Illuminating dark fishing fleets in North Korea

Park, Jaeyoon; Lee, Jung-Sam; Seto, Katherine; Hochberg, Timothy; Wong, Brian A.; Miller, Nathan A.; Takasaki, Kenji; Kubota, Hiroshi; Oozeki, Yoshioki; Doshi, Sejal; Midzik, Maya; Hanich, Quentin A; Sullivan, Brian J.; Woods, Paul; Kroodsma, David

doi:10.1126/sciadv.abb1197

Cited by 95 publications

(86 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DNA barcoding also can play a role in deterring IUU fishing by empowering ports and landing sites with quick testing for illegal catch of protected species (Ogden, 2008;Ardura et al, 2013). Other efforts to combat IUU fishing have shown promise, like Global Fishing Watch which has been employed to identify suspect or illegal activities via satellite imagery, typically linked to overexploitation, such as the "dark fishing fleets" (Park et al, 2020). Furthermore, data technologies such as blockchains can help traceability of a fished product along the supply chain, and provide a decentralized system for logging catch statistics that does not rely on different national institutions with varying capacity and incentives for accurate reporting (Probst, 2020).…”

Section: Discussionmentioning

confidence: 99%

Substantial Gaps in the Current Fisheries Data Landscape

et al. 2020

View full text Add to dashboard Cite

Effective management of aquatic resources, wild and farmed, has implications for the livelihoods of dependent communities, food security, and ecosystem health. Good management requires information on the status of harvested species, yet many gaps remain in our understanding of these species and systems, in particular the lack of taxonomic resolution of harvested species. To assess these gaps we compared the occurrence of landed species (freshwater and marine) from the United Nations Food and Agriculture Organization (FAO) global fisheries production database to those in the International Union for Conservation of Nature (IUCN) Red List and the RAM Legacy Stock Assessment Database, some of the largest and most comprehensive global datasets of consumed aquatic species. We also quantified the level of resolution and trends in taxonomic reporting for all landed taxa in the FAO database. Of the 1,695 consumed aquatic species or groups in the FAO database considered in this analysis, a large portion (35%) are missing from both of the other two global datasets, either IUCN or RAM, used to monitor, manage, and protect aquatic resources. Only a small number of all fished taxa reported in FAO data (150 out of 1,695; 9%) have both a stock assessment in RAM and a conservation assessment in IUCN. Furthermore, 40% of wild caught landings are not reported to the species level, limiting our ability to effectively account for the environmental impacts of wild harvest. Landings of invertebrates (44%) and landings in Asia (>75%) accounted for the majority of harvest without species specific information in 2018. Assessing the overlap of species which are both farmed and fished to broadly map possible interactions – which can help or hinder wild populations - we found 296 species, accounting for 12% of total wild landings globally, and 103 countries and territories that have overlap in the species caught in the wild and produced through aquaculture. In all, our work highlights that while fisheries management is improving in many areas there remain key gaps in data resolution that are critical for fisheries assessments and conservation of aquatic systems into the future.

show abstract

Section: Discussionmentioning

confidence: 99%

Substantial Gaps in the Current Fisheries Data Landscape

et al. 2020

View full text Add to dashboard Cite

show abstract

“…(3) For deep-learning-based ship detection, a ship is generally represented as a rectangular box where the width and height are the two core parameters of a rectangular box, and when using deep learning for SAR ship detection, the final detection results are also generally represented by a series of rectangular boxes, instead of the ship length L and the ship breadth B. (4) In fact, there is still a lot of resistance to obtain the physical size of the ship (i.e., the ship length L and the ship breadth B), because it is difficult to obtain these accurate information comprehensively from the limited AIS data (i.e., there are still some "dark" ships [9,92] that fish illegally, smuggle in illegally, etc., which cannot be monitored by AIS, whose ship length L and ship breadth B cannot be obtained; see more detail in references [9,92]). Given the above, it does not affect the core work of this paper if not using the ship length L and ship breadth B, because (1) the width and height of a ship ground truth rectangular box have been able to describe ship pixel size well, merely not containing more information when compared to the ship length L and ship breadth B; (2) different from the ship recognition or classification task in OpenSARShip [80] that may need specific the ship length L and ship breadth B to represent ship features to enhance recognition accuracy, our LS-SSDD-v1.0 only focus on ship location, which means just using a simple rectangle box to frame the ship; and (3) similar to the other datasets, we only use a vertical or horizontal rectangular box to locate the center point of the ship, not considering the direction estimation of rotatable boxes in references [11,93] that may be involved with the ship length L and ship breadth B.…”

