Combining in situ flow cytometry and artificial neural networks for aquatic systems monitoring

Pereira, G. C.; Ebecken, Nelson F. F.

doi:10.1016/j.eswa.2011.01.140

Cited by 12 publications

(11 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 3(a), for example, presents the clusters of real time data of phytoplankton cells acquired by the CytoBuoy instrument since the red fluorescence signals are the results of chlorophyll-a response to the laser excitation and the side scatter (SSC) is proportional to cytoplasmic granularity of a cell or internal complexity measurement [60]. Individuals of these groups were better characterized by [39] at a single cell and species level. During the studied period, the total phytoplankton concentration varied from 3.30 × 10 2 cells/ml in the winter to 8.66 × 10 2 cells/ml in the summer.…”

Section: Resultsmentioning

confidence: 99%

“…These data-driven modelling tools can be useful in dynamic ecosystems where changing trophic conditions and complex non-linear interactions are expected. Such mo-dels have been used to predict aquatic community abundances [33][34][35][36] or biological pattern recognition [37][38][39]. However, if a neural network is too small, it may never be able to learn the desired function and thus produces unacceptably larger errors.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Genetic Optimization of Artificial Neural Networks to Forecast Virioplankton Abundance from Cytometric Data

Pereira¹,

Oliveira²,

Ebecken³

2013

JILSA

View full text Add to dashboard Cite

Since viruses are able to influence the trophic status and community structure they should be accessed and accounted in ecosystem functioning and management models. So, this work met a set of biological, chemical and physical time series in order to explore the correlations with marine virioplankton community across different trophic gradients. The case studied is the Arraial do Cabo upwelling system, northeast of Rio de Janeiro State in Southeast coast of Brazil. The main goal is to evolve three type of artificial neural network (ANN) by genetic algorithm (GA) optimization to predict virioplankton abundance and dynamic. The input variables range from the abundance of phytoplankton, bacterioplankton and its ratios acquired by one in situ and another ex situ flow cytometers. These data were collected with weekly frequency from August 2006 to June 2007. Our results show viruses being highly correlated to their host, and that GA provided an efficient method of optimizing ANN architectures to predict the virioplankton abundance. The RBF-NN model presented the best performance to an accuracy of 97% for any period in the year. A discussion and ecological interpretations about the system behavior is also provided.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Genetic Optimization of Artificial Neural Networks to Forecast Virioplankton Abundance from Cytometric Data

Pereira¹,

Oliveira²,

Ebecken³

2013

JILSA

View full text Add to dashboard Cite

show abstract

“…However, conventional (i.e., not automated) microscopic analysis is extremely labor intensive and time consuming, which strongly limits the throughput of samples. This way, it is not suitable for the high-frequency monitoring of phytoplankton communities as required in modern day field applications (Walker and Kumagai 2000;Embleton et al 2003;Culverhouse 2007;Pereira and Ebecken 2011).…”

mentioning

confidence: 99%

“…Fluorescence intensity provides information on the fluorescent pigments produced by the cells, whereas the degree of scatter is correlated to the size of the cell (forward scattering) and the cell's granularity or internal complexity (90° light scattering or side scattering). This allows the automated classification of planktonic cells into functional groups, but does not typically allow identification at lower taxonomic levels (Rutten et al 2005;Pereira and Ebecken 2011). Yet, the strength of flow cytometry is its ability to rapidly and automatically analyze many populations of cells (Rutten et al 2005).…”

mentioning

confidence: 99%

Imaging‐in‐Flow: Digital holographic microscopy as a novel tool to detect and classify nanoplanktonic organisms

Zetsche

Mallahi

Dubois

et al. 2014

Limnology & Ocean Methods

View full text Add to dashboard Cite

Traditional taxonomic identification of planktonic organisms is based on light microscopy, which is both time‐ consuming and tedious. In response, novel ways of automated (machine) identification, such as flow cytometry, have been investigated over the last two decades. To improve the taxonomic resolution of particle analysis, recent developments have focused on “imaging‐ in‐ flow,” i.e., the ability to acquire microscopic images of planktonic cells in a flow‐ through mode. Imaging‐ in‐ flow systems are traditionally based on classical brightfield microscopy and are faced with a number of issues that decrease the classification performance and accuracy (e.g., projection variance of cells, migration of cells out of the focus plane). Here, we demonstrate that a combination of digital holographic microscopy (DHM) with imaging‐ in‐ flow can improve the detection and classification of planktonic organisms. In addition to light intensity information, DHM provides quantitative phase information, which generates an additional and independent set of features that can be used in classification algorithms. Moreover, the capability of digitally refocusing greatly increases the depth of field, enables a more accurate focusing of cells, and reduces the effects of position variance. Nanoplanktonic organisms similar in shape were successfully classified from images captured with an off‐ axis DHM with partial coherence. Textural features based on DHM phase information proved more efficient in separating the three tested phytoplankton species compared with shape‐ based features or textural features based on light intensity. An overall classification score of 92.4% demonstrates the potential of holographic‐ based imaging‐ in‐ flow for similar looking organisms in the nanoplankton range.

