• Journal of Korean Society on Water Environment
• /
• v.37 no.4
• /
• pp.275-285
• /
• 2021

Algal bloom is an important issue in maintaining the safety of the drinking water supply system. Fast detection and classification of algae images are essential for the management of algal blooms. Conventional visual identification using a microscope is a labor-intensive and time-consuming method that often requires several hours to several days in order to obtain analysis results from field water samples. In recent decades, various deep learning algorithms have been developed and widely used in object detection studies. YOLO is a state-of-the-art deep learning algorithm. In this study the third version of the YOLO algorithm, namely, YOLOv3, was used to develop an algae image detection model. YOLOv3 is one of the most representative one-stage object detection algorithms with faster inference time, which is an important benefit of YOLO. A total of 1,114 algae images for 30 genera collected by microscope were used to develop the YOLOv3 algae image detection model. The algae images were divided into four groups with five, 10, 20, and 30 genera for training and testing the model. The mean average precision (mAP) was 81, 70, 52, and 41 for data sets with five, 10, 20, and 30 genera, respectively. The precision was higher than 0.8 for all four image groups. These results show the practical applicability of the deep learning algorithm, YOLOv3, for algae image detection.

• Membrane and Water Treatment
• /
• v.9 no.6
• /
• pp.447-454
• /
• 2018

Although flotation techniques are often used for the removal of algal particles, the practicality of algae-harvesting technologies is limited owing to the complex and expensive facilities and equipment required for chemical coagulation. Here, we examined the feasibility of an approach to separating algal particles from water bodies without the need for chemical coagulants, depending on the condition of the algae, and to determine the optimal conditions. Using Anabaena sp., a cyanobacterium causes algal blooms in lakes, we stimulated auto-flocculation in algal particles without coagulants and conducted solid-liquid separation experiments of algal particles under various conditions. The six cultivation columns included in our analysis comprised four factors: Water temperature, light intensity, nutrients, and carbon source; auto-flocculation was induced under all treatments, with the exception of the treatment involving no limits to all factors, and algal particles were well-settled under all conditions for which auto-flocculation occurred. Meanwhile, flotation removal of auto-flocculated algal particles was attained only when nutrients were blocked after algae were grown in an optimal medium. However, no significant differences were detected between the functional groups of the extracellular polymeric substances (EPSs) of floated and settled algal particles in the FT-IR peak, which can cause attachment by collision with micro-bubbles.

• Journal of the korean society of oceanography
• /
• v.34 no.3
• /
• pp.167-171
• /
• 1999

Since toxic Alexandrium catenella and non-toxic A. fraterculus are morphologically similar, they are difficult to discriminate under the light microscope. However, a novel technology, such as fluorescein isothiocyanate (FITC)-conjugated lectin probes enables easy and rapid differentiation. Toxic A. catenella bound seven different lectins, whereas the non-toxic A. fratercuzus did not bind Arachis hypogaea (PNA) lectin. In addition, Pseudo-nitrschia species in this study were also difficult to identify to species level with light microscope techniques, but it was possible to classify them using fluorescent lectins. Pseudo-nitzschia multistriata, P. subfraudulenta and P. pungens bound Canavalia ensiformis (ConA), whereas P. subpaclfica did not, and P. pungens also bound Ricinus communis (RCA). These results imply that lectin could be used as a critical tool in the differentiation of P. multistriata, P. subfraudulenta and P. pungens. However, P. subpacifica was not differentiated by the lectins tested. Therefore, it isconcluded that lectin probes are useful for discriminating toxic A. catenella from non-toxic A. fraterculus, and for the identification of some Pseudo-nitzschia species. In addition, this method has a great potential to speed and detection between non-toxic and toxic harmful algal blooms (HABs) in Korean biotoxin monitoring systems.

