Raft Aquaculture Research Articles

Monitoring of floating structures using segmentation and object classification of remotely-sensed images

Abstract With the rapid development of Marine aquaculture, remote sensing monitoring of high space separation Marine floating raft aquaculture has become a key technology to ensure aquaculture efficiency and environmental sustainability. A novel multi-scale layered cascade capsule network (MSHCN) model is proposed to improve the accuracy and efficiency of remote sensing image analysis for high space separation Marine floating raft culture. Firstly, based on the basic principle of the capsule network, the traditional convolutional neural network is improved, and a multi-scale feature extraction mechanism is introduced to adapt to the diversity and complexity of images in the culture area. Secondly, by building a hierarchical cascade structure, the model can further improve its ability to capture small and large scale features, so as to better understand the spatial distribution characteristics of the farming environment. In addition, in the experimental part, we verified with real remote sensing data sets, and the results showed that the MSHCN model outperformed the current mainstream methods on several key performance indicators, including classification accuracy, detection speed and model generalization ability. Finally, the potential value of this model in practical application and future optimization direction is discussed, which provides a new idea and tool for the development of remote sensing monitoring technology for high space separation floating raft culture.

MSSFNet: A Multiscale Spatial-Spectral Fusion Network for Extracting Offshore Floating Raft Aquaculture Areas in Multispectral Remote Sensing Images.

Accurately extracting large-scale offshore floating raft aquaculture (FRA) areas is crucial for supporting scientific planning and precise aquaculture management. While remote sensing technology offers advantages such as wide coverage, rapid imaging, and multispectral capabilities for FRA monitoring, the current methods face challenges in terms of establishing spatial-spectral correlations and extracting multiscale features, thereby limiting their accuracy. To address these issues, we propose an innovative multiscale spatial-spectral fusion network (MSSFNet) designed specifically for extracting offshore FRA areas from multispectral remote sensing imagery. MSSFNet effectively integrates spectral and spatial information through a spatial-spectral feature extraction block (SSFEB), significantly enhancing the accuracy of FRA area identification. Additionally, a multiscale spatial attention block (MSAB) captures contextual information across different scales, improving the ability to detect FRA areas of varying sizes and shapes while minimizing edge artifacts. We created the CHN-YE7-FRA dataset using Sentinel-2 multispectral remote sensing imagery and conducted extensive evaluations. The results showed that MSSFNet achieved impressive metrics: an F1 score of 90.76%, an intersection over union (IoU) of 83.08%, and a kappa coefficient of 89.75%, surpassing those of state-of-the-art methods. The ablation results confirmed that the SSFEB and MSAB modules effectively enhanced the FRA extraction accuracy. Furthermore, the successful practical applications of MSSFNet validated its generalizability and robustness across diverse marine environments. These findings highlight the performance of MSSFNet in both experimental and real-world scenarios, providing reliable, precise FRA area monitoring. This capability provides crucial data for scientific planning and environmental protection purposes in coastal aquaculture zones.

An Attention-Fused Deep Learning Model for Accurately Monitoring Cage and Raft Aquaculture at Large-Scale Using Sentinel-2 Data

An Attention-Fused Deep Learning Model for Accurately Monitoring Cage and Raft Aquaculture at Large-Scale Using Sentinel-2 Data

BI²Net: Graph-Based Boundary–Interior Interaction Network for Raft Aquaculture Area Extraction From Remote Sensing Images

BI²Net: Graph-Based Boundary–Interior Interaction Network for Raft Aquaculture Area Extraction From Remote Sensing Images

MSARG-Net: A Multimodal Offshore Floating Raft Aquaculture Area Extraction Network for Remote Sensing Images Based on Multiscale SAR Guidance

MSARG-Net: A Multimodal Offshore Floating Raft Aquaculture Area Extraction Network for Remote Sensing Images Based on Multiscale SAR Guidance

Progressive Semantic-Guided Network for the Extraction of Raft Aquaculture Areas From Remote Sensing Images

