Search

Fishing data are the basement of fisheries science research, but currently the source of fishing data is extraordinarily scarce, and data quality is poor in some aspects. Satellite low light sensors can detect the light-fishing vessels at night, however, its application in pelagic fishery has been limited by the lack of an algorithm for extracting the location and brightness of operating pelagic light-fishing vessels. An examination of operating pelagic light-fishing vessels features in the day/night band (DNB) image, which was from the visible infrared imaging radiometer suite (VIIRS) on the Suomi National Polar-orbiting Partnership (NPP) satellite, indicated that the features were a list of nonadjacent bright spots. In order to identify the operating pelagic light-fishing vessels from VIIRS/DNB accurately, we designed a set of identification algorithm for operating pelagic light-fishing vessels according to the light radiation characteristics of its fishing gathering lamps in NPP/VIIRS low light image. Before applying the identification algorithm, a data pre-processing step was adopted through radiation stretch and noise reduction by adaptive Wiener filter to prepare the data for further analysis and use. A spike median index (SMI) was used to enlarge the radiation difference between operating pelagic light-fishing vessel pixels and background pixels. On the basis of this, an adaptive threshold segmentation method called the maximum entropy (MaxEnt) method was used to extract the bright spot pixels, and generated a list of candidate operating pelagic light-fishing vessels detections. The candidate pixels were then filtered to remove the false identification bright spot pixels distributed near the operating pelagic light-fishing vessel pixels, and illuminated by the high-power fishing gathering lamps by a local spike detection (LSD) algorithm. A validation study was conducted at a night with weak lunar illuminance on May 24, 2015 which was selected randomly, using the vessel monitoring system (VMS) data of Chinese operating light-seiners vessels on the high seas of Northwest Pacific Ocean light seine fishing ground and the result of VIIRS/DNB image visual interpretation. The validation result showed that the identification algorithm detected 27 operating pelagic light-fishing vessels on the high seas of Northwest Pacific Ocean light seine fishing ground, and the number of operating pelagic light-fishing boats and their distribution were entirely consistent with the result of VIIRS/DNB image visual interpretation; the VMS data had the record of 25 operating pelagic light-fishing vessels among the total 27 vessels, and their distribution was nearly the same with the result of identification algorithm and VIIRS/DNB image visual interpretation. The identification algorithm worked well when lunar illuminance was weak and its identification accuracy was above 92%. The identification algorithm not only avoided the subjectivity and uncertainty of certain threshold segmentation, but also removed the false identification bright spot pixels near the operating pelagic light-fishing vessel pixels, which were illuminated by the high-power fishing gathering lamps. Detection of operating pelagic light-fishing vessels based on VIIRS/DNB imaging data can provide up-to-date activity and change information of operating pelagic light-fishing vessels for pelagic light-fishing industry, which meets the need of fishing boat's daily monitoring, and has a wide application prospect in fishing effort estimation, research of central fishing ground spatial-temporal distribution and change, and fishery forecast and management. [ABSTRACT FROM AUTHOR]

In recent years, with the rapid development and expansion of the global aquaculture industry, and the continuous enlargement of aquaculture farms, the industrialization, intelligence, and informatization of aquaculture have become a trend in the industry. China has become the largest producer of fisheries and aquaculture. Fish farming is an important component of aquaculture, and fish farming monitoring has become an important technology to enhance the efficiency, production, and management of fish farming. Fish farming monitoring can provide real-time and accurate data for farms, assisting farm managers in making decisions to improve efficiency and production. With the emergence of artificial intelligence technology in recent years, deep learning has rapidly developed and been widely applied in various fields such as image and audio recognition, natural language processing, robotics, bioinformatics, chemistry, and finance. The monitoring of fish farming focuses on the quantity, growth, behavior, and health status of fish. Using deep learning technology, we can quickly and accurately obtain information related to fish farming and enhance its efficiency and management. This paper presents a deep learning-based method for fish farming monitoring and reviews the literature progress in fish length measurement, fish counting, fish