Articles | Volume 22, issue 15
https://doi.org/10.5194/bg-22-3867-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/bg-22-3867-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
12 Aug 2025
Research article |
| 12 Aug 2025
| 12 Aug 2025
Groundwater–CO2 emissions relationship in Dutch peatlands derived by machine learning using airborne and ground-based eddy covariance data
Earth Systems and Global Change Group, Wageningen University, 6708 PB Wageningen, the Netherlands
Laurent V. Bataille
Earth Systems and Global Change Group, Wageningen University, 6708 PB Wageningen, the Netherlands
Bart Kruijt
Earth Systems and Global Change Group, Wageningen University, 6708 PB Wageningen, the Netherlands
Wietse Franssen
Earth Systems and Global Change Group, Wageningen University, 6708 PB Wageningen, the Netherlands
Wilma Jans
Earth Systems and Global Change Group, Wageningen University, 6708 PB Wageningen, the Netherlands
Jan Biermann
Earth Systems and Global Change Group, Wageningen University, 6708 PB Wageningen, the Netherlands
Anne Rietman
Earth Systems and Global Change Group, Wageningen University, 6708 PB Wageningen, the Netherlands
Alex J. V. Buzacott
Institute for Atmospheric and Earth System Research, University of Helsinki, 00014 Helsinki, Finland
Ype van der Velde
Faculty of Science, Earth and Climate, Vrije Universiteit Amsterdam, 1081 HV Amsterdam, the Netherlands
Ruben Boelens
HydroLogic, 3811 HN Amersfoort, the Netherlands
Earth Systems and Global Change Group, Wageningen University, 6708 PB Wageningen, the Netherlands
Related authors
No articles found.
Hong Zhao, Han Dolman, Jan Elbers, Wilma Jans, Bart Kruijt, Eddy Moors, Henk Snellen, Jordi Vila-Guerau de Arellano, Wouter Peters, Maarten Krol, Ronald Hutjes, and Michiel van der Molen
Earth Syst. Sci. Data Discuss., https://doi.org/10.5194/essd-2025-372, https://doi.org/10.5194/essd-2025-372, 2025
Preprint under review for ESSD
Short summary
Short summary
Under the Kyoto Protocol the carbon dioxide (CO2) balance for forest ecosystems was required to be measured. Consequently, CO2 flux measurements have been conducted in Loobos site in the Netherlands since 1996, becoming one of the 17 first FLUXNET sites globally. This paper provides a comprehensive overview of the instrumentation, data processing and the resulting data archive, enabling its further use in data analysis, model development and validation of satellite data retrievals.
Paul Waldmann, Max Eckl, Leon Knez, Klaus-Dirk Gottschaldt, Alina Fiehn, Christian Mallaun, Michal Galkowski, Christoph Kiemle, Ronald Hutjes, Thomas Röckmann, Huilin Chen, and Anke Roiger
EGUsphere, https://doi.org/10.5194/egusphere-2025-3297, https://doi.org/10.5194/egusphere-2025-3297, 2025
Short summary
Short summary
Nitrous oxide and methane emissions from agriculture need to be reduced, therefore emissions must be understood to effectively mitigate them. This is the first approach to measure those emissions aircraft-based, to assess their magnitude and drivers. We identified emission hotspots and temporal changes in agricultural emissions in the Netherlands. Our approach is applicable to further greenhouse gas emitters, therefore it builds a step towards more comprehensive emission quantification.
Asta Laasonen, Alexander Buzacott, Kukka-Maaria Kohonen, Erik Lundin, Alexander Meire, Mari Pihlatie, and Ivan Mammarella
EGUsphere, https://doi.org/10.5194/egusphere-2025-2094, https://doi.org/10.5194/egusphere-2025-2094, 2025
Short summary
Short summary
Carbon monoxide (CO) is an important indirect greenhouse gas, but its terrestrial sinks and sources are poorly understood. We present the first CO flux measurements using the eddy covariance method in an Arctic peatland. Our results show CO fluxes are dominated by two processes: radiation driven emissions and soil uptake. Dry peatland areas acted as CO sinks, while wetter areas were CO sources. Our findings suggest current global models may underestimate Arctic CO emissions.
Rutger Willem Vervoort, Floris van Ogtrop, Mina Tambrchi, Farzina Akter, Alexander Buzacott, Jason Lessels, James Moloney, Dipangkar Kundu, Feike Dijkstra, and Thomas Bishop
Earth Syst. Sci. Data Discuss., https://doi.org/10.5194/essd-2025-105, https://doi.org/10.5194/essd-2025-105, 2025
Revised manuscript under review for ESSD
Short summary
Short summary
A detailed water quality dataset for a 1000 km2 catchment in NSW, Australia is presented. The water quality data for surface and groundwater was collected over 14 years and contains more than 1000 records. Despite missing values and different sampling methods and groups, the data provides a consistent overview of the hydrogeochemistry of the catchment. This dataset is valuable for global modelling studies as well as better understanding of local dryland salinity and water quality processes.
Ralf C. H. Aben, Daniël van de Craats, Jim Boonman, Stijn H. Peeters, Bart Vriend, Coline C. F. Boonman, Ype van der Velde, Gilles Erkens, and Merit van den Berg
Biogeosciences, 21, 4099–4118, https://doi.org/10.5194/bg-21-4099-2024, https://doi.org/10.5194/bg-21-4099-2024, 2024
Short summary
Short summary
Drained peatlands cause high CO2 emissions. We assessed the effectiveness of subsurface water infiltration systems (WISs) in reducing CO2 emissions related to increases in water table depth (WTD) on 12 sites for up to 4 years. Results show WISs markedly reduced emissions by 2.1 t CO2-C ha-1 yr-1. The relationship between the amount of carbon above the WTD and CO2 emission was stronger than the relationship between WTD and emission. Long-term monitoring is crucial for accurate emission estimates.
