Wetland CH4 emissions are among the most uncertain components of the global CH4 budget. The complex nature of wetland CH4 processes makes it challenging to identify causal relationships for improving our understanding and predictability of CH4 emissions. In this study, we used the flux measurements of CH4 from eddy covariance towers (30 sites from 4 wetlands types: bog, fen, marsh, and wet tundra) to construct a causality-constrained machine learning (ML) framework to explain the regulative factors and to capture CH4 emissions at sub-seasonal scale. We found that soil temperature is the dominant factor for CH4 emissions in all studied wetland types. Ecosystem respiration (CO2) and gross primary productivity exert controls at bog, fen, and marsh sites with lagged responses of days to weeks. Integrating these asynchronous environmental and biological causal relationships in predictive models significantly improved model performance. More importantly, modeled CH4 emissions differed by up to a factor of 4 under a +1°C warming scenario when causality constraints were considered. These results highlight the significant role of causality in modeling wetland CH4 emissions especially under future warming conditions, while traditional data-driven ML models may reproduce observations for the wrong reasons. Our proposed causality-guided model could benefit predictive modeling, large-scale upscaling, data gap-filling, and surrogate modeling of wetland CH4 emissions within earth system land models.

Abstract Despite the importance of high-latitude surface energy budgets (SEBs) for land-climate interactions in the rapidly changing Arctic, uncertainties in their prediction persist. Here, we harmonize SEB observations across a network of vegetated and glaciated sites at circumpolar scale (1994–2021). Our variance-partitioning analysis identifies vegetation type as an important predictor for SEB-components during Arctic summer (June-August), compared to other SEB-drivers including climate, latitude and permafrost characteristics. Differences among vegetation types can be of similar magnitude as between vegetation and glacier surfaces and are especially high for summer sensible and latent heat fluxes. The timing of SEB-flux summer-regimes (when daily mean values exceed 0 Wm −2 ) relative to snow-free and -onset dates varies substantially depending on vegetation type, implying vegetation controls on snow-cover and SEB-flux seasonality. Our results indicate complex shifts in surface energy fluxes with land-cover transitions and a lengthening summer season, and highlight the potential for improving future Earth system models via a refined representation of Arctic vegetation types.