Progressive Semantic-Guided Network for the Extraction of Raft Aquaculture Areas From Remote Sensing Images

Design and Test of an Efficient Automatic Clip Seedling System for Raft Aquaculture Kelp

Kelp, as a kind of climate-friendly food, animal feed, and bioplastics material, has been gradually cultivated worldwide. In the process of kelp culture, clipping seedling operation is essential to guarantee the yield. Traditionally, the clipping seedling operation is conducted by hand with low production efficiency and high labor intensity. In this paper, a novel automatic clipping seedling machine is developed to improve efficiency. The machine consists of an automatic seedling clipping core device, an automatic seedling feeding device, an automatic seedling rope conveyor, and an automatic product storage device. The corresponding structure, mechanism, and control system are introduced and analyzed. The performances of the automatic machine are tested and compared to manual kelp seedling clipping. Compared to manual kelp seedling clipping, the automatic machine can improve efficiency by 35%. Additionally, the quality of kelp seedling clipping is investigated. The attaching force of the kelp seedling clipped by the automatic machine is 2.179 N (224.4 g × 9.8 N/Kg × 10−3). The rate of the clipped kelp seedlings falling off the rope is only 1.3%. These performances prove that the automatic machine Is feasible and can be used to improve clipping efficiency and ensure clipping quality at the same time.

Application of a VOF Multiphase Flow Model for Issues concerning Floating Raft Aquaculture

Floating raft aquaculture has gradually become a mainstream aquaculture model in the waters of Changhai County, Dalian. To quantitatively describe the impact of floating raft aquaculture facilities on the hydrodynamic environment of nearby sea areas, in this study, we took a single floating raft aquaculture structure as the research object and built a numerical prediction model for water flows passing through the floating raft aquaculture structure using a six-degree-of-freedom VOF (volume of fluid) multiphase flow simulation method based on an overset moving mesh system. Then, we verified the numerical model by utilizing oblique hydraulic jumps and water flows passing through a submerged bar. As shown by the findings, the simulated values are in good agreement with the theoretical solutions and measured values, indicating that the model features high precision and great stability. The impact of the raft area on the hydrodynamic force was introduced into the source term of an equation for consideration. In order to further determine the hindering effect of the raft body on the water body, transport equations and the tracer method were used to simulate the impact of floating raft aquaculture facilities on the water exchange performance of nearby sea areas. This study shows that the VOF multiphase flow model can be easily and accurately applied to studies on floating raft aquaculture, which can greatly reduce the limitations of experiments that utilize pure hydraulic models, wherein the impacts of floating raft aquaculture facilities on hydrodynamic force are generally considered simply based on observations, water roughness or the secondary drag force coefficient, thereby effectively improving the scientific understanding of the physical mechanism involved in floating raft aquaculture.

Synergistic Integration of Time Series Optical and SAR Satellite Data for Mariculture Extraction

Mariculture is an important part of aquaculture, and it is important to address global food security and nutrition issues. However, seawater environmental conditions are complex and variable, which causes large uncertainties in the remote sensing spectral features. At the same time, mariculture types are distinct because of the different types of aquaculture (cage aquaculture and raft aquaculture). These factors bring great challenges for mariculture extraction and mapping using remote sensing. In order to solve these problems, an optical remote sensing aquaculture index named the marine aquaculture index (MAI) is proposed. Based on this spectral index, using time series Sentinel-1 and Sentinel-2 satellite data, a random forest classification scheme is proposed for mapping mariculture by combining spectral, textural, geometric, and synthetic aperture radar (SAR) backscattering. The results revealed that (1) MAI can emphasize the difference between mariculture and seawater; (2) the overall accuracy of mariculture in the Bohai Rim is 94.10%, and the kappa coefficient is 0.91; and (3) the area of cage aquaculture and raft aquaculture in the Bohai Rim is 16.89 km2 and 1206.71 km2, respectively. This study details an effective method for carrying out mariculture monitoring and ensuring the sustainable development of aquaculture.