Merit van den Berg, Thomas M. Gremmen, Renske J. E. Vroom, Jacobus van Huissteden, Jim Boonman, Corine J. A. van Huissteden, Ype van der Velde, Alfons J. P. Smolders, and Bas P. van de Riet
Biogeosciences, 21, 2669–2690, https://doi.org/10.5194/bg-21-2669-2024, https://doi.org/10.5194/bg-21-2669-2024, 2024
Short summary
Short summary
Drained peatlands emit 3 % of the global greenhouse gas emissions. Paludiculture is a way to reduce CO2 emissions while at the same time generating an income for landowners. The side effect is the potentially high methane emissions. We found very high methane emissions for broadleaf cattail compared with narrowleaf cattail and water fern. The rewetting was, however, effective to stop CO2 emissions for all species. The highest potential to reduce greenhouse gas emissions had narrowleaf cattail.
Tanya J. R. Lippmann, Ype van der Velde, Monique M. P. D. Heijmans, Han Dolman, Dimmie M. D. Hendriks, and Ko van Huissteden
Geosci. Model Dev., 16, 6773–6804, https://doi.org/10.5194/gmd-16-6773-2023, https://doi.org/10.5194/gmd-16-6773-2023, 2023
Short summary
Short summary
Vegetation is a critical component of carbon storage in peatlands but an often-overlooked concept in many peatland models. We developed a new model capable of simulating the response of vegetation to changing environments and management regimes. We evaluated the model against observed chamber data collected at two peatland sites. We found that daily air temperature, water level, harvest frequency and height, and vegetation composition drive methane and carbon dioxide emissions.
Alexa Marion Hinzman, Ylva Sjöberg, Steve W. Lyon, Wouter R. Berghuijs, and Ype van der Velde
EGUsphere, https://doi.org/10.5194/egusphere-2023-2391, https://doi.org/10.5194/egusphere-2023-2391, 2023
Preprint archived
Short summary
Short summary
An Arctic catchment with permafrost responds in a linear fashion: water in=water out. As permafrost thaws, 9 of 10 nested catchments become more non-linear over time. We find upstream catchments have stronger streamflow seasonality and exhibit the most nonlinear storage-discharge relationships. Downstream catchments have the greatest increases in non-linearity over time. These long-term shifts in the storage-discharge relationship are not typically seen in current hydrological models.
Ubolya Wanthanaporn, Iwan Supit, Bert van Hove, and Ronald W. A. Hutjes
Hydrol. Earth Syst. Sci. Discuss., https://doi.org/10.5194/hess-2023-56, https://doi.org/10.5194/hess-2023-56, 2023
Revised manuscript not accepted
Short summary
Short summary
We evaluated the potential use of SEAS5 seasonal forecasting for Mainland Southeast Asia. The temperature and precipitation skills are tested. We subsequently implemented a hydrological model VIC to produce seasonal streamflow forecasts. SEAS5 is skilful to forecast temperature and rainfall as well as streamflow, but with strong seasonal and regional dependence. Overall, SEAS5 and hydrological forecasts show skill that can potentially be used for hydrological/agricultural management.
Cindy Quik, Ype van der Velde, Jasper H. J. Candel, Luc Steinbuch, Roy van Beek, and Jakob Wallinga
Biogeosciences, 20, 695–718, https://doi.org/10.5194/bg-20-695-2023, https://doi.org/10.5194/bg-20-695-2023, 2023
Short summary
Short summary
In NW Europe only parts of former peatlands remain. When these peatlands formed is not well known but relevant for questions on landscape, climate and archaeology. We investigated the age of Fochteloërveen, using radiocarbon dating and modelling. Results show that peat initiated at several sites 11 000–7000 years ago and expanded rapidly 5000 years ago. Our approach may ultimately be applied to model peat ages outside current remnants and provide a view of these lost landscapes.
Jim Boonman, Mariet M. Hefting, Corine J. A. van Huissteden, Merit van den Berg, Jacobus (Ko) van Huissteden, Gilles Erkens, Roel Melman, and Ype van der Velde
Biogeosciences, 19, 5707–5727, https://doi.org/10.5194/bg-19-5707-2022, https://doi.org/10.5194/bg-19-5707-2022, 2022
Short summary
Short summary
Draining peat causes high CO2 emissions, and rewetting could potentially help solve this problem. In the dry year 2020 we measured that subsurface irrigation reduced CO2 emissions by 28 % and 83 % on two research sites. We modelled a peat parcel and found that the reduction depends on seepage and weather conditions and increases when using pressurized irrigation or maintaining high ditchwater levels. We found that soil temperature and moisture are suitable as indicators of peat CO2 emissions.
Tanya Juliette Rebecca Lippmann, Monique Heijmans, Han Dolman, Ype van der Velde, Dimmie Hendriks, and Ko van Huissteden
Geosci. Model Dev. Discuss., https://doi.org/10.5194/gmd-2022-143, https://doi.org/10.5194/gmd-2022-143, 2022
Preprint withdrawn
Short summary
Short summary
To assess the impact of vegetation on GHG fluxes in peatlands, we developed a new model, Peatland-VU-NUCOM (PVN). These results showed that plant communities impact GHG emissions, indicating that plant community re-establishment is a critical component of peatland restoration. This is the first time that a peatland emissions model investigated the role of re-introducing peat forming vegetation on GHG emissions.
