Articles | Volume 10, issue 1
https://doi.org/10.5194/gi-10-123-2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gi-10-123-2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
28 Jun 2021
Research article |
| 28 Jun 2021
| 28 Jun 2021
A comparison of gap-filling algorithms for eddy covariance fluxes and their drivers
School of Agriculture and Environment, The University of Western
Australia, 35 Stirling Hwy, Crawley, Perth, WA, 6009, Australia
Jason Beringer
School of Agriculture and Environment, The University of Western
Australia, 35 Stirling Hwy, Crawley, Perth, WA, 6009, Australia
Matthias Leopold
School of Agriculture and Environment, The University of Western
Australia, 35 Stirling Hwy, Crawley, Perth, WA, 6009, Australia
Ian McHugh
School of Ecosystem and Forest Sciences, The University of
Melbourne, Richmond, VIC, 3121, Australia
James Cleverly
School of Life Sciences University of Technology Sydney Broadway
Sydney, NSW, 2007, Australia
Peter Isaac
OzFlux Central Node, TERN Ecosystem Processes, Melbourne, VIC, 3159, Australia
Azizallah Izady
Water Research Center, Sultan Qaboos University, Muscat, Oman
Viewed
Total article views: 3,814 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 07 Sep 2020)
| HTML | XML | Total | Supplement | BibTeX | EndNote | |
|---|---|---|---|---|---|---|
| 2,912 | 831 | 71 | 3,814 | 143 | 66 | 78 |
- HTML: 2,912
- PDF: 831
- XML: 71
- Total: 3,814
- Supplement: 143
- BibTeX: 66
- EndNote: 78
Total article views: 2,733 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 28 Jun 2021)
| HTML | XML | Total | Supplement | BibTeX | EndNote | |
|---|---|---|---|---|---|---|
| 2,160 | 507 | 66 | 2,733 | 143 | 55 | 67 |
- HTML: 2,160
- PDF: 507
- XML: 66
- Total: 2,733
- Supplement: 143
- BibTeX: 55
- EndNote: 67
Total article views: 1,081 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 07 Sep 2020)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 752 | 324 | 5 | 1,081 | 11 | 11 |
- HTML: 752
- PDF: 324
- XML: 5
- Total: 1,081
- BibTeX: 11
- EndNote: 11
Viewed (geographical distribution)
Total article views: 3,814 (including HTML, PDF, and XML)
Thereof 3,354 with geography defined
and 460 with unknown origin.
Total article views: 2,733 (including HTML, PDF, and XML)
Thereof 2,486 with geography defined
and 247 with unknown origin.
Total article views: 1,081 (including HTML, PDF, and XML)
Thereof 868 with geography defined
and 213 with unknown origin.
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
Cited
23 citations as recorded by crossref.
- Spatiotemporal lagging of predictors improves machine learning estimates of atmosphere–forest CO2 exchange M. Kämäräinen et al. 10.5194/bg-20-897-2023
- Full phenology cycle carbon flux dynamics and driving mechanism of Moso bamboo forest C. Xu et al. 10.3389/fpls.2024.1359265
- A widely-used eddy covariance gap-filling method creates systematic bias in carbon balance estimates H. Vekuri et al. 10.1038/s41598-023-28827-2
- Multiple gap-filling for eddy covariance datasets A. Lucas-Moffat et al. 10.1016/j.agrformet.2022.109114
- A physical full-factorial scheme for gap-filling of eddy covariance measurements of daytime evapotranspiration Y. Jiang et al. 10.1016/j.agrformet.2022.109087
- Atmospheric water demand constrains net ecosystem production in subtropical mangrove forests R. Gou et al. 10.1016/j.jhydrol.2024.130651
- Estimating the methane flux of the Dajiuhu subalpine peatland using machine learning algorithms and the maximal information coefficient technique X. Li et al. 10.1016/j.scitotenv.2024.170241
- Artificial intelligence and Eddy covariance: A review A. Lucarini et al. 10.1016/j.scitotenv.2024.175406
- Providing a comprehensive understanding of missing data imputation processes in evapotranspiration-related research: a systematic literature review E. Başakın et al. 10.1080/02626667.2023.2249456
- Testing the suitability of Marginal Distribution Sampling as a gap‐filling method using some meteorological data from seven sites in West Africa D. Koukoui et al. 10.1002/met.2152
- Spatial and temporal variation of three Eddy-Covariance flux footprints in a Tropical Dry Forest M. Abdaki et al. 10.1016/j.agrformet.2023.109863
- Predicting the fundamental fluxes of an eddy-covariance station using machine learning methods D. Garcia-Rodriguez et al. 10.1016/j.ecoinf.2024.102638
- Multiple Gap-Filling for Eddy Covariance Datasets A. Lucas-Moffat et al. 10.2139/ssrn.4065277
- Air–sea interactions in stable atmospheric conditions: lessons from the desert semi-enclosed Gulf of Eilat (Aqaba) S. Abir et al. 10.5194/acp-24-6177-2024
- Gap-filling carbon dioxide, water, energy, and methane fluxes in challenging ecosystems: Comparing between methods, drivers, and gap-lengths S. Zhu et al. 10.1016/j.agrformet.2023.109365
- Trading a little water for substantial carbon gains during the first years of a Eucalyptus globulus plantation M. Silva et al. 10.1016/j.agrformet.2022.108910
- A ground-independent method for obtaining complete time series of in situ evapotranspiration observations W. Li et al. 10.1016/j.jhydrol.2024.130888
- Temporally dynamic carbon dioxide and methane emission factors for rewetted peatlands A. Kalhori et al. 10.1038/s43247-024-01226-9
- Commercial forest carbon protocol over-credit bias delimited by zero-threshold carbon accounting B. Marino & N. Bautista 10.1016/j.tfp.2021.100171
- Drainage effects on carbon budgets of degraded peatlands in the north of the Netherlands T. Nijman et al. 10.1016/j.scitotenv.2024.172882
- A gap filling method for daily evapotranspiration of global flux data sets based on deep learning L. Qian et al. 10.1016/j.jhydrol.2024.131787
- Eddy Covariance CO2 Flux Gap Filling for Long Data Gaps: A Novel Framework Based on Machine Learning and Time Series Decomposition D. Gao et al. 10.3390/rs15102695
- Technical note: Uncertainties in eddy covariance CO<sub>2</sub> fluxes in a semiarid sagebrush ecosystem caused by gap-filling approaches J. Yao et al. 10.5194/acp-21-15589-2021
23 citations as recorded by crossref.