Abstract Wetland methane (CH 4 ) emissions ( $${F}_{{{CH}}_{4}}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msub> <mml:mrow> <mml:mi>F</mml:mi> </mml:mrow> <mml:mrow> <mml:msub> <mml:mrow> <mml:mi>C</mml:mi> <mml:mi>H</mml:mi> </mml:mrow> <mml:mrow> <mml:mn>4</mml:mn> </mml:mrow> </mml:msub> </mml:mrow> </mml:msub> </mml:math> ) are important in global carbon budgets and climate change assessments. Currently, $${F}_{{{CH}}_{4}}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msub> <mml:mrow> <mml:mi>F</mml:mi> </mml:mrow> <mml:mrow> <mml:msub> <mml:mrow> <mml:mi>C</mml:mi> <mml:mi>H</mml:mi> </mml:mrow> <mml:mrow> <mml:mn>4</mml:mn> </mml:mrow> </mml:msub> </mml:mrow> </mml:msub> </mml:math> projections rely on prescribed static temperature sensitivity that varies among biogeochemical models. Meta-analyses have proposed a consistent $${F}_{{{CH}}_{4}}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msub> <mml:mrow> <mml:mi>F</mml:mi> </mml:mrow> <mml:mrow> <mml:msub> <mml:mrow> <mml:mi>C</mml:mi> <mml:mi>H</mml:mi> </mml:mrow> <mml:mrow> <mml:mn>4</mml:mn> </mml:mrow> </mml:msub> </mml:mrow> </mml:msub> </mml:math> temperature dependence across spatial scales for use in models; however, site-level studies demonstrate that $${F}_{{{CH}}_{4}}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msub> <mml:mrow> <mml:mi>F</mml:mi> </mml:mrow> <mml:mrow> <mml:msub> <mml:mrow> <mml:mi>C</mml:mi> <mml:mi>H</mml:mi> </mml:mrow> <mml:mrow> <mml:mn>4</mml:mn> </mml:mrow> </mml:msub> </mml:mrow> </mml:msub> </mml:math> are often controlled by factors beyond temperature. Here, we evaluate the relationship between $${F}_{{{CH}}_{4}}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msub> <mml:mrow> <mml:mi>F</mml:mi> </mml:mrow> <mml:mrow> <mml:msub> <mml:mrow> <mml:mi>C</mml:mi> <mml:mi>H</mml:mi> </mml:mrow> <mml:mrow> <mml:mn>4</mml:mn> </mml:mrow> </mml:msub> </mml:mrow> </mml:msub> </mml:math> and temperature using observations from the FLUXNET-CH 4 database. Measurements collected across the globe show substantial seasonal hysteresis between $${F}_{{{CH}}_{4}}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msub> <mml:mrow> <mml:mi>F</mml:mi> </mml:mrow> <mml:mrow> <mml:msub> <mml:mrow> <mml:mi>C</mml:mi> <mml:mi>H</mml:mi> </mml:mrow> <mml:mrow> <mml:mn>4</mml:mn> </mml:mrow> </mml:msub> </mml:mrow> </mml:msub> </mml:math> and temperature, suggesting larger $${F}_{{{CH}}_{4}}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msub> <mml:mrow> <mml:mi>F</mml:mi> </mml:mrow> <mml:mrow> <mml:msub> <mml:mrow> <mml:mi>C</mml:mi> <mml:mi>H</mml:mi> </mml:mrow> <mml:mrow> <mml:mn>4</mml:mn> </mml:mrow> </mml:msub> </mml:mrow> </mml:msub> </mml:math> sensitivity to temperature later in the frost-free season (about 77% of site-years). Results derived from a machine-learning model and several regression models highlight the importance of representing the large spatial and temporal variability within site-years and ecosystem types. Mechanistic advancements in biogeochemical model parameterization and detailed measurements in factors modulating CH 4 production are thus needed to improve global CH 4 budget assessments.

