Disaggregating the Carbon Exchange of Degrading Permafrost Peatlands Using Bayesian Deep Learning.

Extensive regions in the permafrost zone are projected to become climatically unsuitable to sustain permafrost peatlands over the next century, suggesting transformations in these landscapes that can leave large amounts of permafrost carbon vulnerable to post‐thaw decomposition. We present 3 years of eddy covariance measurements of CH4 and CO2 fluxes from the degrading permafrost peatland Iškoras in Northern Norway, which we disaggregate into separate fluxes of palsa, pond, and fen areas using information provided by the dynamic flux footprint in a novel ensemble‐based Bayesian deep neural network framework. The 3‐year mean CO2‐equivalent flux is estimated to be 106 gCO2 m−2 yr−1 for palsas, 1,780 gCO2 m−2 yr−1 for ponds, and −31 gCO2 m−2 yr−1 for fens, indicating that possible palsa degradation to thermokarst ponds would strengthen the local greenhouse gas forcing by a factor of about 17, while transformation into fens would slightly reduce the current local greenhouse gas forcing. Plain Language Summary: Arctic and sub‐arctic regions on the southern border of the permafrost zone often feature peatlands with a patchy surface of peat mounds, thaw ponds, and surrounding fens. As the permafrost underneath peat mounds thaws, these areas transform and can change their emission or uptake of greenhouse gases like CO2 and methane. Assessing this gas exchange on the patchy surface is difficult because our measurement techniques cannot directly observe the variability in space and time. We collected 3 years of gas exchange measurements at a Norwegian permafrost peatland and developed a new method using a collection of uncertainty‐aware neural networks to predict the greenhouse gas exchange of different surface types. Our work suggests that large amounts of methane are emitted by ponds and fens, while the elevated peat mounds have almost no methane emissions. For CO2, we see that ponds are strong emitters, while fens take up substantial amounts as their vegetation absorbs this gas. We are still unsure when the peat mounds will collapse and if they turn into ponds or fens, but we can say that pond formation would give a 17 fold increase in greenhouse gas emissions, while fen formation would slightly reduce today's emissions of permafrost peatlands. Key Points: Eddy covariance fluxes are disaggregated for different surfaces using Bayesian neural networks to derive uncertainty‐aware carbon balancesWhile palsa areas have a near‐zero annual methane balance, the fens and ponds that form upon palsa degradation emit large amounts of methaneFens compensate for methane emissions with strong annual CO2 sinks, while ponds appear as strong, yet uncertain, CO2 emission hotspots [ABSTRACT FROM AUTHOR]