[论文解读] Decision Support Systems in Fisheries and Aquaculture: A systematic review

Bjørn Magnus Mathisen, Peter Halland Haro+3 more|arXiv (Cornell University)|Nov 25, 2016

Marine and fisheries research被引用 8

一句话总结

本篇系统性综述分析了27项关于渔业和水产养殖领域决策支持系统（DSS）的研究，揭示了缺乏具备实时分析能力、多利益相关方参与及多准则评估的DSS。研究发现，实证评估有限，且基于真实数据的机器学习应用极少，凸显了在可持续和高效渔业与水产养殖管理中，集成化、数据驱动的DSS存在关键性缺口。

ABSTRACT

Decision support systems help decision makers make better decisions in the face of complex decision problems (e.g. investment or policy decisions). Fisheries and Aquaculture is a domain where decision makers face such decisions since they involve factors from many different scientific fields. No systematic overview of literature describing decision support systems and their application in fisheries and aquaculture has been conducted. This paper summarizes scientific literature that describes decision support systems applied to the domain of Fisheries and Aquaculture. We use an established systematic mapping survey method to conduct our literature mapping. Our research questions are: What decision support systems for fisheries and aquaculture exists? What are the most investigated fishery and aquaculture decision support systems topics and how have these changed over time? Do any current DSS for fisheries provide real- time analytics? Do DSSes in Fisheries and Aquaculture build their models using machine learning done on captured and grounded data? The paper then detail how we employ the systematic mapping method in answering these questions. This results in 27 papers being identified as relevant and gives an exposition on the primary methods concluded in the study for designing a decision support system. We provide an analysis of the research done in the studies collected. We discovered that most literature does not consider multiple aspects for multiple stakeholders in their work. In addition we observed that little or no work has been done with real-time analysis in these decision support systems.

研究动机与目标

• 识别并绘制渔业和水产养殖领域现有决策支持系统（DSS）的全景图。
• 评估关于多准则、多利益相关方DSS应用的研究广度与关注重点。
• 评估这些领域DSS中实时分析与机器学习集成的现状。
• 识别在渔业和水产养殖领域中实证评估与系统整合方面的研究缺口。
• 为未来开发具备实际应用价值的集成化、数据驱动DSS奠定基础。

提出的方法

• 采用预定义协议进行系统性文献映射，以确保可重复性并减少偏倚。
• 在科学数据库中采用多阶段搜索策略，使用领域特定关键词及其同义词。
• 根据预设的纳入/排除标准，筛选标题、摘要及全文以判断相关性。
• 按主题、系统类型、利益相关方关注点及方法论路径对入选研究进行分类。
• 分析所审查DSS中的系统设计模式、数据集成方法及建模技术。
• 评估所识别系统中机器学习及实时数据处理能力的应用情况。

实验结果

研究问题

• RQ1 渔业和水产养殖领域存在哪些决策支持系统？
• RQ2 渔业和水产养殖DSS中被研究最多的主题是什么？这些主题随时间如何演变？
• RQ3 当前渔业DSS是否提供实时分析？
• RQ4 渔业和水产养殖DSS是否使用基于捕获和真实数据训练的机器学习模型？

主要发现

• 从初始研究池中仅识别出27项相关研究，表明渔业和水产养殖领域DSS的研究体量相对有限。
• 大多数DSS集中于单一主题或狭窄准则，极少关注多利益相关方或多准则决策框架。
• 文献中几乎不存在对DSS性能的实证评估，表明缺乏在真实场景中的验证。
• 在所审查的文献中未发现任何DSS支持实时分析，尽管其在操作决策中具有潜在优势。
• 渔业和水产养殖DSS中的机器学习应用极少，且无系统报告使用真实捕获数据进行模型训练。
• 尽管小型DSS的组件已可获取，但缺乏对跨物种和地理区域的多因素整合、且有良好文档记录的系统。