Aquaculture Monitoring Research Articles

OPTIMALIZATION AND SOCIALIZATION OF INTERNET-BASED AQUACULTURE MEDIA CONDITION MONITORING TECHNOLOGY, ARSENIK 2

Indonesia's geographical condition, as a maritime country, has a wealth of natural resources in the form of water, which has the potential to support the economy in the aquaculture sector. One of them is the cultivation of freshwater fish ponds as has been carried out by the Maju Rukun Community Group (PokMas) in Ngerong Village, Pasuruan. Lack of equipment and knowledge in monitoring pond water conditions, resulting in problems with the fish nursery process. This is because water is a living medium for aquatic organisms, thus determining the survival of cultivated fish. Therefore, community service activities were held in the form of implementing an appropriate technology device "Arsenik version 2" and a mobile application that can be downloaded on Android to support water quality monitoring in aquaculture. In addition, socialization, training, and seminars regarding parameters of good pond water quality for fish farming were also provided to the Maju Rukun PokMas and the local community. Based on the positive response from the community, the implementation of the Arsenic device version 2 is considered very helpful in terms of monitoring the condition of pond water quality because it has informative parameter values and an easy presentation to understand so that the public can maintain the health of aquatic media for the aquaculture ecosystem in it.

DLRW: Dual-Link Weight Random Walk Model for Aquaculture Boundary Extraction by Single-Polarized SAR Imagery

Coastal aquaculture is undertaken in shallow and usually sheltered waters along the coast, delineated by aquaculture ponds. Illegal usage of coastal aquaculture can lead to conflicts with local communities and environmental problems. Thus, it is necessary to extract the aquaculture boundary to monitor the expansion of coastal aquaculture to the sea. However, it is challenging for most existing algorithms to extract the aquaculture boundary for synthetic aperture radar (SAR) images under a high incident angle (>30 degree) with horizontal transmitted and received (HH) or vertical transmitted and received (VV) polarization. The difficulties come from the following: (1) seawater can be seen on both sides of such boundaries, (2) the contrast of such boundaries is uneven, and (3) the backscattering coefficients in some parts of such boundaries are low. In this paper, a novel dual-link weight random walk (DLRW)-based method is proposed to extract such boundaries. The proposed DLRW is composed of an automatic seed points generation strategy, and the establishment and solving of a random walk model with the dual-link weight. By a coarse-to-fine procedure, DLRW is used to extract the aquaculture boundaries in the whole imagery. Sentinel-1 and GF-3 images in Dalian and Liaodong Bay, China have been used in experiments. Mean offset (MO), root mean square error (RMSE), Overlapped, accuracy within one pixel (WOP), and accuracy within two pixels (WTP) have been used to evaluate the performance with existing methods. Experimental results have demonstrated the proposed DLRW-based method outperforms existing methods in the extraction on aquaculture boundaries. Under the low tide, the DLRW-based method is better than the other two methods with MO, RMSE, Overlapped, WOP, and WTP by at least 5.75 pixels, 10.43 pixels, 2.88%, 11.09%, and 18.04%, respectively. Under the high tide, the DLRW-based method is superior to the other two methods with MO, RMSE, and WTP by at least 3.8 pixels, 10.5 pixels, and 6.3%. In addition, the proposed DLRW-based method has a good ability to extract the shoreline with bedrock, ports, and silt. Therefore, the proposed DLRW-based method can be of great value to coastal aquaculture monitoring, coastal mapping, and other coastal applications.

Dietary analysis of three important mariculture species in South Korea using DNA metabarcoding in fecal samples