Yousef Albuhaisi, Ype van der Velde, and Sander Houweling
Biogeosciences Discuss., https://doi.org/10.5194/bg-2022-55, https://doi.org/10.5194/bg-2022-55, 2022
Manuscript not accepted for further review
Short summary
Short summary
An important uncertainty in the modelling of methane emissions from natural wetlands is the wetland area. It is important to get the spatiotemporal covariance between the variables that drive methane emissions right for accurate quantification. Using high-resolution wetland and soil carbon maps, in combination with a simplified methane emission model that is coarsened in six steps from 0.005° to 1°, we find a strong relation between wetland emissions and the model resolution.
Thomas Janssen, Ype van der Velde, Florian Hofhansl, Sebastiaan Luyssaert, Kim Naudts, Bart Driessen, Katrin Fleischer, and Han Dolman
Biogeosciences, 18, 4445–4472, https://doi.org/10.5194/bg-18-4445-2021, https://doi.org/10.5194/bg-18-4445-2021, 2021
Short summary
Short summary
Satellite images show that the Amazon forest has greened up during past droughts. Measurements of tree stem growth and leaf litterfall upscaled using machine-learning algorithms show that leaf flushing at the onset of a drought results in canopy rejuvenation and green-up during drought while simultaneously trees excessively shed older leaves and tree stem growth declines. Canopy green-up during drought therefore does not necessarily point to enhanced tree growth and improved forest health.
Vince P. Kaandorp, Hans Peter Broers, Ype van der Velde, Joachim Rozemeijer, and Perry G. B. de Louw
Hydrol. Earth Syst. Sci., 25, 3691–3711, https://doi.org/10.5194/hess-25-3691-2021, https://doi.org/10.5194/hess-25-3691-2021, 2021
Short summary
Short summary
We reconstructed historical and present-day tritium, chloride, and nitrate concentrations in stream water of a catchment using
land-use-based input curves and calculated travel times of groundwater. Parameters such as the unsaturated zone thickness, mean travel time, and input patterns determine time lags between inputs and in-stream concentrations. The timescale of the breakthrough of pollutants in streams is dependent on the location of pollution in a catchment.
Jan Pisek, Angela Erb, Lauri Korhonen, Tobias Biermann, Arnaud Carrara, Edoardo Cremonese, Matthias Cuntz, Silvano Fares, Giacomo Gerosa, Thomas Grünwald, Niklas Hase, Michal Heliasz, Andreas Ibrom, Alexander Knohl, Johannes Kobler, Bart Kruijt, Holger Lange, Leena Leppänen, Jean-Marc Limousin, Francisco Ramon Lopez Serrano, Denis Loustau, Petr Lukeš, Lars Lundin, Riccardo Marzuoli, Meelis Mölder, Leonardo Montagnani, Johan Neirynck, Matthias Peichl, Corinna Rebmann, Eva Rubio, Margarida Santos-Reis, Crystal Schaaf, Marius Schmidt, Guillaume Simioni, Kamel Soudani, and Caroline Vincke
Biogeosciences, 18, 621–635, https://doi.org/10.5194/bg-18-621-2021, https://doi.org/10.5194/bg-18-621-2021, 2021
Short summary
Short summary
Understory vegetation is the most diverse, least understood component of forests worldwide. Understory communities are important drivers of overstory succession and nutrient cycling. Multi-angle remote sensing enables us to describe surface properties by means that are not possible when using mono-angle data. Evaluated over an extensive set of forest ecosystem experimental sites in Europe, our reported method can deliver good retrievals, especially over different forest types with open canopies.
Liang Yu, Joachim C. Rozemeijer, Hans Peter Broers, Boris M. van Breukelen, Jack J. Middelburg, Maarten Ouboter, and Ype van der Velde
Hydrol. Earth Syst. Sci., 25, 69–87, https://doi.org/10.5194/hess-25-69-2021, https://doi.org/10.5194/hess-25-69-2021, 2021
Short summary
Short summary
The assessment of the collected water quality information is for the managers to find a way to improve the water environment to satisfy human uses and environmental needs. We found groundwater containing high concentrations of nutrient mixes with rain water in the ditches. The stable solutes are diluted during rain. The change in nutrients over time is determined by and uptaken by organisms and chemical processes. The water is more enriched with nutrients and looked
dirtierduring winter.
Bram Droppers, Wietse H. P. Franssen, Michelle T. H. van Vliet, Bart Nijssen, and Fulco Ludwig
Geosci. Model Dev., 13, 5029–5052, https://doi.org/10.5194/gmd-13-5029-2020, https://doi.org/10.5194/gmd-13-5029-2020, 2020
Short summary
Short summary
Our study aims to include both both societal and natural water requirements and uses into a hydrological model in order to enable worldwide assessments of sustainable water use. The model was extended to include irrigation, domestic, industrial, energy, and livestock water uses as well as minimum flow requirements for natural systems. Initial results showed competition for water resources between society and nature, especially with respect to groundwater withdrawals.