Section: Nomentioning

confidence: 99%

LS-SSDD-v1.0: A Deep Learning Dataset Dedicated to Small Ship Detection from Large-Scale Sentinel-1 SAR Images

Zhang

et al. 2020

Remote Sensing

191

View full text Add to dashboard Cite

Ship detection in synthetic aperture radar (SAR) images is becoming a research hotspot. In recent years, as the rise of artificial intelligence, deep learning has almost dominated SAR ship detection community for its higher accuracy, faster speed, less human intervention, etc. However, today, there is still a lack of a reliable deep learning SAR ship detection dataset that can meet the practical migration application of ship detection in large-scene space-borne SAR images. Thus, to solve this problem, this paper releases a Large-Scale SAR Ship Detection Dataset-v1.0 (LS-SSDD-v1.0) from Sentinel-1, for small ship detection under large-scale backgrounds. LS-SSDD-v1.0 contains 15 large-scale SAR images whose ground truths are correctly labeled by SAR experts by drawing support from the Automatic Identification System (AIS) and Google Earth. To facilitate network training, the large-scale images are directly cut into 9000 sub-images without bells and whistles, providing convenience for subsequent detection result presentation in large-scale SAR images. Notably, LS-SSDD-v1.0 has five advantages: (1) large-scale backgrounds, (2) small ship detection, (3) abundant pure backgrounds, (4) fully automatic detection flow, and (5) numerous and standardized research baselines. Last but not least, combined with the advantage of abundant pure backgrounds, we also propose a Pure Background Hybrid Training mechanism (PBHT-mechanism) to suppress false alarms of land in large-scale SAR images. Experimental results of ablation study can verify the effectiveness of the PBHT-mechanism. LS-SSDD-v1.0 can inspire related scholars to make extensive research into SAR ship detection methods with engineering application value, which is conducive to the progress of SAR intelligent interpretation technology. LS-SSDD-v1.0 is available at https://github.com/TianwenZhang0825/LS-SSDD-v1.0-OPEN.

show abstract

“…For instance, the influx of large, commercial-scale Chinese fishing fleets into North Korean waters has largely pushed the small scale DPRK fishermen farther from port and into Russian waters in search of squid, despite the fact that DPRK fishing vessels are generally too small for such a voyage. 19 Climate change will also make existing fisheries agreements more difficult to manage, even without expansion of DFFs. Many individual global fisheries are regulated by Regional Fishery Management Organizations, which cooperatively set rules for fishing stakeholders within a geographically bound area.…”

Section: Climate Change and Fishery Conflictmentioning

confidence: 99%

Why Climate Change and State Subsidies Will Collide to Create Fishery Conflict

Kelman

2020

JSS

View full text Add to dashboard Cite

Climate change, combined with rising global demand for seafood products, will lead to greater conflict over remaining fisheries. Warming and acidifying oceans are shifting the availability of oxygen and nutrients that are necessary to maintain fish stocks. These changes are likely to increase conflict, both interstate and intrastate, in several important ways. For one, the fish stocks that are already under stress from demand for seafood protein are also shifting location. Most significantly, scarcity will likely draw in greater state involvement in fisheries. As traditional fleets exhaust their territorial waters, domestic political pressure will lead to greater state investment in distant water fishing (DWF) fleets to access fish stocks on the high seas and in the Exclusive Economic Zones (EEZs) of other states. DWF fleets are destabilizing because they can easily access fishing zones with low levels of enforcement. Their industrial scale and low level of transparency means that they are also more likely to engage in Illegal, Unreported, and Unregulated (IUU) fishing activities. States are also more likely to intervene militarily to protect their state-support DWF fleets.

show abstract

Illuminating dark fishing fleets in North Korea

Cited by 95 publications

References 37 publications

Substantial Gaps in the Current Fisheries Data Landscape

Substantial Gaps in the Current Fisheries Data Landscape

LS-SSDD-v1.0: A Deep Learning Dataset Dedicated to Small Ship Detection from Large-Scale Sentinel-1 SAR Images

Why Climate Change and State Subsidies Will Collide to Create Fishery Conflict

Contact Info

Product

Resources

About