feeding, fish swimming behavior, and fish disease diagnosis. Although deep learning-based fish length measurement has achieved high accuracy in underwater environments, some errors still exist. The counting methods based on deep learning can be categorized into segmentation counting, detection counting, tracking counting, and density regression counting. Deep learning models based on video data have higher accuracy in recognizing fish feeding behavior than imagebased models. There have been many studies on fish tracking, but practical applications still face challenges such as fish feature extraction, the influence of fish size and obstructions, and occlusion issues. In fish disease diagnosis, it is necessary to establish standardized and shared fish disease datasets and utilize data fusion, data level information fusion, feature level information fusion, and decision level information fusion. This article also summarizes the main problems of deep learning-based visual technologies in fish farming monitoring from the aspects of monitoring data acquisition and transmission, dataset standardization and processing, deep learning model design, and the lack of business application in fish farming intelligent monitoring. The problems in data acquisition include a limited variety of experimental subjects, a small number of samples, and poor performance of experimental equipment. In the data transmission process, there are challenges in data security and realtime transmission. In terms of datasets, there is a low level of standardization and a lack of large-scale unified datasets. There is also a lack of research on large models and embedded models in deep learning model design. Furthermore, there is a realistic problem of insufficient business application in practical settings. The paper also proposes future research directions, including establishing fish farming monitoring datasets, super-scale parameter models for fish farming, edge computing for terminal monitoring devices, and digital twinning in fish farming monitoring, aiming to provide scientific references for the widespread application of deep learning in fish farming monitoring. [ABSTRACT FROM AUTHOR]

Water quality monitoring is of great significance to maintaining human health, environmental protection and sustainable economic development. Much attention has also been drawn to water quality safety in recent years. Among them, the concentration of chlorophyll-a is one of the most important indicators of water quality in the fields of aquaculture, fishery management, and environmental protection. Multi-point deployment and continuous monitoring are then required to accurately assess the overall evolution of water quality in large-scale water areas. However, the current instruments of chlorophyll detection are limited for the implementation of large-scale water body monitoring, due to the high price and low degree of automation. In this study, a monitoring device was designed to detect the water chlorophyll-a concentration using laser-induced fluorescence technology. An ambient light correction and data processing were also proposed for the real-time monitoring of chlorophyll-a concentration. The laser light was emitted with a wavelength of 440 nm into the water body, in order to induce and excite chlorophyll-a for the fluorescence with a central wavelength of 680 nm. The concentration of chlorophyll-a was then monitored using the visible light sensor in the device, indicating the 680 nm fluorescence intensity excited by chlorophyll-a. There was a low overall manufacturing cost of the device. Low-power device design introduced the standby and serial port wake-up modes for online automatic monitoring. The two-way communication module was used to realize the data interaction. Data processing was evaluated to reduce the influence of the non-uniform distribution of chlorophyll-a in the water body on the measurement using statistical analysis. The mean value was calculated in time and space. A stable and accurate measurement was achieved in the instrument. An ambient light correction was proposed to reduce the impact of ambient light changes on the instrument measurement. A similar corrected value of the 680 nm light intensity was obtained in the water body chlorophyll-a with the same concentration under 6 groups of ambient light. Experiments show that this device effectively reduced the interference of ambient light on the measurement. The instrument stability test was carried out to observe the power supply circuit of the laser module and the 440 nm light intensity value, where the standard deviation coefficients were both 0.001 after 4 minutes, and the Pearson correlation coefficient was 0.84. It indicated that the laser output was controlled by the current intensity. A short time was obtained for the laser module power supply current to reach a stable state after precisely controlling the current, further reducing the overall power consumption of the instrument. 