渔业科学杂志.com

  • 期刊 h 指数: 30
  • 期刊引用分数: 25.50
  • 期刊影响因子: 21.90
索引于
  • 学术期刊数据库
  • Genamics 期刊搜索
  • 全球影响因子 (GIF)
  • 中国知网(CNKI)
  • 引用因子
  • 电子期刊图书馆
  • 国际农业与生物科学中心 (CABI)
  • 研究期刊索引目录 (DRJI)
  • OCLC-WorldCat
  • 普罗奎斯特传票
  • 普布隆斯
  • 米亚尔
  • 高级科学索引
  • 谷歌学术
  • 化学文摘
  • 夏尔巴罗密欧
  • 秘密搜索引擎实验室
  • 研究之门
  • 残疾大学
分享此页面

抽象的

Rhizostome Fish Forecasting Using Available Data: International Statistics and Hooks

Shiva Shankar

As climate change accelerates, biodiversity declines, and ecosystems change, it becomes increasingly difficult to capture dynamic populations, track changes, and predict responses to climate change. At the same time, publicly available databases and tools will increase access to science, foster collaboration, and generate more data than ever before. One of his most successful projects is his AI-driven Social His Network, which also serves as a public database designed to allow citizen scientists to accurately report their personal biodiversity accounts. It's his iNaturalist. INaturalist is particularly useful for studying rare, dangerous and charismatic organisms, but requires better integration into marine systems. Despite their abundance and ecological importance, fish species are difficult to manage due to the lack of long-term datasets with large numbers of samples. 8,412 data curated from both iNaturalist (n = 7,807) and published literature (n = 7,807) to provide a large sample size dataset and demonstrate the utility of publicly collected data We synthesized two global datasets of 10 fish species of the order Rhizostomeae, including points. 605) included). These reports were then used in combination with publicly available environmental data to predict global niche segmentation and distribution. The first niche model revealed that only 2 out of 10 genres have different niche areas. However, application of machine learning-based random forest models suggests species-specific differences in the association of abiotic environmental variables used to predict fish populations. Our approach of integrating reports from the literature with iNaturalist data helped us assess the quality of the models and, more importantly, the quality of the underlying data. We believe that freely accessible online data are valuable but subject to bias due to their limited taxonomic, geographic and ecological resolution. With underrepresented local experts, celebrities and enthusiasts who can implement locally coordinated projects and increase global participation to improve the resolution and meaning of the data. We encourage you to cooperate.

Keywords

Fish: Random forests model; Online databases; Citizen science; Naturalist; Cnidaria