Gap‐filling approaches for eddy covariance methane fluxes: A comparison of three machine learning algorithms and a traditional method with principal component analysis
The DOI matches its Crossref record; 66 of the 66 references it cites were found in a registry or an index.
Abstract
Methane flux (FCH 4) measurements using the eddy covariance technique have increased over the past decade. FCH 4 measurements commonly include data gaps, as is the case with CO 2 and energy fluxes. However, gap‐filling FCH 4 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 FCH 4 datasets, and others have applied artificial neural networks (ANN) to resolve the challenging characteristics of FCH 4. However, there is still no consensus regarding FCH 4 gap‐filling methods due to limited comparative research. We are not aware of the applications of machine learning (ML) algorithms beyond ANN to FCH 4 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 FCH 4 and reduce the internal complexity of the algorithmic structures. We applied this approach to five benchmark FCH 4 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 CH 4 budget. Therefore, the approach used for FCH 4 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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
R: A Language and Environment for Statistical Computing
R Core Team (2025) · doi:10.32614/r.manuals · Cited by 352,181
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · cited 1×
“Random forest algorithm introduced by Breiman (2001) is an ensem‐ ble method of regression tree.”
MethodCortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421
Classification and Regression by randomForest
Liaw, A. I., & Wiener, M. C. (2007) · Cited by 18,594
Summarizing multiple aspects of model performance in a single diagram
Taylor, K. E. (2001) · Journal of Geophysical Research: Atmospheres · doi:10.1029/2000jd900719 · Cited by 8,477 · cited 1×
“We used Taylor diagrams to evaluate the performance of gap‐fill‐ ing approaches (Taylor, 2001) which can concisely summarize the root mean square error (RMSE), the correlation coefficient ( R ), and the ratio of the standard deviation ( SD ) of a model to that of the observation.”
MethodDeep learning and process understanding for data-driven Earth system science
Reichstein, M., Camps-Valls, G., Stevens, B., Jung, M., Denzler, J., Carvalhais, N., & Prabhat (2019) · Nature · doi:10.1038/s41586-019-0912-1 · Cited by 5,673 · cited 1×
“It is unclear that current gap‐filling ap‐ proaches can capture such a lagged effect (e.g., Reichstein et al., 2019).”
BackgroundBaldocchi, D., Falge, E. M., Gu, L., Olson, R., Hollinger, D. Y., Running, S. W., Anthoni, P. M., Bernhofer, C., Davis, K. J., Evans, R., et al. (2001) · Bulletin of the American Meteorological Society · doi:10.1175/1520-0477(2001)082<2415:fantts>2.3.co;2 · Cited by 3,825
Self-citationReichstein, M., Falge, E., Baldocchi, D., Papale, D., Aubinet, M., Berbigier, P., Bernhofer, C., Buchmann, N., Gilmanov, T., Granier, A., et al. (2005) · Global Change Biology · doi:10.1111/j.1365-2486.2005.001002.x · Cited by 3,810 · cited 2×
“The MDS algorithm applies a look‐up table method first, and then applies the mean diurnal curve method if necessary (Reichstein et al., 2005; Wutzler et al., 2018).”
MethodSelf-citationAnthropogenic and Natural Radiative Forcing
(2014) · Climate Change 2013 – The Physical Science Basis · doi:10.1017/cbo9781107415324.018 · Cited by 3,683
openair — An R package for air quality data analysis
Carslaw, D. C., & Ropkins, K. (2012) · Environmental Modelling & Software · doi:10.1016/j.envsoft.2011.09.008 · Cited by 2,002 · cited 1×
“The Taylor diagrams were generated using the “openair” R package (Carslaw & Ropkins, 2012).”
Method
Metadata
- Authors
- Kim, Y., Johnson, M. S., Knox, S. H., Black, T. A., Dalmagro, H. J., Kang, M., Kim, J., & Baldocchi, D.
- Venue
- Global Change Biology
- Publisher
- Wiley
- Published
- 2019-10-21
- Volume
- 26
- Issue
- 3
- Pages
- 1499-1518
- ISSN
- 1354-1013 (ISSN-L)
- 1365-2486
- OpenAlex
- W2975926778
- Cited by
- 203
- References
- 66
- FWCI
- 9.63
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Gap‐filling approaches for eddy covariance methane fluxes: A comparison of three machine learning algorithms and a traditional method with principal component analysis. https://app.cochat.ai/papers/10.1111/gcb.14845
- The paper
- Kim, Y., Johnson, M. S., Knox, S. H., Black, T. A., Dalmagro, H. J., Kang, M., Kim, J., & Baldocchi, D. (2020). Gap‐filling approaches for eddy covariance methane fluxes: A comparison of three machine learning algorithms and a traditional method with principal component analysis. Global Change Biology. https://doi.org/10.1111/gcb.14845
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.