20 groups of water samples were configured with different chlorophyll-a concentrations using Chlorella chlorophyll in the instrument calibration test, referring to the range of chlorophyll-a concentration under different water bloom levels. The fitting model was established using the linear relationship between the fluorescence value at 680nm and the concentration of chlorophyll-a, where the coefficient of determination R² was 0.99. In the performance verification test, the green algae Chlorella and Microcystis aeruginosa were used to prepare 6 groups of water samples to be tested with different dominant algae species. The average measurement error of the instrument was within 5.48% under 2 groups of different light intensities. The test results show that the instrument performed stably to effectively detect the samples to be tested. There was no significant effect of the chlorophyll content in the water samples on the detection, due to the different types of algae, indicating the high detection accuracy. The finding can provide more convenient, cost-effective equipment support in the field of water quality monitoring, in order to realize all-weather monitoring chlorophyll-a concentration. [ABSTRACT FROM AUTHOR]

Overfishing has been one of the greatest risks to marine biodiversity in the world in recent years. Thus, the production of many catches is in a yearly decline, including Acetes chinensis. At the same time, an Acetes chinensis quota has been introduced to promise the marine conservation of biodiversity in China in 2020. Accurate and rapid quantification of fishing vessel fishing information can be one of the most important prerequisites to implementing the fine management of quota fishing. This study aims to perform the target identification and statistics quantification of Acetes chinensis quota fishing. An electronic monitoring (EM) device was installed on Acetes chinensis quota fishing vessels to monitor the main operation process of fishing vessels. An improved target detection algorithm (YOLOv7-MO) and target counting algorithm (YOLOv7- MO-SORT) using YOLOv7 were proposed to realize the target detection and statistics of Acetes chinensis quota fishing vessels. The YOLOv7-MO target detection algorithm used the MobileOne as the backbone network. The C3 modules were added to the head part of the output during the pruning operation. The YOLOv7-MO-SORT target counting algorithm was selected to replace the Faster R-CNN from the SORT (Simple Online and Realtime Tracking) algorithm replaced by YOLOv7- MO for the detection of anchors thrown during fishing operations and baskets containing Acetes chinensis. Kalman filtering and Hungarian matching algorithms were used to track and predict the detected targets, according to the characteristics of actual production operations. The collision detection lines, timestamps, thresholds, and counters were set to count the number of baskets of Acetes chinensis caught and nets during the fishing operation. The results show: (1) The improved YOLOv7-MO was achieved in average detection accuracy, recall, and F1 score of 97.3%, 96.0%, and 96.6%, respectively, on the test set, which were improved by 2.0, 1.1 and 1.5 percentage points, compared with the original model. (2) The improved YOLOv7- MO model size, the number of parameters, and the number of floating-point operations were 64.0 MB, 32.6 M, and 39.7 G, respectively, which were 10.2%, 10.6%, and 61.6% smaller than those of the YOLOv7 model. (3) The accuracy of the SORT algorithm Acetes chinensis fishing operation count with YOLOv7-MO as the detector reached 80.0% and 95.8% in counting the number of Acetes chinensis baskets and the number of nets, respectively. YOLOv7-MO reduced the model magnitude while improving the detection accuracy and efficiency. The SORT algorithm with the YOLOv7-MO as the detection head was also achieved in more accurate statistical quantification of the main operational information of fishing vessels. This function can be expected to facilitate the management and recording of fishing vessel operations, in order to avoid some drawbacks of the traditional manual recording of fishing vessel operations. The gross shrimp basket count statistics can provide better convenience to calculate the fishing parameters, such as the gross shrimp CPUE. The identification can be realized to count the fishing vessel operation of hairy shrimp fishing. The finding can also provide a strong reference to realize the automation and intelligence of recording fishing operations in offshore vessels, particularly for the decision-making on the hairy shrimp quota fishing. [ABSTRACT FROM AUTHOR]

