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

• Published in: Geophysical Research Letters
• Main Authors: Norbert Pirk, Kristoffer Aalstad, Erik Schytt Mannerfelt, François Clayer, Heleen deWit, Casper T. Christiansen, Inge Althuizen, Hanna Lee, Sebastian Westermann
• Format: Article in Journal/Newspaper
• Language: English
• Published: Wiley 2024
• Subjects: carbon fluxes; permafrost degradation; Bayesian neural networks; Geophysics. Cosmic physics; QC801-809; Northern Norway; palsa; palsas; permafrost; Thermokarst
• Online Access: https://doi.org/10.1029/2024GL109283; https://doaj.org/article/4bf78196abe743629c83cefeb4b0ac04

Abstract 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.