Towards a distributed and operational pelagic imaging network DOI Creative Commons
Rainer Kiko, Rubens M. Lopes, Yawouvi Dodji Soviadan

et al.

Ocean and Coastal Research, Journal Year: 2023, Volume and Issue: 71

Published: Jan. 1, 2023

Dimensions of particulate matter found in the water column marine and freshwater environments (the pelagic realm) range from nanometers to tens meters. Included this enormous size are miniature bacteria, phytoplankton (photosynthetic microalgae), mixoplankton (mixotrophic microorganisms), micro- meter sized drifting animals (zooplankton), plastic particles, detrital aggregates fecal pellets, fish, whales many others. These particles organisms involved different processes perform a multitude services, such as oceanic biogeochemistry (carbon fixation, oxygen production, carbon export others) or human nourishment (fisheries). Digital optical tools used imaging approaches now allow bridge span image meter-sized objects situ on discrete samples. Monitoring plankton, nekton, particle dynamics at spatial temporal scales that enable effective management poses collective challenge for society. We here argue global, distributed operational network is needed within reach, we provide recommendations how it can be attained via voluntary activities community strategic support funding agencies other stakeholders.

Language: Английский

An integrated monitoring system for disaster-causing organisms in the water intake areas of coastal nuclear power plants DOI Creative Commons
Chao Li,

Jian-ling Huo,

Yu-ze Song

et al.

Frontiers in Marine Science, Journal Year: 2023, Volume and Issue: 9

Published: Jan. 10, 2023

Nowadays, nuclear power plays an important role in the energy structure of many countries. However, A bloom a disaster-causing organism (DCO) cold-water intake area coastal plant can block water cooling system and seriously affect operational safety unit. Currently, traditional method protection is to estimate DCO abundance by regular manual investigation sampling, but that cannot give continuous real-time data. Instead, proposed implemented here seafloor situ integrated monitoring for DCOs (known as IMSDCO), which equipped with optical microscopic imager (OMI) hydrometric sensors monitor automatically hydrology. All data are transmitted terminal shore station through photoelectric composite cable display. When reaches preset threshold, software raises alarm. Since placing IMSDCO at Changjiang plant, six-month field trial has been completed, during large amounts hydrology images were obtained. successfully identified estimated abundances various (e.g., Phaeocystis globosa , Acetes chinensis small fish) predicted their movements based on Based analysis experimental data, we discussed reasons error estimation methods reduce error. The results show OMI-based early warning areas costal plants worthy long-term deployment.

Language: Английский

Citations

2
Toward efficient deep learning system for in-situ plankton image recognition DOI Creative Commons

Junbai Yue,

Zhenshuai Chen,

Yupu Long

et al.

Frontiers in Marine Science, Journal Year: 2023, Volume and Issue: 10

Published: Sept. 22, 2023

Plankton is critical for the structure and function of marine ecosystems. In past three decades, various underwater imaging systems have been developed to collect in-situ plankton images image processing has a major bottleneck that hinders deployment systems. recent years, deep learning methods greatly enhanced our ability images, but high-computational demands longtime consumption still remain problematic. this study, we used knowledge distillation as framework model compression improved computing efficiency while maintaining original high accuracy. A novel inter-class similarity algorithm based on feature prototypes was proposed enabled student network (small scale) acquire excellent recognition after being guided by teacher (large scale). To identify suitable network, compared emerging Transformer neural networks convolution (CNNs), best performing model, Swin-B, selected. Utilizing algorithm, extraction Swin-B transferred five more lightweight networks, results had evaluated in taxonomic dataset images. Subsequently, chosen Bilateral–Sobel edge enhancement were tested process with level noises captured from coastal waters Guangdong, China achieved an overall recall rate 91.73%. Our work contributes effective models facilitates promoting both accuracy speed targets.

Language: Английский

Citations

2
Diversity and Abundance of Plankton From Peunaga, Cut Ujong Estuary, Meulaboh, West Aceh DOI Open Access
Eka Lisdayanti,

Eko Perbowo Dian Hermawan,

Ananingtyas S Darmarini

et al.

Juvenil Jurnal Ilmiah Kelautan dan Perikanan, Journal Year: 2024, Volume and Issue: 5(1), P. 86 - 95

Published: Feb. 29, 2024

ABSTRACTThe research aims to determine the structure of plankton community in waters Gampong Peunaga Cut Ujong, Meureubo, Meulaboh, West Aceh. The study was conducted September 2023. collection point consisted 3 stations, and sampling carried out at high tide with three repetitions. filtering process uses a net mesh size 30 µm. Phytoplankton location consists five classes, namely Cyanophyceae, Euglenophyceae, Chlorophyceae, Bacillariophyceae, Dinophyceae. Meanwhile, zooplankton 7 groups consisting Protozoa, Rotifera, Crustacea, Polychaeta, Gastropoda, Pelecypoda, Nematoda. has highest percentage Bacillariophyceae class, reaching 71.7%, lowest 1% (Dinophyceae, Chlorophyceae). abundance phytoplankton station during ranged between 2,025,600 cells/m3 - 6,710,400 range 23,400 ind/m3 33,480 ind/m3. average diversity index (H') for 1.04, uniformity (E) 0.40, dominance (C) 0.50. values H' (1.42), E (0.65), D (0.36). To maintain estuary area as an ideal buffer area, it is recommended regularly monitor aquatic biota (plankton, benthos, fish).Keywords: ecosystem, structure, index, Navicula sp.