Knowledge of dietary composition is crucial for understanding the trophic ecology of a mariculture species and the available food in aquafarms, which is fundamental for assessing ecosystem health status and determining ecological response to ecosystem variation to develop a better management plan for marine farming. For suspension-feeding invertebrates, the growth and development rely heavily on the availability and quality of phytoplankton. However, their growth rate can be severely impacted by food deficiency or exposure to harmful algae blooms (HABs) and pathogenic parasites, which are major causes of mass mortality in mariculture. This study aimed to conduct a dietary analysis of three important mariculture species — Magallana gigas, Halocynthia roretzi, and Mizuhopecten yessoensis — on three farms in South Korea using DNA metabarcoding. Sequence processing and filtering generated 304 validated amplicon sequence variants from six fecal samples, taxonomically identifying 15 phyla, 18 classes, 32 orders, 39 families, 43 genera, and 46 species. The DNA recovery of Dinoflagellata was predominantly detected in all fecal samples, followed by Apicomplexa, Bacillariophyta, and Ciliophora. Of the three mariculture species, the fecal assemblage of M. gigas exhibited the highest richness and diversity, with a high read proportion of phytoplankton (specifically Dinoflagellata), while such proportions were relatively low in the M. yessoensis samples. Excessive read proportions of parasites (Apicomplexa) were detected in the fecal samples of two H. roretzi, indicating a possible link to as substantial decrease in H. roretzi production observed in South Korea. A total of 27 key species were detected in six fecal samples, including a high read proportion of Prorocentrum triestinum, which is responsible for HABs in Korean coastal waters. These results emphasize the potential of fecal DNA metabarcoding in the genetic monitoring of aquaculture farms/ecosystems and could be a useful reference for develop effective management plans to guarantee sustainable mariculture production.

Long-Range Self-Powered IoT Devices for Agriculture Aquaponics

The aim of this project is to establish a controlled environment in the aquaculture industry by minimizing human errors and reducing the need for manpower. Additionally, the project seeks to enable remote monitoring of aquatic environments from any location in the world. By utilising mobile phone applications, the physical presence of humans can be significantly reduced. The device is capable of collecting and transmitting data from a variety of sensors, including those that measure temperature, humidity, and pH levels. This real-time monitoring and analysis of the aquaponics systems allows farmers and growers to make informed decisions about water usage, fish health, and other productivity-related factors. Ultimately, this system can improve productivity and efficiency in the aquaculture industry. Aquaculture is a growing industry worldwide, and the need for sustainable and efficient practices is increasing. The use of technology and automation has become more common in recent years as a means of improving productivity and reducing human error. The proposed system for aquaculture monitoring aims to address these issues by utilizing sensors and microcontrollers to create a controlled environment for aquatic organisms. The system employs various sensors to measure critical parameters such as water temperature, pH, and turbidity, and sends this data to a central monitoring system. Farmers and growers can then access this data remotely and make informed decisions about the health and productivity of their aquatic systems. This can lead to better control over water quality and temperature, improved feeding practices, and ultimately higher yields.

Designing Aquaculture Monitoring System Based on Data Fusion through Deep Reinforcement Learning (DRL)

The aquaculture production sector is one of the suppliers of global food consumption needs. Countries that have a large amount of water contribute to the needs of aquaculture production, especially the freshwater fisheries sector. Indonesia is a country that has a large number of large bodies of water and is the top-five producer of aquaculture production. Technology and engineering continue to be developed to improve the quality and quantity of aquaculture production. One aspect that can be observed is how the condition of fish pond water is healthy and supports fish growth. Various studies have been conducted related to the aquaculture monitoring system, but the problem is how effective it is in terms of accuracy of the resulting output, implementation, and costs. In this research, data fusion (DF) and deep reinforcement learning (DRL) were implemented in an aquaculture monitoring system with temperature, turbidity, and pH parameters to produce valid and accurate output. The stage begins with testing sensor accuracy as part of sensor quality validation, then integrating sensors with wireless sensor networks (WSNs) so they can be accessed in real time. The implemented DF is divided into three layers: first, the signal layer consists of WSNs and their components. Second, the feature layer consists of DRL combined with deep learning (DL). Third, the decision layer determines the output of the condition of the fish pond in “normal” or “not normal” conditions. The analysis and testing of this system look at several factors, i.e., (1) the accuracy of the performance of the sensors used; (2) the performance of the models implemented; (3) the comparison of DF-DRL-based systems with rule-based algorithm systems; and (4) the cost effectiveness compared to labor costs. Of these four factors, the DF-DRL-based aquaculture monitoring system has a higher percentage value and is a low-cost alternative for an accurate aquaculture monitoring system.

