Machine-learning and thresholding algorithms to automatically predict fishing effort of small-scale trawl fishery

IF 1.4 4区农林科学 Q3 FISHERIES Fisheries Science Pub Date : 2024-01-05 DOI:10.1007/s12562-023-01734-1

{"title":"Machine-learning and thresholding algorithms to automatically predict fishing effort of small-scale trawl fishery","authors":"","doi":"10.1007/s12562-023-01734-1","DOIUrl":null,"url":null,"abstract":"<h3>Abstract</h3> <p>To assess fishery resources, it is necessary to easily obtain information on catch per unit effort, which is a resource indicator. In this study, two algorithms were developed for predicting the fishing effort (number of fishing operations, daily operating distance, and daily operating time) of a small-scale trawl fishery. These algorithms predict fishing efforts after preprocessing (including deleting outliers from the raw data), followed by classification of the operating conditions and threshold processing based on the operation period. One algorithm uses a machine-learning model for the classification process, and the other uses thresholding. The mean prediction error of the machine-learning algorithm on three datasets ranged from 1% to 11%, 2% to 8%, and 1% to 5% in terms of the number of operations, operating time, and operating distance, whereas that of the thresholding algorithm ranged from 3% to 52%, 2% to 5%, and 2% to 7%, respectively. A sensitivity analysis of the amount of training data indicated that prediction was possible using 5 days of training data. The developed algorithms are potentially useful for fish stock assessment.</p>","PeriodicalId":12231,"journal":{"name":"Fisheries Science","volume":"92 1","pages":""},"PeriodicalIF":1.4000,"publicationDate":"2024-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Fisheries Science","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.1007/s12562-023-01734-1","RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"FISHERIES","Score":null,"Total":0}

引用次数: 0

Abstract

To assess fishery resources, it is necessary to easily obtain information on catch per unit effort, which is a resource indicator. In this study, two algorithms were developed for predicting the fishing effort (number of fishing operations, daily operating distance, and daily operating time) of a small-scale trawl fishery. These algorithms predict fishing efforts after preprocessing (including deleting outliers from the raw data), followed by classification of the operating conditions and threshold processing based on the operation period. One algorithm uses a machine-learning model for the classification process, and the other uses thresholding. The mean prediction error of the machine-learning algorithm on three datasets ranged from 1% to 11%, 2% to 8%, and 1% to 5% in terms of the number of operations, operating time, and operating distance, whereas that of the thresholding algorithm ranged from 3% to 52%, 2% to 5%, and 2% to 7%, respectively. A sensitivity analysis of the amount of training data indicated that prediction was possible using 5 days of training data. The developed algorithms are potentially useful for fish stock assessment.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

自动预测小型拖网渔业捕捞强度的机器学习和阈值算法

摘要要评估渔业资源，就必须方便地获取作为资源指标的单位努力量渔获量信息。本研究开发了两种算法，用于预测小型拖网渔业的捕捞努力量（捕捞作业次数、日作业距离和日作业时间）。这些算法在预处理（包括删除原始数据中的异常值）后预测捕捞强度，然后根据作业期对作业条件和阈值进行分类处理。一种算法在分类过程中使用机器学习模型，另一种算法使用阈值处理。就操作次数、操作时间和操作距离而言，机器学习算法在三个数据集上的平均预测误差分别为 1%至 11%、2%至 8%和 1%至 5%，而阈值算法的平均预测误差分别为 3%至 52%、2%至 5%和 2%至 7%。对训练数据量的敏感性分析表明，使用 5 天的训练数据就可以进行预测。所开发的算法可用于鱼类种群评估。

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分钟内获得全文去求助

来源期刊

Fisheries Science 农林科学-渔业

CiteScore

3.80

自引率

5.30%

发文量

审稿时长

12-24 weeks

期刊介绍： Fisheries Science is the official journal of the Japanese Society of Fisheries Science, which was established in 1932. Recognized as a leading journal in its field, Fisheries Science is respected internationally for the publication of basic and applied research articles in a broad range of subject areas relevant to fisheries science. All articles are peer-reviewed by at least two experts in the field of the submitted paper. Published six times per year, Fisheries Science includes about 120 articles per volume. It has a rich history of publishing quality papers in fisheries, biology, aquaculture, environment, chemistry and biochemistry, food science and technology, and Social Science.