Vertical distributions of blooming cyanobacteria populations in a freshwater lake from LIDAR observations

Moore, Tim; Churnside, James H.; Sullivan, James; Twardowski, Michael; Nayak, Aditya R.; McFarland, Malcolm; Stockley, Nicole; Gould, Richard W.; Johengen, Thomas H.; Ruberg, Steven A.

doi:10.1016/j.rse.2019.02.025

Cited by 40 publications

(28 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among these in situ imaging methods, digital inline holography (DIH) has emerged as a powerful, low cost, and highly compact tool for in situ mapping of particle and plankton distributions (Pfitsch et al 2007; Graham and Nimmo Smith 2010; Bochdansky et al 2013). Sample in situ aquatic applications of DIH include mapping harmful algal blooms (Moore et al 2017, 2019), thin layer research (Talapatra et al 2013), characterizing particle orientation (Nayak et al 2018 a ), and microbial motility studies (Kühn et al 2014). DIH employs a laser beam to illuminate the particle field and acquires an image of the patterns (hologram) generated from the interference between the scattered light from the particles and non‐scattered portion of the laser with a digital camera sensor (Garcia‐Sucerquia et al 2006).…”

Section: Figurementioning

confidence: 99%

Automated plankton classification from holographic imagery with deep convolutional neural networks

Guo

Nyman

Nayak

et al. 2020

Limnology & Ocean Methods

Self Cite

View full text Add to dashboard Cite

In situ digital inline holography is a technique which can be used to acquire high‐resolution imagery of plankton and examine their spatial and temporal distributions within the water column in a nonintrusive manner. However, for effective expert identification of an organism from digital holographic imagery, it is necessary to apply a computationally expensive numerical reconstruction algorithm. This lengthy process inhibits real‐time monitoring of plankton distributions. Deep learning methods, such as convolutional neural networks, applied to interference patterns of different organisms from minimally processed holograms can eliminate the need for reconstruction and accomplish real‐time computation. In this article, we integrate deep learning methods with digital inline holography to create a rapid and accurate plankton classification network for 10 classes of organisms that are commonly seen in our data sets. We describe the procedure from preprocessing to classification. Our network achieves 93.8% accuracy when applied to a manually classified testing data set. Upon further application of a probability filter to eliminate false classification, the average precision and recall are 96.8% and 95.0%, respectively. Furthermore, the network was applied to 7500 in situ holograms collected at East Sound in Washington during a vertical profile to characterize depth distribution of the local diatoms. The results are in agreement with simultaneously recorded independent chlorophyll concentration depth profiles. This lightweight network exemplifies its capability for real‐time, high‐accuracy plankton classification and it has the potential to be deployed on imaging instruments for long‐term in situ plankton monitoring.

show abstract

Section: Figurementioning

confidence: 99%

Automated plankton classification from holographic imagery with deep convolutional neural networks

Guo

Nyman

Nayak

et al. 2020

Limnology & Ocean Methods

Self Cite

View full text Add to dashboard Cite

show abstract

“…For example, probes equipped with chlorophyll-a/phycocyanin and other sensors that can be coupled with autonomous monitoring platforms are now available for punctual or continuous estimations of cyanobacteria biomasses in the water column [ 6 , 7 ]. In the same way, the use of remote sensing [ 8 ] and LIDAR [ 9 ] allows to estimate the horizontal and/or vertical distribution of the cyanobacterial biomass in a lake. Some of these tools remain under development but are increasingly used for cyanobacteria monitoring, particularly in developed countries.…”

Section: Introductionmentioning

confidence: 99%

Can participatory approaches strengthen the monitoring of cyanobacterial blooms in developing countries? Results from a pilot study conducted in the Lagoon Aghien (Ivory Coast)

et al. 2020

View full text Add to dashboard Cite

Monitoring of cyanobacteria in freshwater ecosystems is a complex task, which is time consuming and expensive due to the chaotic population dynamics and highly heterogeneous distribution of cyanobacteria populations in water bodies. The financial cost constitutes a strong limitation for the implementation of long-term monitoring programs in developing countries, particularly in Africa. The work presented here was performed in the framework of an international project addressing the sustainable monitoring and management of surface water resources used for the production of drinking water in three African countries. We tested the potential of a citizen approach for monitoring cyanobacterial blooms, which are a growing threat to the drinking water supply. This pilot study was designed, implemented and evaluated in close interaction with the Pasteur Institute of the Ivory Coast and with the populations of three villages located on the shoreline of a freshwater lagoon located near Abidjan city. Based on the use of a smartphone application, the citizens of the three villages were invited to report water color changes, as these changes could reflect cyanobacteria proliferations. A two-year experimentation period has shown that it is possible to mobilize the local populations to monitor cyanobacterial blooms. The data collected by citizens were consistent with the data obtained by a classical monitoring of cyanobacteria performed over seven months, but it appeared that new approaches were needed to validate the citizen data. This participatory approach also provided great improvements to the understanding and awareness of local populations regarding water quality and cyanobacterial bloom issues. Finally, we discuss some of the difficulties and limitations of our participatory monitoring approach that should be considered by further implementations. Despite these difficulties, our work

show abstract

“…The most interesting instrument, providing active remote sensing of phytoplankton and dissolved organic matter (DOM) fluorescence, is a laser remote sensing spectrometer (LIDAR) used in shipborne laboratories [154][155][156][157][158][159]. A LIDAR fluorosensor for marine and freshwater applications is remotely excite and detect laser-induced fluorescence emissions by chromophore groups belonging to different species present in the water body.…”

Section: Remote Sensingmentioning

confidence: 99%

Studying Cyanobacteria by Means of Fluorescence Methods: A Review

Grigoryeva¹

2020

Fluorescence Methods for Investigation of Living Cells and Microorganisms

View full text Add to dashboard Cite

Self-fluorescence is a powerful tool for investigation of living photosynthetic microorganisms. Since the physiological state of such microorganisms is closely related to the operation and activity of photosynthetic system; thus, any variations in spectroscopic properties of their self-fluorescence indicate the changes in their physiological state. Cyanobacteria (or blue green alga) are one of the most widespread photosynthetic organisms in nature, and the ecological aspect in their investigation is quite valuable. On the other hand, thousands of strains belonging to different cyanobacterial species are cultivated in biolaboratories all over the world for different biotechnological applications such as biofuel cells, food production, pharmaceuticals, and fertilizers. Thus, the novel noninvasive methods of their investigation are quite important for on-line monitoring of cyanobacterial cultures. In this chapter, several fluorescence techniques are presented for investigation of living cyanobacterial cells and cultures.

show abstract

Vertical distributions of blooming cyanobacteria populations in a freshwater lake from LIDAR observations

Cited by 40 publications

References 69 publications

Automated plankton classification from holographic imagery with deep convolutional neural networks

Automated plankton classification from holographic imagery with deep convolutional neural networks

Can participatory approaches strengthen the monitoring of cyanobacterial blooms in developing countries? Results from a pilot study conducted in the Lagoon Aghien (Ivory Coast)

Studying Cyanobacteria by Means of Fluorescence Methods: A Review

Contact Info

Product

Resources

About