Convolutional-LSTM approach for temporal catch hotspots (CATCH): an AI-driven model for spatiotemporal forecasting of fisheries catch probability densities.

IF 1.3 Q3 BIOCHEMICAL RESEARCH METHODS
Biology Methods and Protocols Pub Date : 2025-06-02 eCollection Date: 2025-01-01 DOI:10.1093/biomethods/bpaf045
Altair Agmata, Svanur Guðmundsson
{"title":"Convolutional-LSTM approach for temporal catch hotspots (CATCH): an AI-driven model for spatiotemporal forecasting of fisheries catch probability densities.","authors":"Altair Agmata, Svanur Guðmundsson","doi":"10.1093/biomethods/bpaf045","DOIUrl":null,"url":null,"abstract":"<p><p>Efficient fisheries management is crucial for sustaining both marine ecosystems and the economies that heavily depend on them, such as Iceland. Current fishing practices involve decisions informed by a combination of personal experience, current data on environmental and oceanographic conditions, reports from other captains, and target species within the constraints of the fishing quota. However, the intricate spatiotemporal dynamics of fish behaviour make it difficult to predict fish stock distributions. Despite technological breakthroughs in fishing vessel data collection, much of the decision-making still relies heavily on subjective judgement, highlighting the need for more robust, data-driven predictive methods. This paper presents CATCH, a convolutional long short-term memory neural network model that forecasts fish stock probability densities over time and space in Icelandic waters to support operational planning and adaptive strategy in fisheries. The framework represents the first utilization of large-scale Icelandic fishing fleet data integrating multidimensional inputs, particularly depth, bottom temperature, salinity, dissolved oxygen and catch data, to produce accurate, multivariate forecasts. The model achieves favourable performance with average RMSE, MAE, WD, and SSI of 4.71 × 10<sup>-3</sup>, 1.16 × 10<sup>-3</sup>, 0.94 × 10<sup>-3</sup>, and 0.955, respectively, for cod, while 6.13 × 10<sup>-3</sup>, 1.25 × 10<sup>-3</sup>, 1.04 × 10<sup>-3</sup>, and 0.949, respectively, across other target species (haddock, saithe, golden redfish, and Greenland halibut). Additionally, Syrjala's test yielded nonsignificant <i>P</i>-values (<i>P</i> > .05) in most cases across lags and forecast horizons, indicating that the predicted and observed distributions are statistically indistinguishable. Its promising results suggest deep learning models have the potential to optimize fisheries operations, enhance sustainability, and support data-driven decision-making.</p>","PeriodicalId":36528,"journal":{"name":"Biology Methods and Protocols","volume":"10 1","pages":"bpaf045"},"PeriodicalIF":1.3000,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12203189/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Biology Methods and Protocols","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1093/biomethods/bpaf045","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q3","JCRName":"BIOCHEMICAL RESEARCH METHODS","Score":null,"Total":0}
引用次数: 0

Abstract

Efficient fisheries management is crucial for sustaining both marine ecosystems and the economies that heavily depend on them, such as Iceland. Current fishing practices involve decisions informed by a combination of personal experience, current data on environmental and oceanographic conditions, reports from other captains, and target species within the constraints of the fishing quota. However, the intricate spatiotemporal dynamics of fish behaviour make it difficult to predict fish stock distributions. Despite technological breakthroughs in fishing vessel data collection, much of the decision-making still relies heavily on subjective judgement, highlighting the need for more robust, data-driven predictive methods. This paper presents CATCH, a convolutional long short-term memory neural network model that forecasts fish stock probability densities over time and space in Icelandic waters to support operational planning and adaptive strategy in fisheries. The framework represents the first utilization of large-scale Icelandic fishing fleet data integrating multidimensional inputs, particularly depth, bottom temperature, salinity, dissolved oxygen and catch data, to produce accurate, multivariate forecasts. The model achieves favourable performance with average RMSE, MAE, WD, and SSI of 4.71 × 10-3, 1.16 × 10-3, 0.94 × 10-3, and 0.955, respectively, for cod, while 6.13 × 10-3, 1.25 × 10-3, 1.04 × 10-3, and 0.949, respectively, across other target species (haddock, saithe, golden redfish, and Greenland halibut). Additionally, Syrjala's test yielded nonsignificant P-values (P > .05) in most cases across lags and forecast horizons, indicating that the predicted and observed distributions are statistically indistinguishable. Its promising results suggest deep learning models have the potential to optimize fisheries operations, enhance sustainability, and support data-driven decision-making.

时序捕捞热点(catch)的卷积- lstm方法:一种人工智能驱动的渔业捕捞概率密度时空预测模型。
有效的渔业管理对于维持海洋生态系统和严重依赖海洋生态系统的经济(如冰岛)至关重要。目前的捕鱼做法涉及综合考虑个人经验、当前环境和海洋学条件数据、其他船长的报告以及捕捞配额限制内的目标鱼种所作出的决定。然而,鱼类行为的复杂时空动态使得预测鱼类种群分布变得困难。尽管渔船数据收集技术取得了突破,但大部分决策仍然严重依赖主观判断,这凸显了对更强大、数据驱动的预测方法的需求。本文介绍了CATCH,这是一个卷积长短期记忆神经网络模型,可以预测冰岛水域随时间和空间变化的鱼类种群概率密度,以支持渔业的运营规划和适应策略。该框架是第一次利用大型冰岛渔船队数据,整合多方面的投入,特别是深度、海底温度、盐度、溶解氧和渔获量数据,以产生准确的多元预测。该模型对鳕鱼的平均RMSE、MAE、WD和SSI分别为4.71 × 10-3、1.16 × 10-3、0.94 × 10-3和0.955,对其他目标鱼种(黑线鳕、塞氏、金红鱼和格陵兰大比目鱼)的平均RMSE、MAE、WD和SSI分别为6.13 × 10-3、1.25 × 10-3、1.04 × 10-3和0.949,取得了较好的效果。此外,Syrjala的检验在大多数情况下产生了不显著的P值(P >.05),这表明预测和观测的分布在统计上无法区分。其令人鼓舞的结果表明,深度学习模型有潜力优化渔业运营,提高可持续性,并支持数据驱动的决策。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Biology Methods and Protocols
Biology Methods and Protocols Agricultural and Biological Sciences-Agricultural and Biological Sciences (all)
CiteScore
3.80
自引率
2.80%
发文量
28
审稿时长
19 weeks
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信