globalchange  > 气候变化与战略
DOI: 10.1111/gcb.14845
论文题名:
Gap-filling approaches for eddy covariance methane fluxes: A comparison of three machine learning algorithms and a traditional method with principal component analysis
作者: Kim Y.; Johnson M.S.; Knox S.H.; Black T.A.; Dalmagro H.J.; Kang M.; Kim J.; Baldocchi D.
刊名: Global Change Biology
ISSN: 13541013
出版年: 2020
卷: 26, 期:3
语种: 英语
英文关键词: artificial neural network ; comparison of gap-filling techniques ; eddy covariance ; machine learning ; marginal distribution sampling ; methane flux ; random forest ; support vector machine
Scopus关键词: algorithm ; artificial neural network ; carbon dioxide ; comparative study ; eddy covariance ; energy flux ; machine learning ; methane ; numerical model ; principal component analysis ; support vector machine
英文摘要: Methane flux (FCH4) measurements using the eddy covariance technique have increased over the past decade. FCH4 measurements commonly include data gaps, as is the case with CO2 and energy fluxes. However, gap-filling FCH4 data are more challenging than other fluxes due to its unique characteristics including multidriver dependency, variabilities across multiple timescales, nonstationarity, spatial heterogeneity of flux footprints, and lagged influence of biophysical drivers. Some researchers have applied a marginal distribution sampling (MDS) algorithm, a standard gap-filling method for other fluxes, to FCH4 datasets, and others have applied artificial neural networks (ANN) to resolve the challenging characteristics of FCH4. However, there is still no consensus regarding FCH4 gap-filling methods due to limited comparative research. We are not aware of the applications of machine learning (ML) algorithms beyond ANN to FCH4 datasets. Here, we compare the performance of MDS and three ML algorithms (ANN, random forest [RF], and support vector machine [SVM]) using multiple combinations of ancillary variables. In addition, we applied principal component analysis (PCA) as an input to the algorithms to address multidriver dependency of FCH4 and reduce the internal complexity of the algorithmic structures. We applied this approach to five benchmark FCH4 datasets from both natural and managed systems located in temperate and tropical wetlands and rice paddies. Results indicate that PCA improved the performance of MDS compared to traditional inputs. ML algorithms performed better when using all available biophysical variables compared to using PCA-derived inputs. Overall, RF was found to outperform other techniques for all sites. We found gap-filling uncertainty is much larger than measurement uncertainty in accumulated CH4 budget. Therefore, the approach used for FCH4 gap filling can have important implications for characterizing annual ecosystem-scale methane budgets, the accuracy of which is important for evaluating natural and managed systems and their interactions with global change processes. © 2019 John Wiley & Sons Ltd
Citation statistics:
资源类型: 期刊论文
标识符: http://119.78.100.158/handle/2HF3EXSE/159059
Appears in Collections:气候变化与战略

Files in This Item:

There are no files associated with this item.


作者单位: Institute for Resources Environment and Sustainability, University of British Columbia, Vancouver, BC, Canada; Department of Earth, Ocean and Atmospheric Sciences, University of British Columbia, Vancouver, BC, Canada; Department of Geography, University of British Columbia, Vancouver, BC, Canada; Faculty of Land and Food Systems, University of British Columbia, Vancouver, BC, Canada; Environmental Sciences Graduate Program, University of Cuiabá, Cuiabá, Brazil; National Center for AgroMeteorology, Seoul, South Korea; Department of Landscape Architecture & Rural Systems Engineering, Seoul National University, Seoul, South Korea; Interdisciplinary Program in Agricultural & Forest Meteorology, Seoul National University, Seoul, South Korea; Department of Environmental Science, Policy and Management, University of California, Berkeley, CA, United States

Recommended Citation:
Kim Y.,Johnson M.S.,Knox S.H.,et al. Gap-filling approaches for eddy covariance methane fluxes: A comparison of three machine learning algorithms and a traditional method with principal component analysis[J]. Global Change Biology,2020-01-01,26(3)
Service
Recommend this item
Sava as my favorate item
Show this item's statistics
Export Endnote File
Google Scholar
Similar articles in Google Scholar
[Kim Y.]'s Articles
[Johnson M.S.]'s Articles
[Knox S.H.]'s Articles
百度学术
Similar articles in Baidu Scholar
[Kim Y.]'s Articles
[Johnson M.S.]'s Articles
[Knox S.H.]'s Articles
CSDL cross search
Similar articles in CSDL Cross Search
[Kim Y.]‘s Articles
[Johnson M.S.]‘s Articles
[Knox S.H.]‘s Articles
Related Copyright Policies
Null
收藏/分享
所有评论 (0)
暂无评论
 

Items in IR are protected by copyright, with all rights reserved, unless otherwise indicated.