiro-Araújo MK, Barbosa JEDL. Unveiling the link between Raphidiopsis raciborskii blooms and saxitoxin levels: Evaluating water quality in tropical reservoirs, Brazil. ENVIRONMENTAL POLLUTION (BARKING, ESSEX : 1987) 2024; 344:123401. [PMID: 38244903 DOI: 10.1016/j.envpol.2024.123401] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/07/2023] [Revised: 01/16/2024] [Accepted: 01/17/2024] [Indexed: 01/22/2024]
Abstract
The proliferation of Raphidiopsis raciborskii blooms has sparked concerns regarding potential human exposure to heightened saxitoxins (STXs) levels. Thus, comprehending how environmental elements drive the proliferation of this STXs-producing species can aid in predicting human exposure risks. This study aimed to explore the link between cyanobacteria R. raciborskii, STXs cyanotoxins, and environmental factors in 37 public supply reservoirs in the tropical region and assess potential health hazards these toxins pose in the reservoir waters. A Structural Equation Model was used to assess the impact of environmental factors (water volume and physical and chemical variables) on R. raciborskii biomass and STXs levels. Furthermore, the potential risk of STXs exposure from consuming untreated reservoir water was evaluated. Lastly, the cumulative distribution function (CDF) of STXs across the reservoirs was computed. Our findings revealed a correlation between R. raciborskii biomass and STXs concentrations. Total phosphorus emerged as a critical environmental factor positively influencing species biomass and indirectly affecting STXs levels. pH significantly influenced STXs concentrations, indicating different factors influencing R. raciborskii biomass and STXs. Significantly, for the first time, the risk of STXs exposure was gauged using the risk quotient (HQ) for untreated water consumption from public supply reservoirs in Brazil's semi-arid region. Although the exposure risks were generally low to moderate, the CDF underscored the risk of chronic exposure due to low toxin concentrations in over 90% of samples. These outcomes emphasize the potential expansion of R. raciborskii in tropical settings due to increased phosphorus, amplifying waterborne STXs levels and associated intoxication risks. Thus, this study reinforces the importance of nutrient control, particularly phosphorus regulation, as a mitigation strategy against R. raciborskii blooms and reducing STXs intoxication hazards.
Collapse
Affiliation(s)
- Ranielle Daiana Dos Santos-Silva
- Ecology Program, Department of Biology, State University of Paraíba - UEPB, Rua Baraúnas, nº. 351, Universitario, 58.429-500, Campina Grande, PB, Brazil
| | - Juliana Dos Santos Severiano
- Ecology Program, Department of Biology, State University of Paraíba - UEPB, Rua Baraúnas, nº. 351, Universitario, 58.429-500, Campina Grande, PB, Brazil.
| | - Mathias Ahii Chia
- Department of Botany, Ahmadu University Bello, 81 0001, Zaria, Nigeria; Department of Ecology, University of Brasília - UnB, Graduate Program in Ecology. Institute of Biological Sciences - IB, Asa Norte, DF, 70910-900, Brasilia, Brazil
| | - Tatiane Medeiros Queiroz
- Ecology Program, Department of Biology, State University of Paraíba - UEPB, Rua Baraúnas, nº. 351, Universitario, 58.429-500, Campina Grande, PB, Brazil
| | - Micheline Kézia Cordeiro-Araújo
- Department of Cellular Biology, University of Brasília - UnB, Graduate Program in Microbial Biology. Institute of Biological Sciences - IB, Bloco E, s/n, Asa Norte, DF, 70910-900, Brasilia, Brazil
| | - José Etham de Lucena Barbosa
- Ecology Program, Department of Biology, State University of Paraíba - UEPB, Rua Baraúnas, nº. 351, Universitario, 58.429-500, Campina Grande, PB, Brazil
| |
Collapse
|