Cited articles
Aben, R. C. H., van de Craats, D., Boonman, J., Peeters, S. H., Vriend, B., Boonman, C. C. F., van der Velde, Y., Erkens, G., and van den Berg, M.: Using automated transparent chambers to quantify CO2 emissions and potential emission reduction by water infiltration systems in drained coastal peatlands in the Netherlands, EGUsphere, 403, 1–31, https://doi.org/10.5194/egusphere-2024-403, 2024. a, b, c, d, e, f
Actueel Hoogtebestand Nederland: Kwaliteitsbeschrijving, https://www.ahn.nl/kwaliteitsbeschrijving (last access: 14 April 2025), 2025. a
Arets, E. J. M. M., van der Kolk, J. W. H., Hengeveld, G. M., Lesschen, J. P., Kramer, H., Kuikman, P. J., and Schelhaas, M. J.: Greenhouse gas reporting for the LULUCF sector in the Netherlands: methodological background, update 2018, WOt-technical report; No. 113, WOT Natuur and Milieu, https://doi.org/10.18174/441617, 2018. a
Arora, B., Wainwright, H. M., Dwivedi, D., Vaughn, L. J., Curtis, J. B., Torn, M. S., Dafflon, B., and Hubbard, S. S.: Evaluating temporal controls on greenhouse gas (GHG) fluxes in an Arctic tundra environment: An entropy-based approach, Sci. Total Environ., 649, 284–299, https://doi.org/10.1016/j.scitotenv.2018.08.251, 2019. a
Brouwer, F., Assinck, F., Harkema, T., Teuling, K., and Walvoort, D.: Actualisatie van de bodemkaart in de gemeente Vijfheerenlanden: herkartering van de verbreiding van veen, Tech. rep., WOT Natuur and Milieu, 2023. a
Buzacott, A. J., Kruijt, B., Bataille, L., van Giersbergen, Q., Heuts, T. S., Fritz, C., Nouta, R., Erkens, G., Boonman, J., van den Berg, M., van Huissteden, J., and van der Velde, Y.: Drivers and Annual Totals of Methane Emissions From Dutch Peatlands, Glob. Change Biol., 30, 1–22, https://doi.org/10.1111/gcb.17590, 2024. a
Campbell, D. I., Glover-Clark, G. L., Goodrich, J. P., Morcom, C. P., Schipper, L. A., and Wall, A. M.: Large differences in CO2 emissions from two dairy farms on a drained peatland driven by contrasting respiration rates during seasonal dry conditions, Sci. Total Environ., 760, 141621, https://doi.org/10.1016/j.scitotenv.2020.143410, 2021. a
Casso-Torralba, P., Vilà-Guerau de Arellano, J., Bosveld, F., Soler, M. R., Vermeulen, A., Werner, C., and Moors, E.: Diurnal and vertical variability of the sensible heat and carbon dioxide budgets in the atmospheric surface layer, J. Geophys. Res.-Atmos., 113, D12119, https://doi.org/10.1029/2007JD009583, 2008. a
Chandrashekar, G. and Sahin, F.: A survey on feature selection methods, Comput. Electr. Eng., 40, 16–28, https://doi.org/10.1016/j.compeleceng.2013.11.024, 2014. a
Cohrs, K. H., Varando, G., Carvalhais, N., Reichstein, M., and Camps-Valls, G.: Causal hybrid modeling with double machine learning–applications in carbon flux modeling, Mach. Learn., 5, 035021, https://doi.org/10.1088/2632-2153/ad5a60, 2024. a
de Arellano, J. V. G., Gioli, B., Miglietta, F., Jonker, H. J. J., Baltink, H. K., Hutjes, R. W. A., and Holtslag, A. A. M.: Entrainment process of carbon dioxide in the atmospheric boundary layer, J. Geophys. Res.-Atmos., 109, D18110, https://doi.org/10.1029/2004JD004725, 2004. a
Didan, K.: MOD13Q1 MODIS/Terra Vegetation Indices 16-Day L3 Global 250m SIN Grid V061 [data set], https://doi.org/10.5067/MODIS/MOD13Q1.061, 2021. a
Dou, X., Yang, Y., and Luo, J.: Estimating Forest Carbon Fluxes Using Machine Learning Techniques Based on Eddy Covariance Measurements, Sustainability, 10, 203, https://doi.org/10.3390/su10010203, 2018. a
Erkens, G., van der Meulen, M. J., and Middelkoop, H.: Double trouble: Subsidence and CO2 respiration due to 1,000 years of Dutch coastal peatlands cultivation, Hydrogeol. J., 24, 551–568, https://doi.org/10.1007/s10040-016-1380-4, 2016. a, b
Erkens, G., Melman, R., Jansen, S., Boonman, J., van der Velde, Y., Hefting, M., Keuskamp, J., van den Berg, M., van den Akker, J., Fritz, C., Bootsma, H., Aben, R., Hessel, R., Hutjes, R., van Asselen, S., Harpenslager, S. F., Kruijt, B., and consortium, N.: SOMERS: Monitoring greenhouse gas emission from the Dutch peatland meadows on parcel level, EGU General Assembly 2022, Vienna, Austria, 23–27 May 2022, EGU22-12177, https://doi.org/10.5194/egusphere-egu22-12177, 2022. a
Evans, C. D., Peacock, M., Baird, A. J., Artz, R. R., Burden, A., Callaghan, N., Chapman, P. J., Cooper, H. M., Coyle, M., Craig, E., Cumming, A., Dixon, S., Gauci, V., Grayson, R. P., Helfter, C., Heppell, C. M., Holden, J., Jones, D. L., Kaduk, J., Levy, P., Matthews, R., McNamara, N. P., Misselbrook, T., Oakley, S., Page, S. E., Rayment, M., Ridley, L. M., Stanley, K. M., Williamson, J. L., Worrall, F., and Morrison, R.: Overriding water table control on managed peatland greenhouse gas emissions, Nature, 593, 548–552, https://doi.org/10.1038/s41586-021-03523-1, 2021. a, b, c, d, e, f
