Simulation and Identification of the Habitat of Antarctic Krill Based on Vessel Position Data and Integrated Species Distribution Model: A Case Study of Pumping-Suction Beam Trawl Fishing Vessels
This study, based on the vessel position data of pump-suction beam trawlers and the integrated species distribution model (ISDM), deeply analyzes the spatio-temporal distribution characteristics of the habitat of Antarctic krill and the contributions of key environmental factors. The Convolutional N...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Animals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-2615/15/11/1557 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849723885549780992 |
|---|---|
| author | Heng Zhang Yuyan Sun Hanji Zhu Delong Xiang Jianhua Wang Famou Zhang Sisi Huang Yang Li |
| author_facet | Heng Zhang Yuyan Sun Hanji Zhu Delong Xiang Jianhua Wang Famou Zhang Sisi Huang Yang Li |
| author_sort | Heng Zhang |
| collection | DOAJ |
| description | This study, based on the vessel position data of pump-suction beam trawlers and the integrated species distribution model (ISDM), deeply analyzes the spatio-temporal distribution characteristics of the habitat of Antarctic krill and the contributions of key environmental factors. The Convolutional Neural Network–attention model (CNN–attention model) was used to identify the fishing status of the vessel position data of Norwegian pump-suction beam trawlers for Antarctic krill during the fishing seasons from 2021 to 2023. Variables of marine environment, including sea surface temperature (SST), sea surface height (SSH), chlorophyll concentration (CHL), sea ice concentration (SIC), sea surface salinity (SSS), and spatial factor Geographical Offshore Linear Distance (GLD) were combined and input into the ISDM for simulating and predicting the spatial distribution of the habitat. The model results show that the Area Under the Curve (AUC) and True Skill Statistic (TSS) indices for all months exceed 0.9, with an average AUC of 0.997 and a TSS of 0.973, indicating extremely high accuracy of the model in habitat prediction. Further analysis of environmental factors reveals that Geographical Offshore Linear Distance (GLD) and chlorophyll concentration (CHL) are the main factors affecting habitat suitability, contributing 34.9% and 25.2%, respectively, and their combined contribution exceeds 60%. In addition, factors such as sea surface height (SSH), sea surface temperature (SST), sea ice concentration (SIC), and sea surface salinity (SSS) have impacts on the habitat distribution to varying degrees, and each factor exhibits different suitability response characteristics in different seasons and sub-regions. There is no significant correlation between the habitat area of Antarctic krill and catch (<i>p</i> > 0.05), while there is a significant positive correlation between the fishing duration and the catch (<i>p</i> < 0.001), indicating that a longer fishing duration can effectively increase the Antarctic krill catch. |
| format | Article |
| id | doaj-art-825feea9529a470aaccf7a76fbd60b38 |
| institution | DOAJ |
| issn | 2076-2615 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Animals |
| spelling | doaj-art-825feea9529a470aaccf7a76fbd60b382025-08-20T03:10:54ZengMDPI AGAnimals2076-26152025-05-011511155710.3390/ani15111557Simulation and Identification of the Habitat of Antarctic Krill Based on Vessel Position Data and Integrated Species Distribution Model: A Case Study of Pumping-Suction Beam Trawl Fishing VesselsHeng Zhang0Yuyan Sun1Hanji Zhu2Delong Xiang3Jianhua Wang4Famou Zhang5Sisi Huang6Yang Li7Key Laboratory of Oceanic and Polar Fisheries, Ministry of Agriculture and Rural Affairs, East China Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences, Shanghai 200090, ChinaKey Laboratory of Oceanic and Polar Fisheries, Ministry of Agriculture and Rural Affairs, East China Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences, Shanghai 200090, ChinaKey Laboratory of Oceanic and Polar Fisheries, Ministry of Agriculture and Rural Affairs, East China Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences, Shanghai 200090, ChinaKey Laboratory of Oceanic and Polar Fisheries, Ministry of Agriculture and Rural Affairs, East China Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences, Shanghai 200090, ChinaKey Laboratory of Oceanic and Polar Fisheries, Ministry of Agriculture and Rural Affairs, East China Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences, Shanghai 200090, ChinaKey Laboratory of Oceanic and Polar Fisheries, Ministry of Agriculture and Rural Affairs, East China Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences, Shanghai 200090, ChinaKey Laboratory of Oceanic and Polar Fisheries, Ministry of Agriculture and Rural Affairs, East China Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences, Shanghai 200090, ChinaKey Laboratory of Oceanic and Polar Fisheries, Ministry of Agriculture and Rural Affairs, East China Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences, Shanghai 200090, ChinaThis study, based on the vessel position data of pump-suction beam trawlers and the integrated species distribution model (ISDM), deeply analyzes the spatio-temporal distribution characteristics of the habitat