Variations of Bottom Boundary Layer Turbulence under the Influences of Tidal Currents, Waves, and Raft Aquaculture Structure in a Shallow Bay

High-frequency measurements of tides, waves, and turbulence were made using the bottom-mounted tripod equipped with the Nortek 6-MHz acoustic Doppler velocimetry during 20–23 February 2016 (winter) and 12–26 June 2017 (summer) in Heini Bay, Yellow Sea. The synchro-squeezed wavelet transform was applied for wave-turbulence decomposition, and an iterative procedure was developed to identify the turbulence inertial subrange in the bottom boundary layer. The analysis results reveal the dependency of the inertial subrange on the tidal current and turbulence intensities. The flood-ebb tidal flows are different between the summer and winter seasons, without and with the presence of dense raft aquaculture for kelp, respectively. In summer, the turbulent kinetic energy (TKE), turbulent Reynolds stress (TRS), and dissipation rate (ε) of TKE increase smoothly with the increasing tidal flow magnitude, and ε is approximately in balance with TKE production related to the vertical shear. The presence of heavy kelp aquaculture in winter causes the reduction in flow speeds and TRS, while keeping TKE and ε at high levels.

A Deep Learning Method for Offshore Raft Aquaculture Extraction Based on Medium-Resolution Remote Sensing Images

A Deep Learning Method for Offshore Raft Aquaculture Extraction Based on Medium-Resolution Remote Sensing Images

Comparative Study of Marine Ranching Recognition in Multi-Temporal High-Resolution Remote Sensing Images Based on DeepLab-v3+ and U-Net

The recognition and monitoring of marine ranching help to determine the type, spatial distribution and dynamic change of marine life, as well as promote the rational utilization of marine resources and marine ecological environment protection, which has important research significance and application value. In the study of marine ranching recognition based on high-resolution remote sensing images, the convolutional neural network (CNN)-based deep learning method, which can adapt to different water environments, can be used to identify multi-scale targets and restore the boundaries of extraction results with high accuracy. However, research based on deep learning still has problems such as rarely considering the feature complexity of marine ranching and inadequate discussion of model generalization for multi-temporal images. In this paper, we construct a multi-temporal dataset that describes multiple features of marine ranching to explore the recognition and generalization ability of the semantic segmentation models DeepLab-v3+ and U-Net (used in large-area marine ranching) based on GF-1 remote sensing images with a 2 m spatial resolution. Through experiments, we find that the F-score of the U-Net extraction results from multi-temporal test images is basically stable at more than 90%, while the F-score of DeepLab-v3+ fluctuates around 80%. The results show that, compared with DeepLab-v3+, U-Net has a stronger recognition and generalization ability for marine ranching. U-Net can identify floating raft aquaculture areas at different growing stages and distinguish between cage aquaculture areas with different colors but similar morphological characteristics.

Emergy Synthesis of Two Oyster Aquaculture Systems in Zhejiang Province, China

China is rich in oyster resources and has a long history of oyster aquaculture. Various forms of oyster aquaculture coexist in the coastal regions of China, which are dominated by raft aquaculture and long-line aquaculture. The objective of this study is to assess the environmental sustainability of the oyster aquaculture systems located in Jiantiao Bay, Zhejiang province, China. Emergy synthesis is used in the study to quantify the contributions of the natural and economic inputs to the oyster aquaculture systems, in order to better understand the sustainability. The results show that the raft oyster aquaculture system was high in emergy inputs and yield per unit area, whereas the long-line oyster aquaculture system was low in emergy inputs and yield per unit area. However, the transformities of the oysters from the raft oyster aquaculture system and the long-line aquaculture were similar, reflecting that both systems had a similar efficiency in using natural and economic resources. The oyster aquaculture systems had a different impact on the environment as inferred from the emergy indicators. The higher emergy yield ratio and low emergy loading ratio in the long-line oyster aquaculture system suggest that the system could gain more net benefit, and had a lower impact on the surrounding environment, than raft oyster aquaculture system, and can been considered to be more sustainable. Nevertheless, oyster aquaculture was a labor-intensive process and relied highly on purchased resources, such as labor and construction materials. If the construction materials could be used for a longer time, the oyster aquaculture systems might be more sustainable and environmentally friendly.

