How management interacts with environmental drivers to control greenhouse gas fluxes from Pacific Northwest coastal wetlands

There is increasing interest in utilizing the high carbon sequestration capacity of wetlands as a rationale for their restoration, but this requires careful assessment of their greenhouse gas (GHG) fluxes. We used a spatially extensive sampling approach across salinity gradients and management regimes (disturbed, restored, and reference) in 22 wetland sites across two Oregon, USA estuaries, Tillamook and Coos Bays, to measure fluxes of methane (CH 4 ), ecosystem respiration as carbon dioxide (CO 2 ), and nitrous oxide (N 2 O) over 1 year and related them to environmental forcing variables. Boosted regression tree (BRT) models explained drivers of GHG fluxes reasonably well despite highly nonlinear and interactive relationships and many flux measurements below detection. We used the BRT models to predict annual GHG fluxes in a subset of restored and reference sites where continuous environmental data were recorded and compared them to previously published soil carbon sequestration rates. Most sites had net removal of CO 2 -equivalents from the atmosphere over both 20 and 100 year timeframes. Our results show that a spatially extensive GHG flux sampling scheme and machine-learning statistical techniques can be used to estimate GHG fluxes in other current and former wetlands within the region if environmental data are collected at a spatial resolution that reflects site variability and at sufficient duration to reflect seasonality (i.e., at least one full year). Such an approach can save time and money in determining the feasibility of wetland restoration as a climate mitigation strategy. We use our results to suggest wetland restoration strategies that optimize climate benefits.