Research article - Peer-reviewed, 2021
Show more authors
Gap-filling eddy covariance methane fluxes: Comparison of machine learning model predictions and uncertainties at FLUXNET-CH4 wetlands
Irvin, Jeremy; Zhou, Sharon; McNicol, Gavin; Lu, Fred; Liu, Vincent; Fluet-Chouinard, Etienne; Ouyang, Zutao; Knox, Sara Helen; Lucas-Moffat, Antje; Trotta, Carlo; Papale, Dario; Vitale, Domenico; Mammarella, Ivan; Alekseychik, Pavel; Aurela, Mika; Avati, Anand; Baldocchi, Dennis; Bansal, Sheel; Bohrer, Gil; Campbell, David, I;Show more authors
Abstract
Time series of wetland methane fluxes measured by eddy covariance require gap-filling to estimate daily, seasonal, and annual emissions. Gap-filling methane fluxes is challenging because of high variability and complex responses to multiple drivers. To date, there is no widely established gap-filling standard for wetland methane fluxes, with regards both to the best model algorithms and predictors. This study synthesizes results of different gap-filling methods systematically applied at 17 wetland sites spanning boreal to tropical regions and including all major wetland classes and two rice paddies. Procedures are proposed for: 1) creating realistic artificial gap scenarios, 2) training and evaluating gap-filling models without overstating performance, and 3) predicting halfhourly methane fluxes and annual emissions with realistic uncertainty estimates. Performance is compared between a conventional method (marginal distribution sampling) and four machine learning algorithms. The conventional method achieved similar median performance as the machine learning models but was worse than the best machine learning models and relatively insensitive to predictor choices. Of the machine learning models, decision tree algorithms performed the best in cross-validation experiments, even with a baseline predictor set, and artificial neural networks showed comparable performance when using all predictors. Soil temperature was frequently the most important predictor whilst water table depth was important at sites with substantial water table fluctuations, highlighting the value of data on wetland soil conditions. Raw gap-filling uncertainties from the machine learning models were underestimated and we propose a method to calibrate uncertainties to observations. The python code for model development, evaluation, and uncertainty estimation is publicly available. This study outlines a modular and robust machine learning workflow and makes recommendations for, and evaluates an improved baseline of, methane gap-filling models that can be implemented in multi-site syntheses or standardized products from regional and global flux networks (e.g., FLUXNET).Keywords
Machine learning; time series; imputation; gap-filling; methane; flux; wetlandsPublished in
Agricultural and Forest Meteorology2021, volume: 308, article number: 108528
Publisher: ELSEVIER
Authors' information
Irvin, Jeremy
Stanford University
Zhou, Sharon
Stanford University
McNicol, Gavin
University of Illinois Chicago Hospital
Lu, Fred
Stanford University
Liu, Vincent
Stanford University
Fluet-Chouinard, Etienne
Stanford University
Ouyang, Zutao
Stanford University
Knox, Sara Helen
University of British Columbia
Lucas-Moffat, Antje
Ctr Agrometeorol Res
Trotta, Carlo
Centro Euro-Mediterraneo sui Cambiamenti Climatici (CMCC)
Papale, Dario
Centro Euro-Mediterraneo sui Cambiamenti Climatici (CMCC)
Vitale, Domenico
Centro Euro-Mediterraneo sui Cambiamenti Climatici (CMCC)
Mammarella, Ivan
University of Helsinki
Alekseychik, Pavel
Natural Resources Institute Finland (Luke)
Aurela, Mika
Finnish Meteorological Institute
Avati, Anand
Stanford University
Baldocchi, Dennis
University of California Berkeley
Bansal, Sheel
United States Geological Survey
Bohrer, Gil
Ohio State University
Campbell, David
University of Waikato
UKÄ Subject classification
Oceanography, Hydrology, Water Resources
Physical Geography
Publication Identifiers
DOI: https://doi.org/10.1016/j.agrformet.2021.108528
URI (permanent link to this page)
https://res.slu.se/id/publ/113682