An accurate forecast can be greatly contributed to the yellowfin tuna fishing ground in the western and Central Pacific. However, a large amount of fishery data, and high feature dimension have posed a great over-fitting on the various classification in recent years. The random forest parallel integration can be expected to achieve the excellent performance of the extreme gradient boosting decision tree algorithm. In this study, a hybrid integration model was proposed to combine the Xgboost with Random Forest (XGBRF) with the random forest and extreme gradient lifting decision tree. The fishery production data was also collected from the operation data of 43 distant-water longline fishing vessels of China Aquatic Group in the western and Central Pacific (0°-30°S; 110°E-170°W) from 2008 to 2019, including catch information, such as amount, job date, as well as the job latitude and longitude. A comparison was performed on the fishery data, including the concentration of chlorophyll a, eddy kinetic energy, sea surface height anomalies, temperature and salinity of the 0-500 m mixed water layer. A total of 36 variable combinations were used as the original data set, including the Southern Oscillation Index (SOI), the Arctic Oscillation Index (AOI), the Pacific Decadal Oscillation Index (PDOI), and North Pacific Gyre Oscillation Index (NPGOI). The original data set was divided into the training set and test set after the screening and normalization of the variance expansion factor, accounting for 80% and 20%, respectively. The training set was used to train eight models, including classification and regression, logistic regression, k-nearest neighbor, adaptive boosting, gradient boosting decision tree, xgboost, random forest, and XGBRF. The five-fold cross-validation was used for each model to determine the optimal parameters. Finally, the model was verified to superimpose the actual fishing ground of the test set. The experimental results showed that: 1) There was a significant correlation between the catch per unit fishing effort and various variable factors. There was also a great decrease in the degree of collinearity between the variables that were filtered by variance inflation factor. 2) The XGBRF hybrid ensemble model also significantly improved the performance of XGBoost and RF models. Specifically, the highest accuracy rate and Area Under Curve (AUC) were 75.39%, and 79.48%, respectively. The Receiver Operator Characteristic (ROC) curve of the XGBRF model was closer to the upper left, indicating the best performance of the forecasting model than before. 3) The sea surface temperature was the most important factor to dominate the distribution of yellowfin tuna fishing ground, accounting for 7.573%. The temperature of the 300 m water layer was equally important for the yellowfin tuna, which was 7.369%. In addition, the greater impact was also found in the salinity of the 50-meter water layer, the SOI, the concentration of chlorophyll a, and the surface salinity. There was a relatively low influence of other large-scale climatic factors, except for the SOI. 4) There was only a small deviation between the fishing ground predicted by the XGBRF model and the actual fishing ground, indicating the high accuracy and reliability of the prediction. Overall, the XGBRF ensemble model performed the best on the fishing ground forecast of yellowfin tuna in the western and Central Pacific. The finding can also provide a strong reference for the fishing ground forecast. [ABSTRACT FROM AUTHOR]

Fishing vessels have been ever-increasing to adopt the monitoring system for the combination of human and electronic observers, particularly with a high level of automation in the world. The data processing has required a simple configuration in the electronic monitoring system at present. It is urgent to improve the automation degree of the electronic monitoring system and the management efficiency of relevant fishing. In this study, the combined Convolutional Neural Network (CNN) with the Long Short Term Memory module (LSTM) was used to apply to the traditional electronic monitoring systems for the data extraction from the fishing vessel behavior of Japanese mackerel fishing in the light fishery. Nine types of fishing operations were divided, including sailing, putting net, waiting, pulling net, waiting for fish, organizing fish box, fish in, fish picking and reprinting, according to the operational characteristics of Japanese mackerel fishing boats. Four groups of parallel experiments were designed to compare the performance of a 3-layer CNN, a 3-layer CNN with an LSTM module (3-layer CNN-LSTM), an 8-layer CNN, and an 8-layer CNN with an LSTM module (8-layer CNN-LSTM) in a Japanese mackerel fishing boat during behavior extraction. Both CNN with LSTM modules were designed before the fully connected layers. The behaviors of nine fishing vessels presented the specific time characteristics, such as “pulling net” and “putting net”. Therefore, the 100 consecutive frames were then stitched horizontally to design the dataset during data processing. The frames per second of the video data was 25, and 100 was determined as the length of each dataset. The reason was that the human eye was normally observed the EM video data for 2-4 s to distinguish the two behaviors. Each data sample also contained certain time dimension information in the LSTM module. The test results show that