Gap-filling eddy covariance methane fluxes : Comparison of machine learning model predictions and uncertainties at FLUXNET-CH4 wetlands

Show full item record



Permalink

http://hdl.handle.net/10138/346041

Citation

Irvin , J , Zhou , S , McNicol , G , Lu , F , Liu , V , Fluet-Chouinard , E , Ouyang , Z , Knox , S H , Lucas-Moffat , A , Trotta , C , Papale , D , Vitale , D , Mammarella , I , Alekseychik , P , Aurela , M , Avati , A , Baldocchi , D , Bansal , S , Bohrer , G , Campbell , D , Chen , J , Chu , H , Dalmagro , H J , Delwiche , K B , Desai , A R , Euskirchen , E , Feron , S , Goeckede , M , Heimann , M , Helbig , M , Helfter , C , Hemes , K S , Hirano , T , Iwata , H , Jurasinski , G , Kalhori , A , Kondrich , A , Lai , D Y F , Lohila , A , Malhotra , A , Merbold , L , Mitra , B , Ng , A , Nilsson , M B , Noormets , A , Peichl , M , Rey-Sanchez , A C , Richardson , A D , Runkle , B R K , Schafer , K V R , Sonnentag , O , Stuart-Haentjens , E , Sturtevant , C , Ueyama , M , Valach , A C , Vargas , R , Vourlitis , G L , Ward , E J , Wong , G X , Zona , D , Alberto , M C R , Billesbach , D P , Celis , G , Dolman , H , Friborg , T , Fuchs , K , Gogo , S , Gondwe , M J , Goodrich , J P , Gottschalk , P , Hortnagl , L , Jacotot , A , Koebsch , F , Kasak , K , Maier , R , Morin , T H , Nemitz , E , Oechel , W C , Oikawa , P Y , Ono , K , Sachs , T , Sakabe , A , Schuur , E A , Shortt , R , Sullivan , R C , Szutu , D J , Tuittila , E-S , Varlagin , A , Verfaillie , J G , Wille , C , Windham-Myers , L , Poulter , B & Jackson , R B 2021 , ' Gap-filling eddy covariance methane fluxes : Comparison of machine learning model predictions and uncertainties at FLUXNET-CH4 wetlands ' , Agricultural and Forest Meteorology , vol. 308-309 , 108528 . https://doi.org/10.1016/j.agrformet.2021.108528

Title: Gap-filling eddy covariance methane fluxes : Comparison of machine learning model predictions and uncertainties at FLUXNET-CH4 wetlands
Author: 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; Chen, Jiquan; Chu, Housen; Dalmagro, Higo J.; Delwiche, Kyle B.; Desai, Ankur R.; Euskirchen, Eugenie; Feron, Sarah; Goeckede, Mathias; Heimann, Martin; Helbig, Manuel; Helfter, Carole; Hemes, Kyle S.; Hirano, Takashi; Iwata, Hiroki; Jurasinski, Gerald; Kalhori, Aram; Kondrich, Andrew; Lai, Derrick Y. F.; Lohila, Annalea; Malhotra, Avni; Merbold, Lutz; Mitra, Bhaskar; Ng, Andrew; Nilsson, Mats B.; Noormets, Asko; Peichl, Matthias; Rey-Sanchez, A. Camilo; Richardson, Andrew D.; Runkle, Benjamin R. K.; Schafer, Karina V. R.; Sonnentag, Oliver; Stuart-Haentjens, Ellen; Sturtevant, Cove; Ueyama, Masahito; Valach, Alex C.; Vargas, Rodrigo; Vourlitis, George L.; Ward, Eric J.; Wong, Guan Xhuan; Zona, Donatella; Alberto, Ma Carmelita R.; Billesbach, David P.; Celis, Gerardo; Dolman, Han; Friborg, Thomas; Fuchs, Kathrin; Gogo, Sebastien; Gondwe, Mangaliso J.; Goodrich, Jordan P.; Gottschalk, Pia; Hortnagl, Lukas; Jacotot, Adrien; Koebsch, Franziska; Kasak, Kuno; Maier, Regine; Morin, Timothy H.; Nemitz, Eiko; Oechel, Walter C.; Oikawa, Patricia Y.; Ono, Keisuke; Sachs, Torsten; Sakabe, Ayaka; Schuur, Edward A.; Shortt, Robert; Sullivan, Ryan C.; Szutu, Daphne J.; Tuittila, Eeva-Stiina; Varlagin, Andrej; Verfaillie, Joeseph G.; Wille, Christian; Windham-Myers, Lisamarie; Poulter, Benjamin; Jackson, Robert B.
Contributor organization: Institute for Atmospheric and Earth System Research (INAR)
Micrometeorology and biogeochemical cycles
Date: 2021-10-15
Language: eng
Number of pages: 22
Belongs to series: Agricultural and Forest Meteorology
ISSN: 0168-1923
DOI: https://doi.org/10.1016/j.agrformet.2021.108528
URI: http://hdl.handle.net/10138/346041
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).
Subject: 114 Physical sciences
Peer reviewed: Yes
Rights: cc_by_nc_nd
Usage restriction: openAccess
Self-archived version: acceptedVersion


Files in this item

Total number of downloads: Loading...

Files Size Format View
Irvin_etal_AFM_2021.pdf 7.208Mb PDF View/Open

This item appears in the following Collection(s)

Show full item record