The Impact of Floating Raft Aquaculture on the Hydrodynamic Environment of an Open Sea Area in Liaoning Province, China

The sea area of Changhai County in Dalian City is a typical floating raft aquaculture area, located in Liaoning Province, China, where a key issue in determining the scale and spatial layout of the floating raft aquaculture is the assessment of the impact of aquaculture activities on the hydrodynamic environment. To address this issue, we established depth-averaged two-dimensional shallow water equations and three-dimensional incompressible Reynolds-averaged Navier–Stokes equations for the open sea area described in this paper. The impact of floating rafts for aquaculture on hydrodynamic force was reflected in the numerical model by changing the Manning number, where scenarios with different aquaculture densities were taken into account. Finally, the water exchange rate of the floating raft aquaculture area in the study area was calculated. It was found, through a comparison between the simulated value and the measured value obtained via layered observation, that the two values were in good agreement with each other, indicating that the model exhibits great accuracy. In addition, the calculation results for scenarios before and after aquaculture were compared and analyzed, showing that from low-density to high-density aquaculture zones, the variation in flow rate was greater than 80% at the peak of a flood tide. The water exchange rates of the water body after 1 day, 4 days, and 8 days of water exchange were also calculated, and the results show that they had been reduced by 17.92%, 13.59%, and 1.63%, respectively, indicating that the existence of floating rafts for aquaculture indeed reduced the water exchange capacity of the water body. The model described in this paper can serve as a foundation for other studies on aquaculture in open sea areas, and it provides a theoretical basis for the scientific formulation of marine aquaculture plans and the rational optimization of the spatial layout.

RaftNet: A New Deep Neural Network for Coastal Raft Aquaculture Extraction from Landsat 8 OLI Data

The rapid development of marine ranching in recent years provides a new way of tackling the global food crisis. However, the uncontrolled expansion of coastal aquaculture has raised a series of environmental problems. The fast and accurate detection of raft will facilitate scientific planning and the precise management of coastal aquaculture. A new deep learning-based approach called RaftNet is proposed in this study to extract the coastal raft aquaculture in Sansha Bay using Landsat 8 OLI images accurately. To overcome the issues of turbid water environments and varying raft scales in aquaculture areas, we constructed the RaftNet by modifying the UNet network with dual-channel and residual hybrid dilated convolution blocks to improve the extraction accuracy. Meanwhile, we adopted the well-known semantic segmentation networks (FCN, SegNet, UNet, UNet++, and ResUNet) as the contrastive approaches for the extraction. The results suggested that the proposed RaftNet model achieves the best accuracy with a precision of 84.5%, recall of 88.1%, F1-score of 86.30%, overall accuracy (OA) of 95.7%, and intersection over union (IoU) of 75.9%. We then utilized our RaftNet to accurately extract a raft aquaculture area in Sansha Bay from 2014 to 2018 and quantitatively analyzed the change in the raft area over this period. The results demonstrated that our RaftNet is robust and suitable for the precise extraction of raft aquaculture with varying scales in turbid coastal waters, and the Kappa coefficient and OA can reach as high as 88% and 97%, respectively. Moreover, the proposed RaftNet will unleash a remarkable potential for long time-series and large-scale raft aquaculture mapping.