Farahani, M. A. and Goodwell, A. E.: Causal Drivers of Land-Atmosphere Carbon Fluxes From Machine Learning Models and Data, J. Geophys. Res.-Biogeo., 129, e2023JG007815, https://doi.org/10.1029/2023JG007815, 2024. a, b, c
Finnigan, J.: The storage term in eddy flux calculations, Agr. Forest Meteorol., 136, 108–113, https://doi.org/10.1016/j.agrformet.2004.12.010, 2006. a
Friedrich, S., Gerner, A., Tarantik, M., Chiogna, G., and Disse, M.: Assessment of rewetting scenarios under varying climate conditions in a partially restored raised bog in Bavaria, Germany, J. Hydrol., 52, 101695, https://doi.org/10.1016/j.ejrh.2024.101695, 2024. a
Frolking, S. and Roulet, N. T.: Holocene radiative forcing impact of northern peatland carbon accumulation and methane emissions, Glob. Change Biol., 13, 1079–1088, https://doi.org/10.1111/j.1365-2486.2007.01339.x, 2007. a
Government of the Netherlands: Climate Agreement, https://www.government.nl/binaries/government/documenten/reports/2019/06/28/climate-agreement/Climate+Agreement.pdf (last access: 5 April 2025), 2019. a
Hannun, R. A., Wolfe, G. M., Kawa, S. R., Hanisco, T. F., Newman, P. A., Alfieri, J. G., Barrick, J., Clark, K. L., DiGangi, J. P., Diskinm Glenn S, King, J., Kustas, W. P., Mitra, B., Noormets, A., Nowak, J. B., Thornhill, K. L., and Vargas, R.: Spatial heterogeneity in CO2, CH4, and energy fluxes: insights from airborne eddy covariance measurements over the Mid-Atlantic region, Environ. Res. Lett., 15, 035008, https://doi.org/10.1088/1748-9326/ab7391, 2020. a
Hazeu, G., Schuiling, R., Thomas, D., Vittek, M., Storm, M., and Bulens, J. D.: Landelijk Grondgebruiksbestand Nederland 2021 (LGN2021): achtergronden, methodiek en validatie, Tech. rep., Wageningen Environmental Research, https://doi.org/10.18174/585714, 2023. a
Huete, A., Didan, K., Miura, T., Rodriguez, E. P., Gao, X., and Ferreira, L. G.: Overview of the radiometric and biophysical performance of the MODIS vegetation indices, Remote Sens. Environ., 83, 195–213, https://doi.org/10.1016/S0034-4257(02)00096-2, 2002. a
Hutjes, R. W. A., Vellinga, O. S., Gioli, B., and Miglietta, F.: Dis-aggregation of airborne flux measurements using footprint analysis, Agr. Forest Meteorol., 150, 966–983, https://doi.org/10.1016/j.agrformet.2010.03.004, 2010. a
Hydrologic: OWASIS: essentiële informatie voor het waterbeheer nu beschikbaar, https://www.hydrologic.nl/owasis-essentiele-informatie-voor-het-waterbeheer/ (last access: 29 February 2025), 2019. a
Jung, M., Reichstein, M., Margolis, H. A., Cescatti, A., Richardson, A. D., Arain, M. A., Arneth, A., Bernhofer, C., Bonal, D., Chen, J., Gianelle, D., Gobron, N., Kiely, G., Kutsch, W., Lasslop, G., Law, B. E., Lindroth, A., Merbold, L., Vaccari, F., and Williams, C.: Global patterns of land-atmosphere fluxes of carbon dioxide, latent heat, and sensible heat derived from eddy covariance, satellite, and meteorological observations, J. Geophys. Res., 116, G00J07, https://doi.org/10.1029/2010JG001566, 2011. a
Jung, M., Schwalm, C., Migliavacca, M., Walther, S., Camps-Valls, G., Koirala, S., Anthoni, P., Besnard, S., Bodesheim, P., Carvalhais, N., Chevallier, F., Gans, F., Goll, D. S., Haverd, V., Köhler, P., Ichii, K., Jain, A. K., Liu, J., Lombardozzi, D., Nabel, J. E. M. S., Nelson, J. A., O'Sullivan, M., Pallandt, M., Papale, D., Peters, W., Pongratz, J., Rödenbeck, C., Sitch, S., Tramontana, G., Walker, A., Weber, U., and Reichstein, M.: Scaling carbon fluxes from eddy covariance sites to globe: synthesis and evaluation of the FLUXCOM approach, Biogeosciences, 17, 1343–1365, https://doi.org/10.5194/bg-17-1343-2020, 2020. a
Jurasinski, G., Günther, A., Huth, V., Couwenberg, J., and Glatzel, S.: Greenhouse gas emissions, Schweizerbart Science Publishers, ISBN 9783510652839, http://www.schweizerbart.de//publications/detail/isbn/9783510652839/Wichtmann_Schroder_Joosten_Paludicu (last access: 15 April 2025), 2016. a
Kljun, N., Calanca, P., Rotach, M. W., and Schmid, H. P.: A simple two-dimensional parameterisation for Flux Footprint Prediction (FFP), Geosci. Model Dev., 8, 3695–3713, https://doi.org/10.5194/gmd-8-3695-2015, 2015. a, b, c
Kljun, N., Calanca, P., Rotach, M. W., and Schmid, H. P.: A simple two-dimensional parameterisation for Flux Footprint Prediction (FFP), Footprint [code], https://footprint.kljun.net/ (last access: 20 January 2025), 2025. a
