Methane flux (FCH4) measurements using the eddy covariance technique have increased over the past decade. FCH4 measurements commonly include data gaps, as is the case with CO2 and energy fluxes. However, gap‐filling FCH4 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 FCH4 datasets, and others have applied artificial neural networks (ANN) to resolve the challenging characteristics of FCH4. However, there is still no consensus regarding FCH4 gap‐filling methods due to limited comparative research. We are not aware of the applications of machine learning (ML) algorithms beyond ANN to FCH4 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 FCH4 and reduce the internal complexity of the algorithmic structures. We applied this approach to five benchmark FCH4 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 CH4 budget. Therefore, the approach used for FCH4 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.

Soil respiration (Rs) represents the largest flux of CO2 from terrestrial ecosystems to the atmosphere, but its spatial and temporal changes as well as the driving forces are not well understood. We derived a product of annual global Rs from 2000 to 2014 at 1 km by 1 km spatial resolution using remote sensing data and biome-specific statistical models. Different from the existing view that climate change dominated changes in Rs, we showed that land-cover change played a more important role in regulating Rs changes in temperate and boreal regions during 2000–2014. Significant changes in Rs occurred more frequently in areas with significant changes in short vegetation cover (i.e., all vegetation shorter than 5 m in height) than in areas with significant climate change. These results contribute to our understanding of global Rs patterns and highlight the importance of land-cover change in driving global and regional Rs changes.

Abstract. Many peatlands have been drained and harvested for peat mining, agriculture, and other purposes, which has turned them from carbon (C) sinks into C emitters. Rewetting of disturbed peatlands facilitates their ecological recovery and may help them revert to carbon dioxide (CO 2 ) sinks. However, rewetting may also cause substantial emissions of the more potent greenhouse gas (GHG) methane (CH 4 ). Our knowledge of the exchange of CO 2 and CH 4 following rewetting during restoration of disturbed peatlands is currently limited. This study quantifies annual fluxes of CO 2 and CH 4 in a disturbed and rewetted area located in the Burns Bog Ecological Conservancy Area in Delta, BC, Canada. Burns Bog is recognized as the largest raised bog ecosystem on North America's west coast. Burns Bog was substantially reduced in size and degraded by peat mining and agriculture. Since 2005, the bog has been declared a conservancy area, with restoration efforts focusing on rewetting disturbed ecosystems to recover Sphagnum and suppress fires. Using the eddy covariance (EC) technique, we measured year-round (16 June 2015 to 15 June 2016) turbulent fluxes of CO 2 and CH 4 from a tower platform in an area rewetted for the last 8 years. The study area, dominated by sedges and Sphagnum, experienced a varying water table position that ranged between 7.7 (inundation) and −26.5 cm from the surface during the study year. The annual CO 2 budget of the rewetted area was −179 ± 26.2 g CO 2 -C m −2 yr −1 (CO 2 sink) and the annual CH 4 budget was 17 ± 1.0 g CH 4 -C m −2 yr −1 (CH 4 source). Gross ecosystem productivity (GEP) exceeded ecosystem respiration (R e ) during summer months (June-August), causing a net CO 2 uptake. In summer, high CH 4 emissions (121 mg CH 4 -C m −2 day −1 ) were measured. In winter (December-February), while roughly equal magnitudes of GEP and R e made the study area CO 2 neutral, very low CH 4 emissions (9 mg CH 4 -C m −2 day −1 ) were observed. The key environmental factors controlling the seasonality of these exchanges were downwelling photosynthetically active radiation and 5 cm soil temperature. It appears that the high water table caused by ditch blocking suppressed R e . With low temperatures in winter, CH 4 emissions were more suppressed than R e . Annual net GHG flux from CO 2 and CH 4 expressed in terms of CO 2 equivalents (CO 2 eq.) during the study period totalled −22 ± 103.1 g CO 2 eq. m −2 yr −1 (net CO 2 eq. sink) and 1248 ± 147.6 g CO 2 eq. m −2 yr −1 (net CO 2 eq. source) by using 100-and 20-year global warming potential values, respectively. Consequently, the ecosystem was almost CO 2 eq. neutral during the study period expressed on a 100-year time horizon but was a significant CO 2 eq. source on a 20-year time horizon.