show abstract

“…However, these instruments produced substantial amounts of data. In this context, models based on cytometric signatures have been successfully developed and applied (Embleton et al, 2003;Kenneth et al, 2008;Pereira and Ebecken, 2011).…”

Section: Introductionmentioning

confidence: 99%

Using in situ flow cytometry images of ciliates and dinoflagellates for aquatic system monitoring

2017

View full text Add to dashboard Cite

Short-period variability in plankton communities is poorly documented, especially for variations occurring in specific groups in the assemblage because traditional analysis is laborious and time-consuming. Moreover, it does not allow the high sampling frequency required for decision making. To overcome this limitation, we tested the submersible CytoSub flow cytometer. This device was anchored at a distance of approximately 10 metres from the low tide line at a depth of 1.5 metres for 12 hours to monitor the plankton at a site in the biological reserve of Barra da Tijuca beach, Rio de Janeiro. Data analysis was performed with two-dimensional scatter plots, individual pulse shapes and micro images acquisition. High-frequency monitoring results of two interesting groups are shown. The abundance and carbon biomass of ciliates were relatively stable, whereas those from dinoflagellates were highly variable along the day. The linear regression of biovolume measures between classical microscopy and in situ flow cytometry demonstrate high degree of adjustment. Despite the success of the trial and the promising results obtained, the large volume of images generated by the method also creates a need to develop pattern recognition models for automatic classification of in situ cytometric images.Keywords: aquatic systems, microbial ecology, in situ flow cytometry, method. Usando imagem de citometria de fluxo in situ de ciliados e dinoflagelados para o monitoramento de sistemas aquáticos ResumoA variabilidade de curto período em comunidades do plâncton é pouco documentada, especialmente as variações que ocorrem em grupos específicos das assembleias por causa das análises tradicionais serem muito trabalhosas e demoradas. Além disso, não permitem que a alta frequência amostral necessária para a tomada de decisão. Para superar esta limitação, nós testamos o CytoSub, um citômetro de fluxo submersível. Este aparelho foi ancorado a aproximadamente 10 metros de distância da linha de maré baixa a uma profundidade de 1,5 metros por 12 horas para monitorar o plâncton em um sítio da reserva biológica da praia da Barra da Tijuca, Rio de Janeiro. A análise dos dados foi realizada a partir de gráficos de dispersão bidimensionais, pelas assinaturas ópticas individuais escaneadas (pulse shape profile) e aquisição de micro imagens. Resultados do monitoramento de alta frequência de dois grupos interessantes são apresentados.A abundância e a biomassa de carbono de um grupo de ciliados foram relativamente estáveis, ao passo que o grupo de dinoflagelado, foi altamente variável ao longo do dia. O modelo de regressão linear das medidas de biovolume entre a clássica microscopia e a citometria de fluxo in situ apresentou alto grau de ajustamento. Apesar do sucesso deste ensaio e dos resultados promissores obtidos, o grande volume de imagens geradas por este método também gerou a necessidade de se desenvolver modelos de reconhecimento de padrões para a classificação automática de imagens de citometria in situ.Palavras-chave: sistemas aquáticos...

show abstract

Combining in situ flow cytometry and artificial neural networks for aquatic systems monitoring

Cited by 12 publications

References 26 publications

Genetic Optimization of Artificial Neural Networks to Forecast Virioplankton Abundance from Cytometric Data

Genetic Optimization of Artificial Neural Networks to Forecast Virioplankton Abundance from Cytometric Data

Imaging‐in‐Flow: Digital holographic microscopy as a novel tool to detect and classify nanoplanktonic organisms

Using in situ flow cytometry images of ciliates and dinoflagellates for aquatic system monitoring

Contact Info

Product

Resources

About