Automatic Extraction of Marine Aquaculture Zones from Optical Satellite Images by R3Det with Piecewise Linear Stretching

In recent years, the development of China’s marine aquaculture has brought serious challenges to the marine ecological environment. Therefore, it is significant to classify and extract the aquaculture zone and spatial distribution in order to provide a reference for aquaculture management. However, considering the complex marine aquaculture environment, it is difficult for traditional remote sensing technology and deep learning to achieve a breakthrough in the extraction of large-scale aquaculture zones so far. This study proposes a method based on the combination of piecewise linear stretching and R3Det to classify and extract raft aquaculture and cage aquaculture zones. The grayscale value is changed by piecewise linear stretching to reduce the influence of complex aquaculture backgrounds on the extraction accuracy, to effectively highlight the appearance characteristics of the aquaculture zone, and to improve the image contrast. On this basis, the aquaculture zone is classified and extracted by R3Det. Taking the aquaculture zone of Sansha Bay as the research object, the experimental results showed that the accuracy of R3Det in extracting the number of raft aquaculture and cage aquaculture zones was 98.91% and 97.21%, respectively, and the extraction precision of the area of the aquaculture zone reached 92.08%. The proposed method can classify and extract large-scale marine aquaculture zones more simply and efficiently than common remote sensing techniques.

Remote sensing identification of marine floating raft aquaculture area based on sentinel-2A and DEM data

Marine floating raft aquaculture forms an integral component of the monitoring of coastal marine environments. It is essential to accurately obtain the spatial distribution of marine floating raft aquaculture to gain the fullest understanding of the development of marine fishery production, optimization of the spatial layout of aquaculture, and protection of the marine environment. The Sentinel-2 Multispectral Instrument (MSI) is used to acquire optical imagery at a high spatial and temporal resolution, sampling 13 spectral bands in the visible, near-infrared, and short-wave infrared parts of the spectrum. This research reports how a decision-tree-based procedure was developed to map marine floating raft aquaculture using Sentinel-2A MSI imagery and DEM (Digital Elevation Model) data. Three indices and spectral features were used in this algorithm to differentiate marine floating rafts from other land-cover and land-use types in Fangchenggang City, China. These included the Differential Ratio Floating Raft Index (DRRI), newly proposed in the paper, the Normalized Difference Vegetation Index (NDVI), and visible reflectance. Additionally, a comparison was made between the decision tree classification method (DT) and the random forest (RF) and support vector machine (SVM) methods. The results demonstrate that these three methods can obtain raft information with high accuracy. Finally, the classification results were merged into aquaculture rafts and non-aquaculture rafts. The overall accuracy for DT was 98.20% and 1.28 and 4.99 percentage points higher than RF and SVM, respectively. The user accuracy for marine floating rafts for DT (98.25%) was also markedly higher than that of RF and SVM methods (93.97% and 86.50%, respectively). The producer accuracy for marine floating rafts through the DT method was 98.17%, 0.81 percent lower than that of RF, and 1.03 percent lower than that of SVM. The decision-tree method does not assume strict data distribution parameters, optimization of the application of multispectral imagery and elevation data becomes possible, and combing with the DRRI index, then results in higher classification accuracies of marine floating rafts. When using multi-source data of different types and distributions to map marine floating rafts, a decision-tree method, therefore, appears to be superior to RF and SVM classifiers.

Marine floating raft aquaculture extraction of hyperspectral remote sensing images based decision tree algorithm