Coastal Aquaculture Extraction Using GF-3 Fully Polarimetric SAR Imagery: A Framework Integrating UNet++ with Marker-Controlled Watershed Segmentation

Coastal aquaculture monitoring is vital for sustainable offshore aquaculture management. However, the dense distribution and various sizes of aquacultures make it challenging to accurately extract the boundaries of aquaculture ponds. In this study, we develop a novel combined framework that integrates UNet++ with a marker-controlled watershed segmentation strategy to facilitate aquaculture boundary extraction from fully polarimetric GaoFen-3 SAR imagery. First, four polarimetric decomposition algorithms were applied to extract 13 polarimetric scattering features. Together with the nine other polarisation and texture features, a total of 22 polarimetric features were then extracted, among which four were optimised according to the separability index. Subsequently, to reduce the “adhesion” phenomenon and separate adjacent and even adhering ponds into individual aquaculture units, two UNet++ subnetworks were utilised to construct the marker and foreground functions, the results of which were then used in the marker-controlled watershed algorithm to obtain refined aquaculture results. A multiclass segmentation strategy that divides the intermediate markers into three categories (aquaculture, background and dikes) was applied to the marker function. In addition, a boundary patch refinement postprocessing strategy was applied to the two subnetworks to extract and repair the complex/error-prone boundaries of the aquaculture ponds, followed by a morphological operation that was conducted for label augmentation. An experimental investigation performed to extract individual aquacultures in the Yancheng Coastal Wetlands indicated that the crucial features for aquacultures are Shannon entropy (SE), the intensity component of SE (SE_I) and the corresponding mean texture features (Mean_SE and Mean_SE_I). When the optimal features were introduced, our proposed method performed better than standard UNet++ in aquaculture extraction, achieving improvements of 1.8%, 3.2%, 21.7% and 12.1% in F1, IoU, MR and insF1, respectively. The experimental results indicate that the proposed method can handle the adhesion of both adjacent objects and unclear boundaries effectively and capture clear and refined aquaculture boundaries.

Blynk based aquaculture monitoring system using IOT

Internet of Things (IOT) is one of the development trends technologies reduces the amount of human labor and creates an economy ethnic. Currently, IoT is applied in many fields such as medicine, agriculture, traffic system, training, monitoring, etc. It is the most important because aquaculture is an outdated field of applied science. As similar to In other areas such as agriculture, it is essential to identify problems that arise this field with the help of technology. The term Aquaculture mainly refers to Aquaculture such as fish and plants takes place in many forms aquatic environments, including lakes, rivers, ponds, oceans, and artificially closed areas terrestrial environmental systems. Aqua culture plays an important role in economic development and food production in our country. adopt fish can quickly and easily using monitoring systems. Water quality can be a fundamental problem and it depends on various parameters like pH, turbidity, Temperature, dissolved oxygen, Ammonia etc. Suggestion system continuous monitoring of water quality parameters by various sensors. The detected information is transmitted to the mobile phone of the aquarist via the web cloud waiter. It will also notify the aquarist about the data through the app. This system will activate automated farming system to make appropriate adjustments to the environment of the self-contained artificial pond. So the water quality parameters keeping a balance, culture is the root of health and development of living organisms. This system will monitor the water quality parameters and regularly access water quality parameters.

Relationship between in feed drugs, antibiotics and organic enrichment in marine sediments at Canadian Atlantic salmon aquaculture sites

The presence of in-feed anti-sea lice drugs and their relationship with organic enrichment is poorly understood in sediment surrounding salmon farms. Using data from an aquaculture monitoring program (2018–2020), we describe this relationship at ten sites in four Canadian provinces. Three anti-sea lice pesticides (lufenuron, teflubenzuron, emamectin benzoate and metabolite desmethyl emamectin benzoate), and one antibiotic (oxytetracycline) were detected. Concentrations were often below limits of quantification. Values are also lower than those reported in other aquaculture salmon-producing countries. Highest concentrations, along with organic enrichment, were observed ~200 m of cages with lower concentrations detected up to 1.5 km away. Most samples had at least two drugs present: 75.2 % (British Columbia), 91.4 % (Newfoundland), and 54.8 % (New Brunswick/Nova Scotia) highlighting the potential for cumulative effects. Emamectin benzoate and oxytetracycline were detected four and three years respectively after last known treatments, demonstrating the need for research on overall persistence of compounds.