KNMI: KNMI Climate Data, https://www.knmi.nl/klimaat (last access: 20 February 2025), 2024. a
Koch, J., Elsgaard, L., Greve, M. H., Gyldenkærne, S., Hermansen, C., Levin, G., Wu, S., and Stisen, S.: Water-table-driven greenhouse gas emission estimates guide peatland restoration at national scale, Biogeosciences, 20, 2387–2403, https://doi.org/10.5194/bg-20-2387-2023, 2023. a, b
Kruijt, B., Buzacott, A., van Giersbergen, Q., Bataille, L., Biermann, J., Berghuis, H., Heuts, T., Jans, W., Nouta, R., van Huissteden Hefting, F., and Hoogland, J. M.: CO2 emissions from peatlands in The Netherlands: drivers of variability in Eddy covariance fluxes, Nationaal Onderzoeksprogramma Broeikasgassen Veenweiden (NOBV), Chap. 5, NOBV year report, the Netherlands, 2022. a, b, c, d, e, f, g, h
Kwakernaak, C., van den Akker, J., Veenendaal, E., van Huissteden, K., and Kroon, P.: Mogelijkheden voor mitigatie en adaptatie Veenweiden en klimaat, Bodem: tijdschrift over duurzaam bodembeheer, 3, 6–8, 2010. a
Leifeld, J. and Menichetti, L.: The underappreciated potential of peatlands in global climate change mitigation strategies, Nat. Commun. 9, 1071, https://doi.org/10.1038/s41467-018-03406-6, 2018. a
LI-COR Biosciences: LI-COR Eddy Covariance Instrumentation and Software User Manual, LI-COR Biosciences, https://licor.app.boxenterprise.net/s/1ium2zmwm6hl36yz9bu4 (last access: 11 April 2025), 2023. a
Ligtenberg, J., Berendrecht, W., van Doorn, A., Klopstra, D., Pezij, M., Velstra, J., and van der Vliet, N.: Validatie en toetsing LHM 4.1 Samenvattend hoofdrapport, PR4313.10, HKV, Acacia Water and Berendrecht Consultancy, https://open.rijkswaterstaat.nl/@47860/validatie-toetsing-lhm-4-1-samenvattend/ (last access: 20 January 2025), 2021. a
Liu, L., Zhou, W., Guan, K., Peng, B., Xu, S., Tang, J., Zhu, Q., Till, J., Jia, X., Jiang, C., Wang, S., Qin, Z., Kong, H., Grant, R., Mezbahuddin, S., Kumar, V., and Jin, Z.: Knowledge-guided machine learning can improve carbon cycle quantification in agroecosystems, Nat. Commun., 15, 357, https://doi.org/10.1038/s41467-023-43860-5, 2024. a
Loisel, J., Gallego-Sala, A. V., Amesbury, M. J., Magnan, G., Anshari, G., Beilman, D. W., Benavides, J. C., Blewett, J., Camill, P., Charman, D. J., Chawchai, S., Hedgpeth, A., Kleinen, T., Korhola, A., Large, D., Mansilla, C. A., Müller, J., van Bellen, S., West, J. B., Yu, Z., Bubier, J. L., Garneau, M., Moore, T., Sannel, A. B., Page, S., Väliranta, M., Bechtold, M., Brovkin, V., Cole, L. E., Chanton, J. P., Christensen, T. R., Davies, M. A., De Vleeschouwer, F., Finkelstein, S. A., Frolking, S., Gałka, M., Gandois, L., Girkin, N., Harris, L. I., Heinemeyer, A., Hoyt, A. M., Jones, M. C., Joos, F., Juutinen, S., Kaiser, K., Lacourse, T., Lamentowicz, M., Larmola, T., Leifeld, J., Lohila, A., Milner, A. M., Minkkinen, K., Moss, P., Naafs, B. D., Nichols, J., O'Donnell, J., Payne, R., Philben, M., Piilo, S., Quillet, A., Ratnayake, A. S., Roland, T. P., Sjögersten, S., Sonnentag, O., Swindles, G. T., Swinnen, W., Talbot, J., Treat, C., Valach, A. C., and Wu, J.: Expert assessment of future vulnerability of the global peatland carbon sink, Nat. Clim. Change, 11, 70–77, https://doi.org/10.1038/s41558-020-00944-0, 2021. a
Lundberg, S. M. and Lee, S. I.: A Unified Approach to Interpreting Model Predictions, in: Advances in Neural Information Processing Systems 30 (NIPS 2017), 4765–4774, ISBN 9781510860964, 2017. a
McDermitt, D., Burba, G., Xu, L., Anderson, T., Komissarov, A., Riensche, B., Schedlbauer, J., Starr, G., Zona, D., Oechel, W., Oberbauer, S., and Hastings, S.: A new low-power, open-path instrument for measuring methane flux by eddy covariance, Appl. Phys. B, 102, 391–405, https://doi.org/10.1007/s00340-010-4307-0, 2011. a
Meesters, A., Tolk, L., Peters, W., Hutjes, R., Vellinga, O., Elbers, J., Vermeulen, A., van der Laan, S., Neubert, R., Meijer, H., and Dolman, A.: Inverse carbon dioxide flux estimates for the Netherlands, J. Geophys. Res.-Atmos., 117, D20306, https://doi.org/10.1029/2012JD017797, 2012. a
Metzger, S., Junkermann, W., Mauder, M., Butterbach-Bahl, K., Trancón Y Widemann, B., Neidl, F., Schäfer, K., Wieneke, S., Zheng, X. H., Schmid, H. P., and Foken, T.: Spatially explicit regionalization of airborne flux measurements using environmental response functions, Biogeosciences, 10, 2193–2217, https://doi.org/10.5194/bg-10-2193-2013, 2013. a, b, c, d, e
