Projecting future changes in distributions of small-scale pelagic fisheries of the southern Colombian Pacific Ocean

Selvaraj, John Josephraj; Rosero-Henao, Leidy Viviana; Cifuentes-Ossa, Maria Alejandra

doi:10.1016/j.heliyon.2022.e08975

Cited by 8 publications

(11 citation statements)

References 31 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, neural networks have gradually become the preferred solution for image detection and object classification. In the fishery field, with a relatively low degree of informatization, neural networks have also been applied to a certain extent (Sarr et al, 2021;Selvaraj et al, 2022).…”

Section: Network Structure Optimizationmentioning

confidence: 99%

Developing machine learning methods for automatic recognition of fishing vessel behaviour in the Scomber japonicus fisheries

et al. 2023

View full text Add to dashboard Cite

IntroductionWith a higher degree of automation, fishing vessels have gradually begun adopting a fishing monitoring method that combines human and electronic observers. However, the objective data of electronic monitoring systems (EMS) has not yet been fully applied in various fishing boat scenarios such as ship behavior recognition.MethodsIn order to make full use of EMS data and improve the accuracy of behaviors recognition of fishing vessels, the present study proposes applying popular deep learning technologies such as convolutional neural network, long short-term memory, and attention mechanism to Chub mackerel (Scomber japonicus) fishing vessel behaviors recognition. The operation process of Chub mackerel fishing vessels was divided into nine kinds of behaviors, such as “pulling nets”, “putting nets”, “fish pick”, “reprint”, etc. According to the characteristics of their fishing work, four networks with different convolutional layers were designed in the pre-experiment. And the feasibility of each network in behavior recognition of the fishing vessels was observed. The pre-experiment is optimized from the perspective of the data set and the network. From the standpoint of the data set, the size of the optimized data set is significantly reduced, and the original data characteristics are preserved as much as possible. From the perspective of the network, different combinations of pooling, long short-term memory(LSTM) network, and attention(including CBAM and SE) are added to the network, and their effects on training time and recognition effect are compared.ResultsThe experimental results reveal that the deep learning methods have outstanding performance in behaviors recognition of fishing vessels. The LSTM and SE module combination produced the most apparent optimization effect on the network, and the optimized model can achieve an F1 score of 97.12% in the test set, surpassing the classic ResNet, VGGNet, and AlexNet.DiscussionThis research is of great significance to the management of intelligent fishery vessels and can promote the development of electronic monitoring systems for ships.

show abstract

Section: Network Structure Optimizationmentioning

confidence: 99%

Developing machine learning methods for automatic recognition of fishing vessel behaviour in the Scomber japonicus fisheries

et al. 2023

View full text Add to dashboard Cite

show abstract

“…The Pacific basin experimented with rapid changes in many ecosystems, driven by economic development (Romero 2009;Lozada-Ordóñez et al 2018). The most important anthropogenic disturbances in the Colombian Pacific basin are mainly due to historical deforestation (Leal and Restrepo 2003;Velez et al 2020;Gonzalez-Gonzalez et al 2021), continental or/and alluvial illegal mining (Romero 2009;Rodríguez-Zapata and Ruiz-Agudelo 2021), arms conflict and violence (Restrepo and Rojas 2004;Hougaard 2022), illegal crops (Romero 2009;Lobo and Vélez 2022), overfishing (Castellanos-Galindo et al 2018;Selvaraj et al 2022), and expansion of the agricultural and livestock frontier (Romero 2009;Velez et al 2020). Additionally, the persistence of poverty in this region of the country is another threat to biodiversity and ecosystem services (Lozada-Ordóñez et al 2018).…”

Section: Study Areamentioning

confidence: 99%

The natural capital of the Colombian Pacific basin. Challenges for a megadiverse region with little Government assistance