Fish Monitoring in Aquaculture Using Multibeam Echosounders and Machine Learning

Fish Monitoring in Aquaculture Using Multibeam Echosounders and Machine Learning

A Self-Supervised Transformer With Feature Fusion for SAR Image Semantic Segmentation in Marine Aquaculture Monitoring

A Self-Supervised Transformer With Feature Fusion for SAR Image Semantic Segmentation in Marine Aquaculture Monitoring

Internet of Things-Based Surveillance and Feeding System for Aquaculture Applications

In both developed and developing countries, the agricultural sector is playing a significant role in driving economic growth. In Nigeria, there has been an increased push to diversify the economy through agriculture, and aquaculture has been identified as a key sector to aid in this effort. However, the sector faces various challenges, such as poor water quality, feeding-related issues, pest control, disease, and predator control, resulting in reduced output and lower incomes. Previous research has aimed to provide solutions to these challenges, but some works only focus on monitoring water quality, disease, or surveillance against predators or theft, without considering feeding rates. Therefore, a monitoring and surveillance system is required to minimize death rates caused by hunger and increase productivity. This work presents the use of IoT to enable real-time monitoring in aquaculture. The system successfully initiated and terminated the feeding process in the pond within a 3-second timeframe and provided a live feed of the pond

Fuzzy Logic-Based Adaptive Aquaculture Water Monitoring System Based on Instantaneous Limnological Parameters

Water quality is crucial for maintaining a sustainable living environment in aquaculture. Limnological parameters affects the fish physiology, growth rate, and feed efficiency and may lead to high mortality rate under extreme conditions. The development of an adaptive aquaculture monitoring system for water quality using fuzzy logic will address this problem. Using Mamdani-type fuzzy inferences system (FIS) model, the input limnological parameters such as pH, temperature, total dissolved solids, and dissolved oxygen levels were transformed to four output states: excellent, good, poor, and toxic, for the prediction of water quality. For the simulation and evaluation of the developed FIS, MATLAB Simulink was used. Results of this study can be integrated with a feedback system for appropriate treatments including filtering, aeration, and water flushing to maintain safe environment for Nile tilapia.

Feasibility Study of a Small-Scale Recirculating Aquaculture System for Sustainable (Peri-)Urban Farming in Sub-Saharan Africa: A Nigerian Perspective

The (peri-)urban population in developing countries, especially sub-Saharan Africa, is rapidly increasing. As towns and cities grow, so does the demand for fish protein. While flow-through aquaculture can provide fresh, healthy and nutritious fish protein, it is plagued by extensive land requirements as well as effluent discharge and is thus unsuitable for city regions. Alternatively, small-scale Recirculating Aquaculture Systems (RAS) could improve food and nutritional security and livelihoods as well as reduce environmental degradation in (peri-)urban areas despite land and water constraints. The question, however, remains—what are the key technical, business and managerial issues surrounding small-scale RAS in (peri-)urban farming? To answer this question, first, a systematic literature review on RAS in sub-Saharan Africa is conducted. Second, the RAS prototype of the Sustainable Aquaponics for Nutritional and Food Security in Urban Sub-Saharan Africa (SANFU) II project is assessed. This assessment is based on the mass balance and stock density, relevant for fish survival and/or availability as well as net cash flow analyses. The results suggest that small-scale RAS are technically and financially viable with efficient filtration and family labor having proper aquaculture monitoring and management skills. Furthermore, access to adequate equipment and inputs as well as electricity for the recirculating system are crucial. (Peri-)urban innovation actors will adopt RAS if operations are profitable.

Bacterial Community and Antibiotic Resistance Gene Profiles of Fish Gut Contents and Their Aquaculture Environment in Tianjin, China

The continuous expansion of freshwater fish culture is confronted with environmental problems owing to their high antibiotic inputs and antibiotic-resistant bacteria. This study explored the antibiotic resistance gene (ARG) profiles of water and fish gut contents from three fishponds in Tianjin using a metagenomics approach. Proteobacteria, Bacteroidetes, and Actinobacteria were the most abundant phyla in all water samples. However, the microbial composition of the fish guts was distinctly different among the three aquaculture farms. Cetobacterium, Bacillus, Weissella, and Fusobacterium were the dominant genera in the gut contents of all fish. More than 20 unique ARGs with relatively high abundances were detected in both water and fish gut content samples. The dominant genes and pathways of antibiotic resistance mechanisms detected in all samples were antibiotic efflux, antibiotic inactivation, antibiotic target alteration, antibiotic target protection, antibiotic target replacement, and reduced permeability to antibiotics. In addition, our results indicate that antibiotics, such as florfenicol, and heavy metals, such as Zn and Cu, could have a significant correlation with some common ARGs, indicating that antibiotic-resistant bacteria could co-occur with heavy metals. Our study provides a research basis for the development of a strategy for practical antibiotic application and heavy metal monitoring in aquaculture.