Metzger, S., Durden, D., Paleri, S., Sühring, M., Butterworth, B. J., Florian, C., Mauder, M., Plummer, D. M., Wanner, L., Xu, K., and Desai, A. R.: Novel approach to observing system simulation experiments improves information gain of surface–atmosphere field measurements, Atmos. Meas. Tech., 14, 6929–6954, https://doi.org/10.5194/amt-14-6929-2021, 2021. a, b
NHI: Netherlands Hydrological Instrumentarium Models, https://nhi.nu/modellen/ (last access: 20 January 2025), 2025. a
Nielsen, D.: Tree Boosting With XGBoost, Ph.D. thesis, Norwegian University of Science and Technology, ISSN 17585880, https://doi.org/10.1111/j.1758-5899.2011.00096.x, 2016. a
Nijman, T. P., van Giersbergen, Q., Heuts, T. S., Nouta, R., Boonman, C. C., Velthuis, M., Kruijt, B., Aben, R. C., and Fritz, C.: Drainage effects on carbon budgets of degraded peatlands in the north of the Netherlands, Sci. Total Environ., 935, 172882, https://doi.org/10.1016/j.scitotenv.2024.172882, 2024. a, b
Ogunleye, A. and Wang, Q.-G.: XGBoost model for chronic kidney disease diagnosis, IEEE/ACM transactions on computational biology and bioinformatics, 17, 2131–2140, https://doi.org/10.1109/TCBB.2019.2911071, 2019. a
Paleri, S., Desai, A. R., Metzger, S., Durden, D., Butterworth, B. J., Mauder, M., Kohnert, K., and Serafimovich, A.: Space-Scale Resolved Surface Fluxes Across a Heterogeneous, Mid-Latitude Forested Landscape, J. Geophys. Res.-Atmos., 127, e2022JD037138, https://doi.org/10.1029/2022JD037138, 2022. a
Papale, D., Reichstein, M., Aubinet, M., Canfora, E., Bernhofer, C., Kutsch, W., Longdoz, B., Rambal, S., Valentini, R., Vesala, T., and Yakir, D.: Towards a standardized processing of Net Ecosystem Exchange measured with eddy covariance technique: algorithms and uncertainty estimation, Biogeosciences, 3, 571–583, https://doi.org/10.5194/bg-3-571-2006, 2006. a
Prabha, A., Yadav, J., Rani, A., and Singh, V.: Design of intelligent diabetes mellitus detection system using hybrid feature selection based XGBoost classifier, Comput. Biol. Med., 136, 104664, https://doi.org/10.1016/j.compbiomed.2021.104664, 2021. a
Rijkswaterstaat: Actueel Hoogtebestand Nederland (AHN3), https://www.pdok.nl/introductie/-/article/actueel-hoogtebestand-nederland-ahn (last access: 14 April 2025), 2019. a
Rodríguez-Pérez, R. and Bajorath, J.: Interpretation of machine learning models using shapley values: application to compound potency and multi-target activity predictions, J. Comput. Aided. Mol. Des., 34, 1013–1026, https://doi.org/10.1007/s10822-020-00314-0, 2020. a, b
Ruyssenaars, P., van der Net, L., Coenen, P., Rienstra, J., Zijlema, P., Arets, E., Baas, K., Dröge, R., Geilenkirchen, G., t Hoen, M., Honig, E., van Huet, B., van Huis, E., Koch, W., Lagerwerf, L., te Molder, R., Montfoort, J., Vonk, J., and van Zanten, M.: Greenhouse gas emissions in the Netherlands 1990–2020, Rijksinstituut voor Volksgezondheid en Milieu Rijksinstituut voor Volksgezondheid en Milieu RIVM, https://doi.org/10.21945/RIVM-2022-0005, 2022. a
Sang, X., Xiao, W., Zheng, H., Yang, Y., and Liu, T.: HMMPred : Accurate Prediction of DNA-Binding Proteins Based on HMM Profiles and XGBoost Feature Selection, Comput. Math. Method. M., 2020, 384749, https://doi.org/10.1155/2020/1384749, 2020. a
Serafimovich, A., Metzger, S., Hartmann, J., Kohnert, K., Zona, D., and Sachs, T.: Upscaling surface energy fluxes over the North Slope of Alaska using airborne eddy-covariance measurements and environmental response functions, Atmos. Chem. Phys., 18, 10007–10023, https://doi.org/10.5194/acp-18-10007-2018, 2018. a, b, c
Sun, Y., Jia, L., Chen, Q., and Zheng, C.: Optimizing window length for turbulent heat flux calculations from airborne eddy covariance measurements under near neutral to unstable atmospheric stability conditions, Remote Sens., 10, 670, https://doi.org/10.3390/rs10050670, 2018. a
Sun, Y., Jia, L., Chen, Q., Lin, X., Sude, B., Quan, Z., and Hutjes, R. W.: Construction of a spatially gridded heat flux map based on airborne flux Measurements using remote sensing and machine learning methods, Agr. Forest Meteorol., 334, 109424, https://doi.org/10.1016/j.agrformet.2023.109424, 2023. a
Tiemeyer, B., Freibauer, A., Borraz, E. A., Augustin, J., Bechtold, M., Beetz, S., Beyer, C., Ebli, M., Eickenscheidt, T., Fiedler, S., Förster, C., Gensior, A., Giebels, M., Glatzel, S., Heinichen, J., Hoffmann, M., Höper, H., Jurasinski, G., Laggner, A., Leiber-Sauheitl, K., Peichl-Brak, M., and Drösler, M.: A new methodology for organic soils in national greenhouse gas inventories: Data synthesis, derivation and application, Ecol. Indic., 109, 105838, https://doi.org/10.1016/j.ecolind.2019.105838, 2020. a, b, c, d, e, f
