CCPortal
DOI10.1029/2018GB005992
A Machine Learning (kNN) Approach to Predicting Global Seafloor Total Organic Carbon
Lee T.R.; Wood W.T.; Phrampus B.J.
发表日期2019
ISSN0886-6236
EISSN1944-9224
起始页码37
结束页码46
卷号33期号:1
英文摘要Seafloor properties, including total organic carbon (TOC), are sparsely measured on a global scale, and interpolation (prediction) techniques are often used as a proxy for observation. Previous geospatial interpolations of seafloor TOC exhibit gaps where little to no observed data exists. In contrast, recent machine learning techniques, relying on geophysical and geochemical properties (e.g., seafloor biomass, porosity, and distance from coast), show promise in making comprehensive, statistically optimal predictions. Here we apply a nonparametric (i.e., data-driven) machine learning algorithm, specifically k-nearest neighbors (kNN), to estimate the global distribution of seafloor TOC. Our results include predictor (feature) selection specifically designed to mitigate bias and produce a statistically optimal estimation of seafloor TOC, with uncertainty, at 5 × 5-arc minute resolution. Analysis of parameter space sample density provides a guide for future sampling. One use for this prediction is to constrain a global inventory, indicating that just the upper 5 cm of the seafloor contains about 87 ± 43 gigatons of carbon (Gt C) in organic form. ©2019. This article is a US Government work and is in the public domain in the USA.
英文关键词global prediction; interpolation techniques; machine learning; seafloor properties; total organic carbon
语种英语
scopus关键词global perspective; interpolation; machine learning; nearest neighbor analysis; prediction; seafloor; total organic carbon
来源期刊Global Biogeochemical Cycles
文献类型期刊论文
条目标识符http://gcip.llas.ac.cn/handle/2XKMVOVA/129762
作者单位U.S. Naval Research Laboratory, John C. Stennis Space Center, Hancock County, MS, United States; ASEE Postdoctoral Program, U.S. Naval Research Laboratory, John C. Stennis Space Center, Hancock County, MS, United States
推荐引用方式
GB/T 7714
Lee T.R.,Wood W.T.,Phrampus B.J.. A Machine Learning (kNN) Approach to Predicting Global Seafloor Total Organic Carbon[J],2019,33(1).
APA Lee T.R.,Wood W.T.,&Phrampus B.J..(2019).A Machine Learning (kNN) Approach to Predicting Global Seafloor Total Organic Carbon.Global Biogeochemical Cycles,33(1).
MLA Lee T.R.,et al."A Machine Learning (kNN) Approach to Predicting Global Seafloor Total Organic Carbon".Global Biogeochemical Cycles 33.1(2019).
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Lee T.R.]的文章
[Wood W.T.]的文章
[Phrampus B.J.]的文章
百度学术
百度学术中相似的文章
[Lee T.R.]的文章
[Wood W.T.]的文章
[Phrampus B.J.]的文章
必应学术
必应学术中相似的文章
[Lee T.R.]的文章
[Wood W.T.]的文章
[Phrampus B.J.]的文章
相关权益政策
暂无数据
收藏/分享

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。