Language: Английский

Citations

0
Seasonal changes in the protist communities of Hakodate Bay, southern Hokkaido, from 2020 to 2022 DOI
Yusuke Hamao,

Kyosei Morimoto,

Shoko Tatamisashi

et al.

Regional Studies in Marine Science, Journal Year: 2024, Volume and Issue: 78, P. 103775 - 103775

Published: Aug. 27, 2024

Language: Английский

Citations

0
Growth and defence in a unicellular microalga: the coexistence of r and K strategies DOI Creative Commons
Lu Liu,

Si Tang,

Yaqing Liu

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 26, 2024

Abstract r (high reproductivity but stress-sensitive offspring) and K (low high stress-resistant strategies are two classical life history theories. Contrary to the belief that one species only has a single strategy (i.e., either or K), we present experimental evidence for coexistence of both in isogenic microalga Haematococcus lacustris . Under standard conditions, swimming vegetative cells (SVC) normally grew divided via binary fission (r strategy) gradually shifted into non-swimming cysts (NSC) over time. Intriguingly, unlike prevailing notion NSC cannot propagate under stress, they were found reproduce multiple at barely detectable growth rate, resulting stress-resistant, non-mobile daughter demonstrating complete (K strategy). Collectively, our findings indicate H. adopts throughout its history. This research enhances understanding adaptation survival microbial populations changing environments.

Language: Английский

Citations

0
DeepLOKI- a deep learning based approach to identify zooplankton taxa on high-resolution images from the optical plankton recorder LOKI DOI Creative Commons
Ellen Oldenburg, Raphael M. Kronberg,

Barbara Niehoff

et al.

Frontiers in Marine Science, Journal Year: 2023, Volume and Issue: 10

Published: Nov. 30, 2023

Zooplankton play a crucial role in the ocean’s ecology, as they form foundational component food chain by consuming phytoplankton or other zooplankton, supporting various marine species and influencing nutrient cycling. The vertical distribution of zooplankton ocean is patchy, its relation to hydrographical conditions cannot be fully deciphered using traditional net casts due large depth intervals sampled. Lightframe On-sight Keyspecies Investigation (LOKI) concentrates with that leads flow-through chamber camera taking images. These high-resolution images allow for determination taxa, often even genus level, and, case copepods, developmental stages. Each cruise produces substantial volume images, ideally requiring onboard analysis, which presently consumes significant amount time necessitates internet connectivity access EcoTaxa Web service. To enhance analyses, we developed an AI-based software framework named DeepLOKI, utilizing Deep Transfer Learning Convolution Neural Network Backbone. Our DeepLOKI can applied directly on board. We trained validated model pre-labeled from four cruises, while fifth were used testing. best-performing model, self-supervised pre-trained ResNet18 Backbone, achieved notable average classification accuracy 83.9%, surpassing regularly frequently method (default) this field factor two. In summary, tool pre-sorting black white high accuracy, will simplify quicken final annotation process. addition, provide user-friendly graphical interface efficient concise processes leading up stage. Moreover, performing latent space analysis Backbone could prove advantageous identifying anomalies such deviations image parameter settings. This, turn, enhances quality control data. methodology remains agnostic specific imaging end system used, Loki, UVP, ZooScan, long there sufficient appropriately labeled data available enable effective task performance our algorithms.

Language: Английский

Citations

0
Towards a distributed and operational pelagic imaging network DOI Creative Commons
Rainer Kiko, Rubens M. Lopes, Yawouvi Dodji Soviadan

et al.

Ocean and Coastal Research, Journal Year: 2023, Volume and Issue: 71

Published: Jan. 1, 2023

Dimensions of particulate matter found in the water column marine and freshwater environments (the pelagic realm) range from nanometers to tens meters. Included this enormous size are miniature bacteria, phytoplankton (photosynthetic microalgae), mixoplankton (mixotrophic microorganisms), micro- meter sized drifting animals (zooplankton), plastic particles, detrital aggregates fecal pellets, fish, whales many others. These particles organisms involved different processes perform a multitude services, such as oceanic biogeochemistry (carbon fixation, oxygen production, carbon export others) or human nourishment (fisheries). Digital optical tools used imaging approaches now allow bridge span image meter-sized objects situ on discrete samples. Monitoring plankton, nekton, particle dynamics at spatial temporal scales that enable effective management poses collective challenge for society. We here argue global, distributed operational network is needed within reach, we provide recommendations how it can be attained via voluntary activities community strategic support funding agencies other stakeholders.

Language: Английский

Citations

0