Using machine learning to achieve simultaneous, georeferenced surveys of fish and benthic communities on shallow coral reefs

Using machine learning to achieve simultaneous, georeferenced surveys of fish and benthic communities on shallow coral reefs
复制标题

利用机器学习对浅海珊瑚礁上的鱼类和底栖群落进行同步地理参考调查

DOI:
10.1002/lom3.10557
复制
发表时间:
2023
期刊:
Limnology and Oceanography: Methods
影响因子:
--
通讯作者:
Rassweiler, Andrew
Rassweiler, Andrew
中科院分区:
--
文献类型:
--
作者:
Miller, Scott D.;Dubel, Alexandra K.;Adam, Thomas C.;Cook, Dana T.;Holbrook, Sally J.;Schmitt, Russell J.;Rassweiler, Andrew

文献摘要

参考文献

相似文献

测量沿海系统以估计鱼类和底栖生物的分布和丰度是劳动密集型的,通常导致空间有限的数据难以扩展到整个珊瑚礁或岛屿。我们开发了一种方法,利用机器学习平台CoralNet的自动化,以高效和成本效益的方式允许单个观察者同时生成关于浅水沿海环境中大面积鱼类和底栖生物类群丰度的地理参考数据。简而言之,一名研究人员在水面上浮潜并拖着一个配备手持GPS和向下的GoPro的浮子进行鱼类调查,被动地拍摄每米底栖生物约10张照片。照片和调查后来进行了地理参考,照片由CoralNet自动注释。我们发现,这种方法提供了类似的生物量和密度值为常见的鱼类作为传统的水肺为基础的鱼类计数固定样带,具有覆盖面积更大的优势。我们的CoralNet验证确定,虽然CoralNet自动注释的照片在单个图像水平上不如人工注释的照片准确,但自动方法在一分钟调查水平上提供了可比或更好的底栖基质覆盖百分比估计(约50平方米的珊瑚礁),因为可以自动标注的照片量,提供了更大的空间覆盖范围的网站。该方法可用于各种浅层系统,当需要空间明确的数据或大空间范围的调查时,该方法特别有利。
Surveying coastal systems to estimate distribution and abundance of fish and benthic organisms is labor‐intensive, often resulting in spatially limited data that are difficult to scale up to an entire reef or island. We developed a method that leverages the automation of a machine learning platform, CoralNet, to efficiently and cost‐effectively allow a single observer to simultaneously generate georeferenced data on abundances of fish and benthic taxa over large areas in shallow coastal environments. Briefly, a researcher conducts a fish survey while snorkeling on the surface and towing a float equipped with a handheld GPS and a downward‐facing GoPro, passively taking ~ 10 photographs per meter of benthos. Photographs and surveys are later georeferenced and photographs are automatically annotated by CoralNet. We found that this method provides similar biomass and density values for common fishes as traditional scuba‐based fish counts on fixed transects, with the advantage of covering a larger area. Our CoralNet validation determined that while photographs automatically annotated by CoralNet are less accurate than photographs annotated by humans at the level of a single image, the automated approach provides comparable or better estimations of the percent cover of the benthic substrates at the level of a minute of survey (~ 50 m2of reef) due to the volume of photographs that can be automatically annotated, providing greater spatial coverage of the site. This method can be used in a variety of shallow systems and is particularly advantageous when spatially explicit data or surveys of large spatial extents are necessary.
DOI: 10.3390/rs12183036
发表时间: 2020-09
期刊: Remote. Sens.
影响因子: --
作者:
E. Nocerino;F. Menna;A. Gruen;M. Troyer;A. Capra;C. Castagnetti;P. Rossi;A. Brooks;R. Schmitt;S. Holbrook
通讯作者: E. Nocerino;F. Menna;A. Gruen;M. Troyer;A. Capra;C. Castagnetti;P. Rossi;A. Brooks;R. Schmitt;S. Holbrook
DOI: 10.1002/ece3.3041
发表时间: 2017-07
影响因子: 2.6
作者:
Griffin KJ;Hedge LH;González-Rivero M;Hoegh-Guldberg OI;Johnston EL
通讯作者: Johnston EL
评估热带珊瑚礁鱼类的范围变化:带样线和漫游水下目视普查方法的比较
DOI: --
发表时间: 2014
期刊:
影响因子: --
作者:
H. Beck;D. Feary;W. Figueira;D. Booth
通讯作者: D. Booth
一种拖曳潜水员调查方法,用于大型珊瑚礁鱼类的中尺度渔业独立评估
DOI: --
发表时间: 2011
期刊:
影响因子: --
作者:
Benjamin L. Richards;I. Williams;M. Nadon;B. Zgliczynski
通讯作者: B. Zgliczynski
不要把婴儿和洗澡水一起倒掉:重新欣赏人、机器和风景图像之间的动态关系
DOI: --
发表时间: 2020
期刊: Landscape Ecology
影响因子: 5.2
作者:
Raechel A. Portelli
通讯作者: Raechel A. Portelli