Development of a Buoy-Borne Underwater Imaging System for <i>In Situ</i> Mesoplankton Monitoring of Coastal Waters

Li, Minglu; Chen, Tao; Yang, Zhenyu; Chen, Liangpei; Liu, Peng; Zhang, Yizhou; Yu, Guangwen; Chen, Jixin; Li, Haitao; Sun, Xingming

doi:10.1109/joe.2021.3106122

Cited by 24 publications

(15 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They continued this procedure until further improvements became marginal. Li et al (2022) systematized a scheme of human-model interaction, where validated images are added to the training set during applied usage of the classifier. However, neither study has explicitly quantified performance decay nor the effect of training-set updates over a spatial trajectory as presented here.…”

Section: Discussionmentioning

confidence: 99%

Automated Plankton Classification With a Dynamic Optimization and Adaptation Cycle

et al. 2022

View full text Add to dashboard Cite

With recent advances in Machine Learning techniques based on Deep Neural Networks (DNNs), automated plankton image classification is becoming increasingly popular within the marine ecological sciences. Yet, while the most advanced methods can achieve human-level performance on the classification of everyday images, plankton image data possess properties that frequently require a final manual validation step. On the one hand, this is due to morphological properties manifesting in high intra-class and low inter-class variability, and, on the other hand is due to spatial-temporal changes in the composition and structure of the plankton community. Composition changes enforce a frequent updating of the classifier model via training with new user-generated training datasets. Here, we present a Dynamic Optimization Cycle (DOC), a processing pipeline that systematizes and streamlines the model adaptation process via an automatic updating of the training dataset based on manual-validation results. We find that frequent adaptation using the DOC pipeline yields strong maintenance of performance with respect to precision, recall and prediction of community composition, compared to more limited adaptation schemes. The DOC is therefore particularly useful when analyzing plankton at novel locations or time periods, where community differences are likely to occur. In order to enable an easy implementation of the DOC pipeline, we provide an end-to-end application with graphical user interface, as well as an initial dataset of training images. The DOC pipeline thus allows for high-throughput plankton classification and quick and systematized model adaptation, thus providing the means for highly-accelerated plankton analysis.

show abstract

Section: Discussionmentioning

confidence: 99%

Automated Plankton Classification With a Dynamic Optimization and Adaptation Cycle

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Event or pattern recognition may also be applied to data from other sensor types, e.g., cameras [16]. When working with distributed, resource-constraint networks, communication need to be reduced to a bare minimum.…”

Section: K Applying Ai In Underwater Sensing Communication and Data F...mentioning

confidence: 99%

Cross-domain fusion in smart seafloor sensor networks

Zainab

Karstens

2022

Informatik Spektrum

View full text Add to dashboard Cite

Many of the socio-economic and environmental challenges of the 21st century like the growing energy and food demand, rising sea levels and temperatures put stress on marine ecosystems and coastal populations. This requires a significant strengthening of our monitoring capacities for processes in the water column, at the seafloor and in the subsurface. However, present-day seafloor instruments and the required infrastructure to operate these are expensive and inaccessible. We envision a future Internet of Underwater Things, composed of small and cheap but intelligent underwater nodes. Each node will be equipped with sensing, communication, and computing capabilities. Building on distributed event detection and cross-domain data fusion, such an Internet of Underwater Things will enable new applications. In this paper, we argue that to make this vision a reality, we need new methodologies for resource-efficient and distributed cross-domain data fusion. Resource-efficient, distributed neural networks will serve as data-analytics pipelines to derive highly aggregated patterns of interest from raw data. These will serve as (1) a common base in time and space for fusion of heterogeneous data, and (2) be sufficiently small to be transmitted efficiently in resource-constrained settings.

show abstract

“…In China, Bi et al (Bi et al, 2022) used PlanktonScope to monitor plankton such as copepods, jellyfish, chaetognaths, appendicularians, and meroplanktonic larvae in coastal estuaries, and they researched the primary productivity of estuaries. Also, Li et al (Li et al, 2022) installed an OMI on a buoy and carried out plankton and water quality monitoring in Dapeng Cove. However, to the best of our knowledge, there have been no reports to date of an OMI being installed on a bottom platform to monitor DCOs at the water intake of a nuclear power plant.…”

Section: Introductionmentioning

confidence: 99%

An integrated monitoring system for disaster-causing organisms in the water intake areas of coastal nuclear power plants

Huo²,

Yu-ze³

et al. 2023

Front. Mar. Sci.

View full text Add to dashboard Cite

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

show abstract

Development of a Buoy-Borne Underwater Imaging System for In Situ Mesoplankton Monitoring of Coastal Waters

Cited by 24 publications

References 72 publications

Automated Plankton Classification With a Dynamic Optimization and Adaptation Cycle

Automated Plankton Classification With a Dynamic Optimization and Adaptation Cycle

Cross-domain fusion in smart seafloor sensor networks

An integrated monitoring system for disaster-causing organisms in the water intake areas of coastal nuclear power plants

Contact Info

Product

Resources

About