Scholarlink

<p>DNA-based biodiversity surveys result in massive-scale data, including up to millions of species—of which, most are rare. Making the most of such data for inference and prediction requires modeling approaches that can relate species occurrences to environmental and spatial predictors, while incorporating information about their taxonomic or phylogenetic placement. Even if the scalability of joint species distribution models to large communities has greatly advanced, incorporating hundreds of thousands of species has not been feasible to date, leading to compromised analyses. Here we present a ‘common to rare transfer learning’ (CORAL) approach, based on borrowing information from the common species to enable statistically and computationally efficient modeling of both common and rare species. We illustrate that CORAL leads to much improved prediction and inference in the context of DNA metabarcoding data from Madagascar, comprising 255,188 arthropod species detected in 2,874 samples.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Common to rare transfer learning (CORAL) enables inference and prediction for a quarter million rare Malagasy arthropods

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年9月23日

查看全文
  • Otso Ovaskainen,
  • Steven Winter,
  • Gleb Tikhonov,
  • Nerea Abrego,
  • Sten Anslan,
  • Jeremy R. deWaard,
  • Stephanie L. deWaard,
  • Brian L. Fisher,
  • Brendan Furneaux,
  • Bess Hardwick,
  • Deirdre Kerdraon,
  • Mikko Pentinsaari,
  • Dimby Raharinjanahary,
  • Eric Tsiriniaina Rajoelison,
  • Sujeevan Ratnasingham,
  • Panu Somervuo,
  • Jayme E. Sones,
  • Evgeny V. Zakharov,
  • Paul D. N. Hebert,
  • Tomas Roslin,
  • David Dunson

摘要

DNA-based biodiversity surveys result in massive-scale data, including up to millions of species—of which, most are rare. Making the most of such data for inference and prediction requires modeling approaches that can relate species occurrences to environmental and spatial predictors, while incorporating information about their taxonomic or phylogenetic placement. Even if the scalability of joint species distribution models to large communities has greatly advanced, incorporating hundreds of thousands of species has not been feasible to date, leading to compromised analyses. Here we present a ‘common to rare transfer learning’ (CORAL) approach, based on borrowing information from the common species to enable statistically and computationally efficient modeling of both common and rare species. We illustrate that CORAL leads to much improved prediction and inference in the context of DNA metabarcoding data from Madagascar, comprising 255,188 arthropod species detected in 2,874 samples.