Thallusin Quantification in Marine Bacteria and Algae Cultures.

Thallusin, a highly biologically active, phytohormone-like and bacterial compound-inducing morphogenesis of the green tide-forming macroalga Ulva (Chlorophyta), was determined in bacteria and algae cultures. A sensitive and selective method was developed for quantification based on ultra-high-performance liquid chromatography coupled with electrospray ionization and a high-resolution mass spectrometer. Upon C18 solid phase extraction of the water samples, thallusin was derivatized with iodomethane to inhibit the formation of Fe−thallusin complexes interfering with the chromatographic separation. The concentration of thallusin was quantified during the relevant phases of the bacterial growth of Maribacter spp., ranging from 0.16 ± 0.01 amol cell−1 (at the peak of the exponential growth phase) to 0.86 ± 0.13 amol cell−1 (late stationary phase), indicating its accumulation in the growth medium. Finally, we directly determined the concentration of thallusin in algal culture to validate our approach for monitoring applications. Detection and quantification limits of 2.5 and 7.4 pmol L−1, respectively, were reached, which allow for quantifying ecologically relevant thallusin concentrations. Our approach will enable the surveying of thallusin in culture and in nature and will thus contribute to the chemical monitoring of aquaculture.

Mapping Coastal Aquaculture Ponds of China Using Sentinel SAR Images in 2020 and Google Earth Engine

Aquaculture has enormous potential for ensuring global food security and has experienced rapid growth globally. Thus, the accurate monitoring and mapping of coastal aquaculture ponds is necessary for the sustainable development and efficient management of the aquaculture industry. Here, we developed a map of coastal aquaculture ponds in China using Google Earth Engine (GEE) and the ArcGIS platform, Sentinel-1 SAR image data for 2020, the Sentinel-1 Dual-Polarized Water Index (SDWI), and water frequency obtained by identifying the special object features of aquaculture ponds and postprocessing interpretation. Our map had an overall accuracy of 93%, and we found that the coastal aquaculture pond area in China reached 6937 km2 in 2020. The aquaculture pond area was highest in Shandong, Guangdong, and Jiangsu Provinces, and at the city level, Dongying, Binzhou, Tangshan, and Dalian had the most aquaculture pond area. Aquaculture ponds had spatial heterogeneity; the aquaculture pond area in north China was larger than in south China and seaside areas had more pond area than inland regions. In addition, aquaculture ponds were concentrated near river estuaries, coastal plains, and gulfs, and were most dense in the Huang-Huai-Hai Plain and Pearl River Delta. We showed that GEE cloud processing and ArcGIS local processing could facilitate the classification of coastal aquaculture ponds, which can be used to inform and improve decision-making for the spatial optimization and intelligent monitoring of coastal aquaculture, with certain potential for spatial migration.

A Super-resolution Reconstruction Method for Underwater Fish Images with Feedback Networks

<p>Video surveillance is commonly used for production process monitoring in aquaculture. Because underwater video images are prone to blurring and unclear detail texture, this paper proposes a super-resolution network reconstruction method with a feedback network. The reconstruction effect is enhanced by a feedback network in the process of mapping low-resolution images to high-resolution images, which is implemented with a constrained recurrent neural network (RNN) to process deep feedback information. However, the shallow features are fed to the feedback net-work module to generate deeper features through multiple upsampling and downsampling and progressive refinement, which give the network structure an early reconstruction capability and are conducive to more realistically reconstructing high-resolution images. A course learning strategy is introduced to make the network applicable to more complex tasks and improve its robust-ness. We construct a training set of 800 images and validation and test sets of 10 images each using images of marine net fish as the research object. The method of this paper is validated on the public dataset Set14 and a self-built dataset. The proposed method outperforms other methods in both subjective and objective evaluations on the public and self-built datasets. Good foundation for high-definition monitoring of aquaculture is laid. </p> <p> </p>