• ALGAE
• /
• v.20 no.2
• /
• pp.113-120
• /
• 2005

The freshwater blooms mainly blue-green algal blooms occur frequently in the lower Naktong River in summer, which provoke many socio-economical problems; therefore, the early detection of bloom events are demanding through the quantitative and qualitative analyses of blue green algal species. The in vivo fluorescence properties of cultured strains of Microcystis aeruginosa, M. viridis, M. wesenbergii, M. ichthyoblabe, Anabaena cylindrica, A. flos-aquae, and Synedra sp. were investigated. Wild phytoplankton communities of the lower Naktong River were also monitored at four stations in terms of their standing stocks, biomass and fluorescence properties compared with its absorption spectram. The 77K fluorescence emission spectra of each cultured strains normalized at 620 nm was very specific and enabled to detect of blue green algal biomass qualitatively and quantitatively. The relative chlorophyll a concentration determined by chlorophyll fluorescence analysis method showed significant relationship with chlorophyll a concentration determined by solvent extraction method ($R^2$ = 0.906), and the blue-green algal cell number determined by microscopic observation ($R^2$ = 0.588), which gives insight into applications to early detection of blue green algal bloom.

• ALGAE
• /
• v.31 no.4
• /
• pp.373-378
• /
• 2016

Cochlodinium polykrikoides is a red-tide forming dinoflagellate that causes significant worldwide impacts on aquaculture industries and the marine ecosystem. There have been extensive studies on managing and preventing C. polykrikoides blooms, but it has been difficult to identify an effective method to control the bloom development. There is also limited genome information on the molecular mechanisms involved in its various ecophysiology and metabolism processes. Thus, comprehensive genome information is required to better understand harmful algal blooms caused by C. polykrikoides. We estimated the C. polykrikoides genome size using flow cytometry, with detection of the fluorescence of DNA stained with propidium iodide (PI). The nuclear genome size of C. polykrikoides was 100.97 Gb, as calculated by comparing its mean fluorescence intensity (MFI) to the MFI of Mus musculus, which is 2.8 Gb. The exceptionally large genome size of C. polykrikoides might indicate its complex physiological and metabolic characteristics. Our optimized protocol for estimating the nuclear genome size of a dinoflagellate using flow cytometry with PI can be applied in studies of other marine organisms.

• Korean Journal of Environmental Biology
• /
• v.31 no.4
• /
• pp.233-242
• /
• 2013

Cyanobacteria (blue-green algae) are not only the first oxygenic organisms on earth but also the foremost primary producers in aquatic environment. Massive growth of cyanobacteria, in eutrophic waters, usually changes the water colour to green and is called as algal (cyanobacterial) bloom or green tide. Cyanobacterial blooms are a result of high levels of primary production by certain species such as Microcystis sp., Anabaena sp., Oscillatoria sp., Aphanizomenon sp. and Phormidium sp. These cyanobacterial species can produce hepatotoxins or neurotoxins as well as malodorous compounds like geosmin and 2-methylisoborneol (MIB). In order to solve the nationwide problem of hazardous cyanobacterial blooms in Korea, the following technically and strategically sound approaches need to be developed. 1) As a long-term strategy, reduction of the nutrients such as phosphorus and nitrogen in our water bodies to below permitted levels. 2) As a short term strategy, field application of combination of already established bloom remediation techniques. 3) Development of emerging convergence technologies based on information and communication technology (ICT), environmental technology (ET) and biotechnology (BT). 4) Finally, strengthening education and creating awareness among students, public and industry for effective reduction of pollution discharge. Considering their ecological roles, a complete elimination of cyanobacteria is not desirable. Hence a holistic approach mentioned above in combination to addressing the issue from a social perspective with cooperation from public, government, industry, academic and research institutions is more pragmatic and desirable management strategy.