<p><strong>Abstract.</strong> Many peatlands have been drained and harvested for peat mining, which has turned them from carbon (C) sinks into C emitters. Rewetting of disturbed peatlands facilitates their ecological recovery, and may help them revert to carbon dioxide (CO<sub>2</sub>) sinks. However, rewetting may also cause substantial emissions of the more potent greenhouse gas (GHG) methane (CH<sub>4</sub>). Our knowledge on the exchange of CO<sub>2</sub> and CH<sub>4</sub> following rewetting during restoration of disturbed peatlands is currently limited. This study quantifies annual fluxes of CO<sub>2</sub> and CH<sub>4</sub> in a disturbed and rewetted area located in the Burns Bog Ecological Conservancy Area in Delta, BC, Canada. Burns Bog is recognized as the largest raised bog ecosystem on North America's West Coast. Burns Bog was substantially reduced in size and degraded by peat mining and agriculture. Since 2005, the bog has been declared a conservancy area, with restoration efforts focusing on rewetting disturbed ecosystems to recover Sphagnum and suppress fires. Using the eddy-covariance (EC) technique, we measured year-round (16<sup>th</sup> June 2015 to 15<sup>th</sup> June 2016) turbulent fluxes of CO<sub>2</sub> and CH<sub>4</sub> from a tower platform in an area rewetted for the last 8 years. The study area, dominated by sedges and Sphagnum, experienced a varying water table position that ranged between 7.7 (inundation) and −26.5 cm from the surface during the study year. The annual CO<sub>2</sub> budget of the rewetted area was −179 g CO<sub>2</sub>-C m<sup>−2</sup> year<sup>−1</sup> (CO<sub>2</sub> sink) and the annual CH<sub>4</sub> budget was 16 g CH<sub>4</sub>-C m<sup>−2</sup> year<sup>−1</sup> (CH<sub>4</sub> source). Gross ecosystem productivity (GEP) exceeded ecosystem respiration (Re) during summer months (June–August), causing a net CO<sub>2</sub> uptake. In summer, high CH<sub>4</sub> emissions (121 mg CH<sub>4</sub>-C m<sup>−2</sup> day<sup>−1</sup>) were measured. In winter (December–February), while roughly equal magnitudes of GEP and Re made the study area CO<sub>2</sub> neutral, very low CH<sub>4</sub> emissions (9 mg CH<sub>4</sub>-C m<sup>−2</sup> day<sup>−1</sup>) were observed. The key environmental factors controlling the seasonality of these exchanges were downwelling photosynthetically active radiation and 5-cm soil temperature. It appears that the high water table caused by ditch blocking which suppresses Re. With low temperatures in winter, CH<sup>4</sup> emission was more suppressed than Re. Annual net GHG flux from CO<sub>2</sub> and CH<sub>4</sub> expressed in terms of CO<sub>2</sub> equivalents (CO<sub>2</sub>e) during the study period totaled to −55 g CO<sub>2</sub>e m<sup>−2</sup> year<sup>−1</sup> (net CO<sub>2</sub>e sink) and 1147 g CO<sub>2</sub>e m<sup>−2</sup> year<sup>−1</sup> (net CO<sub>2</sub>e source) by using 100-year and 20-year global warming potential values, respectively. Consequently, the ecosystem was almost CO<sub>2</sub>e neutral during the study period expressed on a 100-year time horizon but was a significant CO<sub>2</sub>e source on a 20-year time horizon.</p>

Abstract. The recent mountain pine beetle (MPB) outbreak has had an impact on the carbon (C) cycling of lodgepole pine forests in British Columbia. This study examines how partial harvesting as a forest management response to MPB infestation affects the net ecosystem production (NEP) of a mixed conifer forest (MPB-09) in Interior BC. MPB-09 is a 70-year-old stand that was partially harvested in 2009 after it had been attacked by MPB. Using the eddy-covariance technique, the C dynamics of the stand were studied over two years and compared to an adjacent clear-cut (MPB-09C) over the summertime. The annual NEP at MPB-09 increased from −108 g C m−2 in 2010 to −57 g C m−2 in 2011. The increase of NEP was due to the associated increase in annual gross ecosystem photosynthesis (GEP) from 812 g C m−2 in 2010 to 954 g C m−2 in 2011, exceeding the increase in annual respiration (Re) from 920 g C m−2 to 1011 g C m−2 during the two years. During the four month period between June and September 2010, NEP at MPB-09C was −103 g C m−2, indicating high C losses in the clear-cut. MPB-09 was a C sink during the growing season of both years, increasing from 9 g C m−2 in 2010 to 47 g C m−2 in 2011. The increase of NEP in the partially harvested stand amounted to a recovery corresponding to a 26% increase in the maximum assimilation rate in the second year. This study shows that retaining the healthy residual forest can result in higher C sequestration of MPB-attacked stands compared to clear-cut harvesting.