- Spatiotemporal lagging of predictors improves machine learning estimates of atmosphere–forest CO2 exchange M. Kämäräinen et al. 10.5194/bg-20-897-2023
- Full phenology cycle carbon flux dynamics and driving mechanism of Moso bamboo forest C. Xu et al. 10.3389/fpls.2024.1359265
- A widely-used eddy covariance gap-filling method creates systematic bias in carbon balance estimates H. Vekuri et al. 10.1038/s41598-023-28827-2
- Multiple gap-filling for eddy covariance datasets A. Lucas-Moffat et al. 10.1016/j.agrformet.2022.109114
- A physical full-factorial scheme for gap-filling of eddy covariance measurements of daytime evapotranspiration Y. Jiang et al. 10.1016/j.agrformet.2022.109087
- Atmospheric water demand constrains net ecosystem production in subtropical mangrove forests R. Gou et al. 10.1016/j.jhydrol.2024.130651
- Estimating the methane flux of the Dajiuhu subalpine peatland using machine learning algorithms and the maximal information coefficient technique X. Li et al. 10.1016/j.scitotenv.2024.170241
- Artificial intelligence and Eddy covariance: A review A. Lucarini et al. 10.1016/j.scitotenv.2024.175406
- Providing a comprehensive understanding of missing data imputation processes in evapotranspiration-related research: a systematic literature review E. Başakın et al. 10.1080/02626667.2023.2249456
- Testing the suitability of Marginal Distribution Sampling as a gap‐filling method using some meteorological data from seven sites in West Africa D. Koukoui et al. 10.1002/met.2152
- Spatial and temporal variation of three Eddy-Covariance flux footprints in a Tropical Dry Forest M. Abdaki et al. 10.1016/j.agrformet.2023.109863
- Predicting the fundamental fluxes of an eddy-covariance station using machine learning methods D. Garcia-Rodriguez et al. 10.1016/j.ecoinf.2024.102638
- Multiple Gap-Filling for Eddy Covariance Datasets A. Lucas-Moffat et al. 10.2139/ssrn.4065277
- Air–sea interactions in stable atmospheric conditions: lessons from the desert semi-enclosed Gulf of Eilat (Aqaba) S. Abir et al. 10.5194/acp-24-6177-2024
- Gap-filling carbon dioxide, water, energy, and methane fluxes in challenging ecosystems: Comparing between methods, drivers, and gap-lengths S. Zhu et al. 10.1016/j.agrformet.2023.109365
- Trading a little water for substantial carbon gains during the first years of a Eucalyptus globulus plantation M. Silva et al. 10.1016/j.agrformet.2022.108910
- A ground-independent method for obtaining complete time series of in situ evapotranspiration observations W. Li et al. 10.1016/j.jhydrol.2024.130888
- Temporally dynamic carbon dioxide and methane emission factors for rewetted peatlands A. Kalhori et al. 10.1038/s43247-024-01226-9
- Commercial forest carbon protocol over-credit bias delimited by zero-threshold carbon accounting B. Marino & N. Bautista 10.1016/j.tfp.2021.100171
- Drainage effects on carbon budgets of degraded peatlands in the north of the Netherlands T. Nijman et al. 10.1016/j.scitotenv.2024.172882
- A gap filling method for daily evapotranspiration of global flux data sets based on deep learning L. Qian et al. 10.1016/j.jhydrol.2024.131787
- Eddy Covariance CO2 Flux Gap Filling for Long Data Gaps: A Novel Framework Based on Machine Learning and Time Series Decomposition D. Gao et al. 10.3390/rs15102695
- Technical note: Uncertainties in eddy covariance CO<sub>2</sub> fluxes in a semiarid sagebrush ecosystem caused by gap-filling approaches J. Yao et al. 10.5194/acp-21-15589-2021
Latest update: 20 Nov 2024
Short summary
We reviewed eight algorithms to estimate missing values of environmental drivers and three major fluxes in eddy covariance time series. Overall, machine-learning algorithms showed superiority over the rest. Among the top three models (feed-forward neural networks, eXtreme Gradient Boost, and random forest algorithms), the latter showed the most solid performance in different scenarios.
We reviewed eight algorithms to estimate missing values of environmental drivers and three major...