the comprehensive evaluation index, the F1 score of the models that trained by the 3-layer CNN, 3-layer CNN-LSTM, 8-layer CNN, and 8-layer CNN-LSTM in the test set reached 0.794, 0.799, 0.966, and 0.972, respectively. In addition, the average detection speed of each model on three devices was measured to fully detect the detection efficiency of each model, including a laboratory supercomputer, small mobile workstation, and personal computer. The test samples of 5 000 data sets were taken 34.66, 34.50, 37.41, and 37.61 ms to process each piece using 3-layer CNN, 3-layer CNN-LSTM 8-layer CNN, and 8-layer CNN-LSTM on the supercomputer, respectively. In a small workstation, they were 85.47, 86.10, 120.13, and 121.15 ms in PC2, respectively, whereas, 93.77, 102.27, 118.51, and 124.50 ms in PC3, respectively, in the personal computer. Consequently, the network depth significantly improved the efficiency of the model within the specific range, but the detection time also increased significantly. Specifically, the F1 score of the 8-layer CNN increased from 0.794 to 0.966, while the training time increased from 23.028 to 29.624 h, compared with the 3-layer CNN. The LSTM module enhanced the performance of the network model with the sound detection time. Therefore, the CNN-LSTM modules presented excellent application prospects in the high real-time and high-precision scenarios of electronic monitoring systems. The finding can be expected to improve the automation degree of electronic monitoring systems for the better management efficiency of fishing boats. [ABSTRACT FROM AUTHOR]

In order to provide relevant information for natural resource management, impact assessment and marine spatial planning, high-resolution estimation of longline fishing gear is needed. Because the use of satellite vessel monitoring system (VMS) data is limited by data access and receiving offshore ship location information. In this paper, based on the data of automatic identification system (AIS) and logbook data of Chinese longline fishing from October to November 2017, a model of fishing detection based on support vector machine (SVM) learning method is established to classify the fishing and non fishing activities in the central and Western Pacific Ocean, to carry out longline fishing and draw fishing effort map in the Western and Central Pacific Ocean. Before constructing a fishing detection model, each AIS point was classified and pre-labeled as potential fishing and non-fishing events by an expert based on information on information on fisheries characteristics as obtained from literature, analysis of the tracks and logbook data. The performance of the fishing detection model was evaluated by the overall accuracy, precision, sensibility and specificity. Fishing intensities were computed from the known fishing positions and the estimated fishing positions were compared with correlation coefficient. The spatial correlation coefficient of fishing intensities and catch data was computed to quantify the extent to which the distribution of longline vessels describes tuna distribution. The results showed that the overall accuracy and the Kappa coefficient of the model training dataset were 95.24% and 0.9, respectively. The precision, sensibility and specificity were 94.74%, 93.44%, 96.56%, respectively. The overall accuracy and the Kappa coefficient of the model testing dataset were 93.85% and 0.87 respectively. The precision, sensibility and specificity were 93.49%, 90.67%, 95.91%, respectively. Then the constructed model was used to identify all the AIS data for 12 longline fishing vessels in the Western and Central Pacific in October and November 2017, with an overall accuracy rate of 83.3% and the Kappa coefficient was 0.67. The precision, sensibility and specificity were 82.33%, 88.32%, and 77.27%, respectively. The longline fishing distinct in October and November 2017 mainly located in 168°E-173°E, 12°S-18°S, and there were three obvious high fishing intensity areas on the map. The spatial distribution of fishing effort was significantly different between October and November. The distribution of fishing intensity in November was closer to the island than in October and the value of fishing intensity in October was lower than November. The fishing intensity information based on the SVM model and logbook data records was highly correlated (r>0.98). The spatial distribution characteristics of the fishing effort of the fishing vessel identified by the SVM model were similar to the known fishing positions. But the fishing intensities were calculated from known fishing positions was higher than that of estimated fishing positions. The spatial correlation coefficients of cumulative fishing effort and catch per unit of effort (CPUE), catch tail, catch weight and number of hooks were 0.68, 0.93, 0.93 and 0.94, respectively. The fishing capacity of fishing vessels based on AIS information mining can also be used as an alternative method for fishery resource analysis. [ABSTRACT FROM AUTHOR]