Broodstock breeding behaviour recognition based on Resnet50-LSTM with CBAM attention mechanism

Broodstock has the characteristics of a long breeding time, small breeding quantity, and a high economic value. At the same time, the broodstock is weak during the spawning period, which needs to be observed in time. Therefore, studying the behaviours of broodstock (chasing, spawning, aggregation, feeding, and swimming normally) could help fish farmers to understand the health status of broodstock and adjust breeding strategies in time. However, it is challenging to recognise these behaviours due to the high similarity between these behaviours. In this study, a camera’s infrared mode was used to obtain the behaviour recognition data in weak light conditions, and the visible light mode of the camera was used to obtain the data in sufficient lighting conditions. A Resnet50-LSTM based approach was proposed to recognise five standard behaviours. Due to the advantages of deep feature extraction, Resnet50 extracted the features of the input data in different dimensions through multiple convolution. These features were input into the Long-Short-Term-Memory (LSTM) classification model, enabling the extraction of time-series behavioural information Convolutional Block Attention Module (CBAM) was added after each stage in the Resnet50 network, which was able to focus on important features and suppress unnecessary noise interference. Meanwhile, mish activation function and ranger optimiser were used to improve the accuracy of behaviour recognition. 3925 videos containing 981,250 frames were collected and tested to compare the performance of the proposed algorithm. The test results showed that our method achieved a recognition accuracy of 98.52%. Additionally, we compared the test accuracy between the proposed method with eight competitive models, and the test results showed that the average recognition accuracy of the eight models was 95.04%, 97.32%, 97.18%, 97.52%, 98.32%, 77.80%, 85.10%, 90.8%, respectively. Our method shows higher average recognition accuracy. Overall, this is an effective method for intelligent aquaculture monitoring. The algorithm meets the needs of behaviour recognition, which has good robustness in an aquaculture environment and provides a new strategy for smart aquaculture.

Environmental and disease monitoring in the northern aquaculture area

Aquaculture is facing many challenges related to diseases and environmental pollution. Environmental and disease monitoring in aquaculture is to help authorities in planning and management, and to provide technical measures to support farmers. The study was carried out from January to October 2020, including 13 sites of supply water of brackish water shrimp farming areas of Nam Dinh, Nghe An, Ha Tinh, Quang Binh, Quang Tri, and Thua Thien Hue; 11 sites of clam/mollusc farming areas of Thai Binh, Thanh Hoa, and Quang Ninh; 11 sites of cage aquaculture of Hoa Binh, Yen Bai, and Hai Duong, with 23 monitoring times of the inlet water for brackish shrimp, 7 monitoring times for tilapia and freshwater cage culture. Alkalinity, ammonia, nitrite, total Vibrio, and VpAHPND values in shrimp farming water were higher than Vietnam’s environmental standard, valued at 12.37, 25.08, 16.67, 3.68, and 0.67% respectively. Salinity, ammonia, nitrite values, and total Vibrio in the mollusc farming water were higher than Vietnam’s environmental standard, which were 23.38, 33.77, 32.50, and 3.9%, respectively. Chemical oxygen demand and nitrite in the tilapia and freshwater cage farming water were higher than Vietnam’s environmental standard, which were 29.87 and 22.08%, respectively. Timely recommendations and warnings helped farmers minimise the damage caused by environmental pollution and diseases.

Low-Cost Underwater Camera: Design and Development

The understanding of vision-based data acquisition and processing aids in developing predictive frameworks and decision support systems for efficient aquaculture monitoring and management. However, this emerging field is confronted by a lack of high-quality underwater visual data, whether from public or local setups and high cost of development. In this regard, an underwater camera that captures underwater images from an inland freshwater aquaculture setup was proposed. The components of the underwater camera system are primarily based on Raspberry Pi, an open-source computing platform. The underwater camera continuously provides a real-time video streaming link of underwater scenes, and the local processor periodically acquires and stores data from this link in the form of images. These data are stored locally and remotely. Based on the results of the developed low-cost underwater camera, it captures and differentiate fish region to its background before and after flushing as influenced by turbidity. Hence, the developed camera can be used for both aquarium and inland aquaculture pond setup for fish monitoring.