of Antarctic krill and the contributions of key environmental factors. The Convolutional Neural Network–attention model (CNN–attention model) was used to identify the fishing status of the vessel position data of Norwegian pump-suction beam trawlers for Antarctic krill during the fishing seasons from 2021 to 2023. Variables of marine environment, including sea surface temperature (SST), sea surface height (SSH), chlorophyll concentration (CHL), sea ice concentration (SIC), sea surface salinity (SSS), and spatial factor Geographical Offshore Linear Distance (GLD) were combined and input into the ISDM for simulating and predicting the spatial distribution of the habitat. The model results show that the Area Under the Curve (AUC) and True Skill Statistic (TSS) indices for all months exceed 0.9, with an average AUC of 0.997 and a TSS of 0.973, indicating extremely high accuracy of the model in habitat prediction. Further analysis of environmental factors reveals that Geographical Offshore Linear Distance (GLD) and chlorophyll concentration (CHL) are the main factors affecting habitat suitability, contributing 34.9% and 25.2%, respectively, and their combined contribution exceeds 60%. In addition, factors such as sea surface height (SSH), sea surface temperature (SST), sea ice concentration (SIC), and sea surface salinity (SSS) have impacts on the habitat distribution to varying degrees, and each factor exhibits different suitability response characteristics in different seasons and sub-regions. There is no significant correlation between the habitat area of Antarctic krill and catch (<i>p</i> > 0.05), while there is a significant positive correlation between the fishing duration and the catch (<i>p</i> < 0.001), indicating that a longer fishing duration can effectively increase the Antarctic krill catch.https://www.mdpi.com/2076-2615/15/11/1557Antarctic krillvessel position dataenvironmental dataspecies distribution modelhabitat research |
| spellingShingle | Heng Zhang Yuyan Sun Hanji Zhu Delong Xiang Jianhua Wang Famou Zhang Sisi Huang Yang Li Simulation and Identification of the Habitat of Antarctic Krill Based on Vessel Position Data and Integrated Species Distribution Model: A Case Study of Pumping-Suction Beam Trawl Fishing Vessels Animals Antarctic krill vessel position data environmental data species distribution model habitat research |
| title | Simulation and Identification of the Habitat of Antarctic Krill Based on Vessel Position Data and Integrated Species Distribution Model: A Case Study of Pumping-Suction Beam Trawl Fishing Vessels |
| title_full | Simulation and Identification of the Habitat of Antarctic Krill Based on Vessel Position Data and Integrated Species Distribution Model: A Case Study of Pumping-Suction Beam Trawl Fishing Vessels |
| title_fullStr | Simulation and Identification of the Habitat of Antarctic Krill Based on Vessel Position Data and Integrated Species Distribution Model: A Case Study of Pumping-Suction Beam Trawl Fishing Vessels |
| title_full_unstemmed | Simulation and Identification of the Habitat of Antarctic Krill Based on Vessel Position Data and Integrated Species Distribution Model: A Case Study of Pumping-Suction Beam Trawl Fishing Vessels |
| title_short | Simulation and Identification of the Habitat of Antarctic Krill Based on Vessel Position Data and Integrated Species Distribution Model: A Case Study of Pumping-Suction Beam Trawl Fishing Vessels |
| title_sort | simulation and identification of the habitat of antarctic krill based on vessel position data and integrated species distribution model a case study of pumping suction beam trawl fishing vessels |
| topic | Antarctic krill vessel position data environmental data species distribution model habitat research |
| url | https://www.mdpi.com/2076-2615/15/11/1557 |
| work_keys_str_mv | AT hengzhang simulationandidentificationofthehabitatofantarctickrillbasedonvesselpositiondataandintegratedspeciesdistributionmodelacasestudyofpumpingsuctionbeamtrawlfishingvessels AT yuyansun simulationandidentificationofthehabitatofantarctickrillbasedonvesselpositiondataandintegratedspeciesdistributionmodelacasestudyofpumpingsuctionbeamtrawlfishingvessels AT hanjizhu simulationandidentificationofthehabitatofantarctickrillbasedonvesselpositiondataandintegratedspeciesdistributionmodelacasestudyofpumpingsuctionbeamtrawlfishingvessels AT delongxiang simulationandidentificationofthehabitatofantarctickrillbasedonvesselpositiondataandintegratedspeciesdistributionmodelacasestudyofpumpingsuctionbeamtrawlfishingvessels AT jianhuawang simulationandidentificationofthehabitatofantarctickrillbasedonvesselpositiondataandintegratedspeciesdistributionmodelacasestudyofpumpingsuctionbeamtrawlfishingvessels AT famouzhang simulationandidentificationofthehabitatofantarctickrillbasedonvesselpositiondataandintegratedspeciesdistributionmodelacasestudyofpumpingsuctionbeamtrawlfishingvessels AT sisihuang simulationandidentificationofthehabitatofantarctickrillbasedonvesselpositiondataandintegratedspeciesdistributionmodelacasestudyofpumpingsuctionbeamtrawlfishingvessels AT yangli simulationandidentificationofthehabitatofantarctickrillbasedonvesselpositiondataandintegratedspeciesdistributionmodelacasestudyofpumpingsuctionbeamtrawlfishingvessels |