Agudelo

BONILLA

2022

Preprint

View full text Add to dashboard Cite

The Pacific region is considered a biodiversity hotspot and presents high species endemic levels. The Colombian Pacific basin occupies an area of approx. eight million hectares, located in the country's west. The literature about the economic valuation of ecosystem services (ES) and the spatial information on natural resources in the Colombian Pacific basin was revised through various information sources to document the earliest approximation to the state, spatial distribution, and economic value of the natural capital at the scale of biomes, specific ecosystems, and political-administrative units. Our assessment estimated a natural capital loss of 40 billion Int.$2020/year (15% of Colombian GDP in 2020) and a remnant natural capital worth 139 billion Int.$2020/year (51% of Colombia's GDP in 2020) for 15 ecosystem services. This research establishes that a potential expansion in livestock production systems will generate an additional loss of natural capital between six and eight billion Int.$2020/year. Additionally, we include an analysis based on the GLOBIO4 initiative models, identifying future natural capital losses between 7.5 and 7.6 billion Int.$2020/year. Lastly, the policy challenges and gaps in research and management concerning this remaining natural capital in the Colombian Pacific basin are pointed out.

show abstract

“…In the exploration and management of marine resources, accurate detection and localization of underwater resources are essential for their sustainable utilization. This area of application is extensive, encompassing, but not limited to, monitoring marine ecosystems [1], exploring underwater historical sites [2], and assessing the health of aquaculture [2]. To address the challenges posed by the limitations of traditional detection methods and the complexity of marine environments, this study investigates the use of intelligent sensors and automation technologies, such as Autonomous Underwater Vehicles (AUVs), underwater positioning and navigation systems, wireless underwater communication systems, and Remotely Operated Vehicles (ROVs), for efficient underwater exploration.…”

Section: Introductionmentioning

confidence: 99%

YOLOv8-Mu: An Improved YOLOv8 Underwater Detector Based on Large Kernel Block and Multi-branch Heavy Parameterization Module

Jiang,

Zhuang,

Chen

et al. 2024

Preprint

View full text Add to dashboard Cite

Underwater visual detection technology plays a pivotal role in fields such as marine exploration. With the increasing demand for underwater monitoring, the quest for efficient and reliable methods for underwater target recognition has become particularly significant. To address this requirement, this study developed an innovative underwater object detection architecture based on YOLOv8, named YOLOv8-MU, aimed at significantly enhancing detection accuracy.By integrating the LarK module proposed in UniRepLKNet to optimize the backbone network, YOLOv8-MU aims to achieve a larger receptive field without increasing the model’s depth. Further, this research introduces C2fSTR, an innovative method that combines Swin Transformer with the C2f module. Additionally, we have incorporated the SPPFCSPC_EMA module, which combines Cross-Stage Partial Fast Spatial Pyramid Pooling (SPPFCSPC) with attention mechanisms, significantly improving the detection accuracy and robustness of various biological targets. Moreover, by introducing a fusion block based on DAMO-YOLO into the neck of the model, we further enhanced the model’s capability in multi-scale feature extraction. Finally, the adoption of the MPDIoU loss function, designed around vertex distance, effectively tackles the challenges of localization accuracy and boundary clarity in underwater organism detection. Experimental results on the URPC2019 dataset demonstrate that the YOLOv8-MU model achieved an mAP@0.5 of 78.4%, marking improvements of 5.6%, 1.1%, and 4.0% over YOLOv5s, YOLOv7, and YOLOv8n respectively, indicating the leading performance (SOTA) of this method. On the other hand, further evaluation on the URPC2020 dataset confirmed the generalization capability of the YOLOv8-MU architecture, with its mAP@0.5 reaching 80.4%, surpassing various models including YOLOv5x and YOLOv8n, showcasing the wide applicability of our proposed improved model architecture.

show abstract

Projecting future changes in distributions of small-scale pelagic fisheries of the southern Colombian Pacific Ocean

Cited by 8 publications

References 31 publications

Developing machine learning methods for automatic recognition of fishing vessel behaviour in the Scomber japonicus fisheries

Developing machine learning methods for automatic recognition of fishing vessel behaviour in the Scomber japonicus fisheries

The natural capital of the Colombian Pacific basin. Challenges for a megadiverse region with little Government assistance

YOLOv8-Mu: An Improved YOLOv8 Underwater Detector Based on Large Kernel Block and Multi-branch Heavy Parameterization Module

Contact Info

Product

Resources

About