van Asselen, S., Erkens, G., and de Graaf, F.: Monitoring shallow subsidence in cultivated peatlands, P. Int. Assoc. Hydrol. Sci., 382, 189–194, https://doi.org/10.5194/piahs-382-189-2020, 2020. a
van den Akker, J., Kuikman, P., de Vries, F., Hoving, I., Pleijter, M., Hendriks, R., Wolleswinkel, R., Simões, R., and Kwakernaak, C.: Emission of CO2 from Agriculutral Peat Soils in the Netherlands and Ways to Limit this Emission, Proceedings of the 13th International Peat Congress, Tullamore, Ireland, 8–13 June 2008, OND1314518, International Peat Society, ISBN: 9780951489048, 2008. a
Vaughan, A. R., Lee, J. D., Metzger, S., Durden, D., Lewis, A. C., Shaw, M. D., Drysdale, W. S., Purvis, R. M., Davison, B., and Nicholas Hewitt, C.: Spatially and temporally resolved measurements of NOx fluxes by airborne eddy covariance over Greater London, Atmos. Chem. Phys., 21, 15283–15298, https://doi.org/10.5194/acp-21-15283-2021, 2021. a, b
Vellinga, O. S., Gioli, B., Elbers, J. A., Holtslag, A. A. M., Kabat, P., and Hutjes, R. W. A.: Regional carbon dioxide and energy fluxes from airborne observations using flight-path segmentation based on landscape characteristics, Biogeosciences, 7, 1307–1321, https://doi.org/10.5194/bg-7-1307-2010, 2010. a, b
Vellinga, O. S., Dobosy, R. J., Dumas, E. J., Gioli, B., Elbers, J. A., and Hutjes, R. W.: Calibration and Quality Assurance of Flux Observations from a Small Research Aircraft, J. Atmos. Ocean. Technol., 30, 161–181, https://doi.org/10.1175/JTECH-D-11-00138.1, 2013. a, b
Vickers, D. and Mahrt, L.: Quality control and flux sampling problems for tower and aircraft data, J. Atmos. Ocean. Technol., 14, 512–526, https://doi.org/10.1175/1520-0426(1997)014<0512:QCAFSP>2.0.CO;2, 1997. a
Wageningen Environmental Research: Veendikte 2014, https://opendata.zuid-holland.nl/geonetwork/srv/api/records/098B74D3-D49B-422A-BCA4-6C11A3FA7D2A (last access: 14 April 2025), 2015. a
Wang, Y. and Ni, X. S.: A XGBoost risk model via feature selection and Bayesian hyper-parameter optimization, arXiv Prepr, arXiv1901.08433, https://doi.org/10.48550/arXiv.1901.08433, 2019. a
Webb, E. K., Pearman, G. I., and Leuning, R.: Correction of flux measurements for density effects due to heat and water vapour transfer, Quarterly J. Roy. Meteorol. Soc., 106, 85–100, https://doi.org/10.1002/qj.49710644707, 1980. a
Yu, Z., Loisel, J., Brosseau, D. P., Beilman, D. W., and Hunt, S. J.: Global peatland dynamics since the Last Glacial Maximum, Geophys. Res. Lett., 37, L13402, https://doi.org/10.1029/2010GL043584, 2010. a
Yuan, K., Zhu, Q., Li, F., Riley, W. J., Torn, M., Chu, H., McNicol, G., Chen, M., Knox, S., Delwiche, K., Wu, H., Baldocchi, D., Ma, H., Desai, A. R., Chen, J., Sachs, T., Ueyama, M., Sonnentag, O., Helbig, M., Tuittila, E. S., Jurasinski, G., Koebsch, F., Campbell, D., Schmid, H. P., Lohila, A., Goeckede, M., Nilsson, M. B., Friborg, T., Jansen, J., Zona, D., Euskirchen, E., Ward, E. J., Bohrer, G., Jin, Z., Liu, L., Iwata, H., Goodrich, J., and Jackson, R.: Causality guided machine learning model on wetland CH4 emissions across global wetlands, Agr. Forest Meteorol., 324, 109115, https://doi.org/10.1016/j.agrformet.2022.109115, 2022. a, b
Zhou, Y., Sachs, T., Li, Z., Pang, Y., Xu, J., Kalhori, A., Wille, C., Peng, X., Fu, X., Wu, Y., and Wu, L.: Long-term effects of rewetting and drought on GPP in a temperate peatland based on satellite remote sensing data, Sci. Total Environ., 882, 163395, https://doi.org/10.1016/j.scitotenv.2023.163395, 2023. a
Zulueta, R. C., Oechel, W. C., Loescher, H. W., Lawrence, W. T., and Paw U, K. T.: Aircraft-derived regional scale CO2 fluxes from vegetated drained thaw-lake basins and interstitial tundra on the Arctic Coastal Plain of Alaska, Glob. Change Biol., 17, 2781–2802, https://doi.org/10.1111/j.1365-2486.2011.02433.x, 2011. a
Short summary
We combine two types of carbon dioxide (CO2) data from Dutch peatlands in a machine learning model: from fixed measurement towers and from a light research aircraft. We find that emissions increase with deeper water table depths (WTDs) by 4.6 tons of CO2 per hectare per year for each 10 cm deeper WTD on average. The effect is stronger in winter than in summer and varies between locations. This variability should be taken into account when developing mitigation measures.
We combine two types of carbon dioxide (CO2) data from Dutch peatlands in a machine learning...
Altmetrics
Final-revised paper
Preprint