Abstract Wetland methane (CH 4 ) emissions ( $${F}_{{{CH}}_{4}}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msub> <mml:mrow> <mml:mi>F</mml:mi> </mml:mrow> <mml:mrow> <mml:msub> <mml:mrow> <mml:mi>C</mml:mi> <mml:mi>H</mml:mi> </mml:mrow> <mml:mrow> <mml:mn>4</mml:mn> </mml:mrow> </mml:msub> </mml:mrow> </mml:msub> </mml:math> ) are important in global carbon budgets and climate change assessments. Currently, $${F}_{{{CH}}_{4}}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msub> <mml:mrow> <mml:mi>F</mml:mi> </mml:mrow> <mml:mrow> <mml:msub> <mml:mrow> <mml:mi>C</mml:mi> <mml:mi>H</mml:mi> </mml:mrow> <mml:mrow> <mml:mn>4</mml:mn> </mml:mrow> </mml:msub> </mml:mrow> </mml:msub> </mml:math> projections rely on prescribed static temperature sensitivity that varies among biogeochemical models. Meta-analyses have proposed a consistent $${F}_{{{CH}}_{4}}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msub> <mml:mrow> <mml:mi>F</mml:mi> </mml:mrow> <mml:mrow> <mml:msub> <mml:mrow> <mml:mi>C</mml:mi> <mml:mi>H</mml:mi> </mml:mrow> <mml:mrow> <mml:mn>4</mml:mn> </mml:mrow> </mml:msub> </mml:mrow> </mml:msub> </mml:math> temperature dependence across spatial scales for use in models; however, site-level studies demonstrate that $${F}_{{{CH}}_{4}}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msub> <mml:mrow> <mml:mi>F</mml:mi> </mml:mrow> <mml:mrow> <mml:msub> <mml:mrow> <mml:mi>C</mml:mi> <mml:mi>H</mml:mi> </mml:mrow> <mml:mrow> <mml:mn>4</mml:mn> </mml:mrow> </mml:msub> </mml:mrow> </mml:msub> </mml:math> are often controlled by factors beyond temperature. Here, we evaluate the relationship between $${F}_{{{CH}}_{4}}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msub> <mml:mrow> <mml:mi>F</mml:mi> </mml:mrow> <mml:mrow> <mml:msub> <mml:mrow> <mml:mi>C</mml:mi> <mml:mi>H</mml:mi> </mml:mrow> <mml:mrow> <mml:mn>4</mml:mn> </mml:mrow> </mml:msub> </mml:mrow> </mml:msub> </mml:math> and temperature using observations from the FLUXNET-CH 4 database. Measurements collected across the globe show substantial seasonal hysteresis between $${F}_{{{CH}}_{4}}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msub> <mml:mrow> <mml:mi>F</mml:mi> </mml:mrow> <mml:mrow> <mml:msub> <mml:mrow> <mml:mi>C</mml:mi> <mml:mi>H</mml:mi> </mml:mrow> <mml:mrow> <mml:mn>4</mml:mn> </mml:mrow> </mml:msub> </mml:mrow> </mml:msub> </mml:math> and temperature, suggesting larger $${F}_{{{CH}}_{4}}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msub> <mml:mrow> <mml:mi>F</mml:mi> </mml:mrow> <mml:mrow> <mml:msub> <mml:mrow> <mml:mi>C</mml:mi> <mml:mi>H</mml:mi> </mml:mrow> <mml:mrow> <mml:mn>4</mml:mn> </mml:mrow> </mml:msub> </mml:mrow> </mml:msub> </mml:math> sensitivity to temperature later in the frost-free season (about 77% of site-years). Results derived from a machine-learning model and several regression models highlight the importance of representing the large spatial and temporal variability within site-years and ecosystem types. Mechanistic advancements in biogeochemical model parameterization and detailed measurements in factors modulating CH 4 production are thus needed to improve global CH 4 budget assessments.

• We evaluate methane flux gap-filling methods across 17 boreal-to-tropical wetlands • New methods for generating realistic artificial gaps and uncertainties are proposed • Decision tree algorithms perform slightly better than neural networks on average • Soil temperature and generic seasonality are the most important predictors • Open-source code is released for gap-filling steps and uncertainty evaluation 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 half-hourly 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).

• We evaluate methane flux gap-filling methods across 17 boreal-to-tropical wetlands • New methods for generating realistic artificial gaps and uncertainties are proposed • Decision tree algorithms perform slightly better than neural networks on average • Soil temperature and generic seasonality are the most important predictors • Open-source code is released for gap-filling steps and uncertainty evaluation 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 half-hourly 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).

The response of evapotranspiration (ET) to warming is of critical importance to the water and carbon cycle of the boreal biome, a mosaic of land cover types dominated by forests and peatlands. The effect of warming-induced vapour pressure deficit (VPD) increases on boreal ET remains poorly understood because peatlands are not specifically represented as plant functional types in Earth system models. Here we show that peatland ET increases more than forest ET with increasing VPD using observations from 95 eddy covariance tower sites. At high VPD of more than 2 kPa, peatland ET exceeds forest ET by up to 30%. Future (2091–2100) mid-growing season peatland ET is estimated to exceed forest ET by over 20% in about one-third of the boreal biome for RCP4.5 and about two-thirds for RCP8.5. Peatland-specific ET responses to VPD should therefore be included in Earth system models to avoid biases in water and carbon cycle projections.