• The HSI-FRA (Hyperspectral remote sensing index for floating-raft aquaculture) has been constructed. • The decision tree model is designed by combining MNDWI and prior knowledge. • The proposed method is suitable for extracting floating-raft aquaculture in coastal areas of high suspended matter. The accurate extraction and mapping of floating raft aquaculture (FRA) is significant to the scientific management and sustainable development of coastal zones. However, the current relevant methods rely on large sample size and complex classifiers, which have poor generalization ability and thus are not suitable for large-scale application. To address these issues, this study proposes a new hyperspectral index based on remote sensing images, namely hyperspectral index for floating raft aquaculture (HSI-FRA). Based on the analysis of the spectral information, the HSI-FRA utilizes four bands at 580 nm, 740 nm, 1040 nm, and 1290 nm, respectively, to enhance the spectral difference between the floating raft aquaculture and the seawater through band calculation, and constructs the extraction index of the floating raft aquaculture. Using the HSI-FRA, a decision tree classification process is carried out to realize the extraction of floating raft aquaculture information. The extraction accuracy in the three study areas of Dayu Bay of Zhejiang Province, Fengwei Town of Fujian Province and Chao'an Bay of Guangdong Province is 94.3%, 95.5% and 91.44%, respectively, which has Larger advantage than those of traditional methods. The experimental results show that the proposed method is simple, fast and accurate at separating the floating raft aquacultures in an offshore complex marine environment.

Extraction of Floating Raft Aquaculture Areas from Sentinel-1 SAR Images by a Dense Residual U-Net Model with Pre-Trained Resnet34 as the Encoder

Marine floating raft aquaculture (FRA) monitoring is significant for marine ecological environment and food security assessment. Synthetic aperture radar-based monitoring is considered to be an effective means of FRA identification because of its capability for all-weather applications. Considering the poor generalization and extraction accuracy of traditional monitoring methods, a semantic segmentation model called D-ResUnet is proposed to extract FRA areas from Sentinel-1 images. The proposed model has a U-Net-like structure but combines the pre-trained ResNet34 as the encoder and adds dense residual units into the decoder. For this model, the final layer and cropping operation of the original U-Net model are removed to eliminate the model parameters. The mean and standard deviation of Precision, Recall, Intersection over Union (IoU), and F1 score are calculated under a five-fold training strategy to evaluate the model accuracy. The test experiments indicated that the proposed model performs well with the F1 of 92.6% and IoU of 86.24% in FRA extraction tasks. In particular, the ablation experiments and application experiments proved the effectiveness of the improvement strategy and the portability of the proposed D-ResUnet model, respectively. Compared with the other three state-of-the-art semantic segmentation models, the experiments demonstrate a clear accuracy advantage of the D-ResUnet model. For the FRA extraction task, this paper presents a promising approach that has refined extraction capability, high accuracy, and acceptable model complexity.

Assessment of Sea-Area Benchmark Pricing: Using Chinese Aquaculture to Evaluate and Revise the Price Structure of Resources

Kong, H.; Shen, J.; Zhao, Y., and Sun, Q., 2022. Assessment of sea-area benchmark pricing: Using Chinese aquaculture to evaluate and revise the price structure of resources. Journal of Coastal Research, 38(5), 925–936. Coconut Creek (Florida), ISSN 0749-0208. China has implemented a system of paid use of sea areas and has in recent years promoted their market-oriented allocation to ameliorate the efficiency and to realize their intensive and economical use. Estimations of the sea-area benchmark price can reveal the differences in sea areas, quality, and efficiency. This study introduces a framework to assess the benchmark price of the sea areas, applied to open aquaculture in Lianjiang County (Fujian Province, China). The assessment results show that the sea area used for bottom-sowing aquaculture in Lianjiang County was classified as Grade 2, whereas the sea area used for raft aquaculture and net cage aquaculture was classified as Grade 4. Upon comprehensive consideration of the theoretical value and the actual demand for sea-area management, the benchmark price of three types of open aquaculture sea areas is evaluated. The benchmark prices for bottom-sowing culture sea areas were found to be RMB 65–117/mu/year; for raft culture sea areas, they were RMB 20–252/mu/year; and for net cage culture, sea areas were RMB 100–800/mu/year. Overall, this study constructed a revised system of sea-area benchmark pricing, considering the natural conditions of the sea area, policy factors, transportation and infrastructure, culture conditions, and development degree. These results could be used as the guiding prices of the government to transfer sea-area resources and could ensure the realization of the economic interests of the government as owner of the sea area. Furthermore, this approach can provide a novel way to evaluate sea-area prices in other coastal areas.