• Korean Journal of Ecology and Environment
• /
• v.42 no.1
• /
• pp.67-74
• /
• 2009

To study the influence of the rotifer Brachionus calyciflorus on harmful algal bloom suppression, we focused on assessing the rotifer's abilities using several prey species : Microcystis aeruginosa, Synechocystis sp., Chlorella vulgaris and Coelastrum sp. of the warm-weather species and the cold-weather centric diatom Stephanodiscus hantzchii. Grazing effects and growth rates of rotifers B. calyciflorus were 94.5% and $1.29d^{-1}$, respectively, for Synechocystis sp., 87.4% and $0.60d^{-1}$, respectively, for M. aeruginosa, 95.2% and $0.65d^{-1}$, respectively, for C. $vulgaris^{TM}$, 78.6% and $0.45d^{-1}$, respectively, for C. vulgaris UTEX., 86.5% and $0.99d^{-1}$, respectively, for Coelastrum sp., and 82.6% and $0.40d^{-1}$, respectively, for S. hantzchii. Of these, although the growth of Synechocystis and Coelastrum was effectively suppressed by rotifer grazing, efficient suppression effects on Stephanodiscus blooms were unexpected. The present study revealed that reproduction of B. calyciflorus was greatly influenced by its food types in the initial stages and the efficiencies of bio-agents as sole food sources vary depending on the target algae and the agent.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.2
• /
• pp.331-336
• /
• 2012

Red tide is a temporary natural phenomenon involving harmful algal blooms (HABs) in company with a changing sea color from normal to red or reddish brown, and which has a bad influence on coast environments and sea ecosystems. The HABs have inflicted massive mortality on fin fish and shellfish, damaging the economies of fisheries for almost every year from 1990 in South Korea. There have been many studies on red tide due to increasing damage from red tide on fishing and aquaculture industry. However, internal study of automatic red tide image classification is not enough. Especially, extraction of matching center features for recognizing algae image object is difficult because over 200 species of algae in the world have a different size and features. Previously studies used a few type of red tide algae for image classification. In this paper, we proposed the red tide image recognition method using NMF and revison of rotation angle for enhancing of recognition of red tide algae image.

• Journal of Korean Society on Water Environment
• /
• v.26 no.6
• /
• pp.994-999
• /
• 2010

The toxin of Cyanobacteria (blue-green algae) during summer season has been a problem and early prevention should be considered. A variety of methods can be used to forecast algal blooms and this study aims at examining feasibility of chlorophyll-a. The real-time data were collected by automatic water quality monitoring system (AWQMS) in Daecheong reservoir and invalid data were sorted by experts. And then, the sorted data were filled using linear interpolation. When the concentration of chlorophyll-a increased by $15mg/m^3$, water temperature and pH exceeded $26.8^{\circ}C$ and 9.5 respectively. As a result of correlation between chlorophyll-a and other parameters(i.e. water quality items and hydrological data), temperature (r=0.502 - 0.574), pH (r=0.583 - 0.681), total organic carbon (TOC, r=0.583 - 0.681) comparably had higher values. Meanwhile, the data around a day or two showed the highest correlation. In addition, chlorophyll-a is considered to be significantly effected by precipitation and inflow.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.58 no.2
• /
• pp.53-63
• /
• 2016

Monitoring of cyanobacteria bloom in reservoir systems is important for water managers responsible of water supply system. Cyanobacteria affect the taste and smell of water and pose considerable filtration problems at water use places. Harmful cyanobacteria bloom in reservoir have significant economic impacts. We develop a new method for estimating the cyanobacteria bloom using Landsat TM and ETM+ data. Developed model was calibrated and cross-validated with existing in situ measurements from Daecheong Reservoir's Water Quality Monitoring Program and Algae Alarm System. Measurements data of three stations taken from 2004 to 2012 were matched with radiometrically converted reflectance data from the Landsat TM and ETM+ sensor. Stepwise multiple linear regression was used to select wavelengths in the Landsat TM and ETM+ bands 1, 2 and 4 that were most significant for predicting cyanobacteria cell number and bio-volume. Based on statistical analysis, the linear models were that included visible band ratios slightly outperformed single band models. The final monitoring models captured the extents of cyanobacteria blooms throughout the 2004-2012 study period. The results serve as an added broad area monitoring tool for water resource managers and present new insight into the initiation and propagation of cyanobacteria blooms in Daecheong reservoir.