期刊
LIMNOLOGY AND OCEANOGRAPHY
卷 67, 期 8, 页码 1647-1669出版社
WILEY
DOI: 10.1002/lno.12101
关键词
-
资金
- Sentinelle Nord (Universite Laval, Quebec)
- MODELIFE (UCA)
- LOV (SU/CNRS)
- CNRS
- Institut des Sciences du Calcul et des Donnees (ISCD) of Sorbonne Universite (SU)
- Belmont Forum [ANR-18-BELM-0003-01]
- Quebec Ocean
- Takuvik Joint International Laboratory [UMI3376]
- CNRS - Universite Laval
- NSERC [RGPIN-2014-05433]
- Research Foundation - Flanders [FWO17/PDO/067]
- ETH Zurich
- Gordon and Betty Moore Foundation
- U.S. National Science Foundation
- Coordenacao de Aperfeicoamento de Pessoal de Nivel Superior (CAPES) [88882.438735/2019-01]
- French National Research Agency [ANR-19-CE01-0006]
- Spanish State Research Agency, Ministry of Science and Innovation [PTA2016-12822-I]
- Institut Universitaire de France (IUF)
- Simons Foundation [561126]
- U.S. National Science Foundation [CCF-1539256, OCE-1655686]
- Chair VISION from CNRS/Sorbonne Universite
- Agence Nationale de la Recherche (ANR) [ANR-19-CE01-0006, ANR-18-BELM-0003] Funding Source: Agence Nationale de la Recherche (ANR)
Plankton imaging systems, supported by automated classification and analysis, have enhanced the ability of ecologists to observe aquatic ecosystems. These systems enable the collection of imaging data at unprecedented levels of spatial and temporal resolution, allowing for reliable tracking of plankton populations. Additionally, the individual images themselves contain valuable information on functional traits, which can be extracted using machine learning and computer vision techniques for further analysis and novel studies.
Plankton imaging systems supported by automated classification and analysis have improved ecologists' ability to observe aquatic ecosystems. Today, we are on the cusp of reliably tracking plankton populations with a suite of lab-based and in situ tools, collecting imaging data at unprecedentedly fine spatial and temporal scales. But these data have potential well beyond examining the abundances of different taxa; the individual images themselves contain a wealth of information on functional traits. Here, we outline traits that could be measured from image data, suggest machine learning and computer vision approaches to extract functional trait information from the images, and discuss promising avenues for novel studies. The approaches we discuss are data agnostic and are broadly applicable to imagery of other aquatic or terrestrial organisms.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据