Peatlands and forests cover large areas of the boreal biome and are critical for global climate regulation. They also regulate regional climate through heat and water vapour exchange with the atmosphere. Understanding how land-atmosphere interactions in peatlands differ from forests may therefore be crucial for modelling boreal climate system dynamics and for assessing climate benefits of peatland conservation and restoration. To assess the biophysical impacts of peatlands and forests on peak growing season air temperature and humidity, we analysed surface energy fluxes and albedo from 35 peatlands and 37 evergreen needleleaf forests - the dominant boreal forest type - and simulated air temperature and vapour pressure deficit (VPD) over hypothetical homogeneous peatland and forest landscapes. We ran an evapotranspiration model using land surface parameters derived from energy flux observations and coupled an analytical solution for the surface energy balance to an atmospheric boundary layer (ABL) model. We found that peatlands, compared to forests, are characterized by higher growing season albedo, lower aerodynamic conductance, and higher surface conductance for an equivalent VPD. This combination of peatland surface properties results in a ∼20% decrease in afternoon ABL height, a cooling (from 1.7 to 2.5 °C) in afternoon air temperatures, and a decrease in afternoon VPD (from 0.4 to 0.7 kPa) for peatland landscapes compared to forest landscapes. These biophysical climate impacts of peatlands are most pronounced at lower latitudes (∼45°N) and decrease toward the northern limit of the boreal biome (∼70°N). Thus, boreal peatlands have the potential to mitigate the effect of regional climate warming during the growing season. The biophysical climate mitigation potential of peatlands needs to be accounted for when projecting the future climate of the boreal biome, when assessing the climate benefits of conserving pristine boreal peatlands, and when restoring peatlands that have experienced peatland drainage and mining. © 2020 The Author(s). Published by IOP Publishing Ltd. (Less)

Recent warming in the Arctic, which has been amplified during the winter1-3, greatly enhances microbial decomposition of soil organic matter and subsequent release of carbon dioxide (CO2)4. However, the amount of CO2 released in winter is highly uncertain and has not been well represented by ecosystem models or by empirically-based estimates5,6. Here we synthesize regional in situ observations of CO2 flux from arctic and boreal soils to assess current and future winter carbon losses from the northern permafrost domain. We estimate a contemporary loss of 1662 Tg C yr-1 from the permafrost region during the winter season (October through April). This loss is greater than the average growing season carbon uptake for this region estimated from process models (-1032 Tg C yr-1). Extending model predictions to warmer conditions in 2100 indicates that winter CO2 emissions will increase 17% under a moderate mitigation scenario-Representative Concentration Pathway (RCP) 4.5-and 41% under business-as-usual emissions scenario-RCP 8.5. Our results provide a new baseline for winter CO2 emissions from northern terrestrial regions and indicate that enhanced soil CO2 loss due to winter warming may offset growing season carbon uptake under future climatic conditions.

Abstract. Natural wetlands constitute the largest and most uncertain source of methane (CH4) to the atmosphere and a large fraction of them are found in the northern latitudes. These emissions are typically estimated using process (“bottom-up”) or inversion (“top-down”) models. However, estimates from these two types of models are not independent of each other since the top-down estimates usually rely on the a priori estimation of these emissions obtained with process models. Hence, independent spatially explicit validation data are needed. Here we utilize a random forest (RF) machine-learning technique to upscale CH4 eddy covariance flux measurements from 25 sites to estimate CH4 wetland emissions from the northern latitudes (north of 45∘ N). Eddy covariance data from 2005 to 2016 are used for model development. The model is then used to predict emissions during 2013 and 2014. The predictive performance of the RF model is evaluated using a leave-one-site-out cross-validation scheme. The performance (Nash–Sutcliffe model efficiency =0.47) is comparable to previous studies upscaling net ecosystem exchange of carbon dioxide and studies comparing process model output against site-level CH4 emission data. The global distribution of wetlands is one major source of uncertainty for upscaling CH4. Thus, three wetland distribution maps are utilized in the upscaling. Depending on the wetland distribution map, the annual emissions for the northern wetlands yield 32 (22.3–41.2, 95 % confidence interval calculated from a RF model ensemble), 31 (21.4–39.9) or 38 (25.9–49.5) Tg(CH4) yr−1. To further evaluate the uncertainties of the upscaled CH4 flux data products we also compared them against output from two process models (LPX-Bern and WetCHARTs), and methodological issues related to CH4 flux upscaling are discussed. The monthly upscaled CH4 flux data products are available at https://doi.org/10.5281/zenodo.2560163 (Peltola et al., 2019).