2010
DOI: 10.1371/journal.pone.0015323
|View full text |Cite
|
Sign up to set email alerts
|

Global Patterns and Predictions of Seafloor Biomass Using Random Forests

Abstract: A comprehensive seafloor biomass and abundance database has been constructed from 24 oceanographic institutions worldwide within the Census of Marine Life (CoML) field projects. The machine-learning algorithm, Random Forests, was employed to model and predict seafloor standing stocks from surface primary production, water-column integrated and export particulate organic matter (POM), seafloor relief, and bottom water properties. The predictive models explain 63% to 88% of stock variance among the major size gr… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

24
260
3

Year Published

2013
2013
2023
2023

Publication Types

Select...
9

Relationship

0
9

Authors

Journals

citations
Cited by 305 publications
(287 citation statements)
references
References 73 publications
24
260
3
Order By: Relevance
“…A more rapid decrease in the macrobenthos standing stock, and generally in the big-ger organisms, is a universal phenomenon that involves complex changes in the relative importance of each of the different size groups Etter 1998, Rex et al 2006). Usually this restriction in size arises from low amounts of food (Wei et al 2010). In the present study, the significant increase in prokaryote biomass of the total biomass suggests two things: (i) a greater ability of prokaryotes to exploit the organic carbon in the sediments, as compared to the other two benthic classes; and consequently, (ii) a partial channelling of the carbon to the higher trophic levels through the prokaryote component (Danovaro et al 2000).…”
Section: Contributions Of Different Benthic Size Classes To Total Biosupporting
confidence: 45%
“…A more rapid decrease in the macrobenthos standing stock, and generally in the big-ger organisms, is a universal phenomenon that involves complex changes in the relative importance of each of the different size groups Etter 1998, Rex et al 2006). Usually this restriction in size arises from low amounts of food (Wei et al 2010). In the present study, the significant increase in prokaryote biomass of the total biomass suggests two things: (i) a greater ability of prokaryotes to exploit the organic carbon in the sediments, as compared to the other two benthic classes; and consequently, (ii) a partial channelling of the carbon to the higher trophic levels through the prokaryote component (Danovaro et al 2000).…”
Section: Contributions Of Different Benthic Size Classes To Total Biosupporting
confidence: 45%
“…The small size of trench habitats relative to the surrounding abyssal plains, as well as their geographical isolation, may limit both the size of species pools and connectivity among trenches, and may account for the limited diversity observed particularly in the deepest parts of trenches (Jamieson 2015). Analyses of global datasets show that metazoan meiofauna biomass exceeds that of macrofauna below depths of 4000 m (Wei et al 2010) and, not surprisingly, meiofauna are by far the most abundant component of sediment communities in trenches. Deep-sea kinorhynchs are largely unknown compared to the 250 species recorded from relatively shallow waters.…”
Section: Metazoan Meiofaunamentioning
confidence: 99%
“…Also, although this ordering of importance of the different types of factors is quite coherent across the RF approach outcomes, the question remains as to whether it is "true". Claims to this effect are supported by noting that factors that RF-type methods have identified as most important for classification have been found to coincide with ecological expectations in the literature (Cutler et al 2007;Wei et al 2010;Ellis et al 2012b). …”
Section: Random Forest Analysismentioning
confidence: 88%
“…The stepwise method combines forward selection and backward elimination procedures (Venables and Ripley 2002;James et al 2013). It proceeds by first setting up an initial model incorporating a subset of the candidate independent variables.…”
Section: Stepwise Multiple Linear Regression (Step)mentioning
confidence: 99%