Global Change Biology · 2022 · 36 citations · 44 references
Natural SciencesEarth SciencesEnvironmental SciencesClimate ScienceClimatologyTerrestrial EcologyCarbon CycleCarbon Cycle VariabilityCarbon SequestrationClimate ChangeEcosystem RespirationPermafrostCarbon DioxideClimate Feedback MechanismsField ObservationsPermafrost Carbon FeedbacksPermafrost Carbon LossPermafrost Carbon ReleasePermafrost Greenhouse Gas ReleaseSoil Respiration Modeling
Abstract One of the major uncertainties for projecting permafrost carbon (C)‐climate feedback is a poor representation of the non‐growing season carbon dioxide (CO 2 ) emissions under a changing climate. Here, combining in situ field observations, regional synthesis and a random forest model, we assessed contemporary and future soil respired CO 2 (i.e., soil respiration, R s ) across the Tibetan alpine permafrost region, which has received much less attention compared with the Arctic permafrost domain. We estimated the regional mean R s of 229.8, 72.9 and 302.7 g C m −2 year −1 during growing season, non‐growing season and the entire year, respectively; corresponding to the contemporary losses of 296.9, 94.3 and 391.2 Tg C year −1 from this high‐altitude permafrost‐affected area. The non‐growing season R s accounted for a quarter of the annual soil CO 2 efflux. Different from the prevailing view that temperature is the most limiting factor for cold‐period CO 2 release in Arctic permafrost ecosystems, precipitation determined the spatial pattern of non‐growing season R s on the Tibetan Plateau. Using the key predictors, model extrapolation demonstrated additional losses of 38.8 and 74.5 Tg C from the non‐growing season for a moderate mitigation scenario and a business‐as‐usual emissions scenario, respectively. These results provide a baseline for non‐growing season CO 2 emissions from high‐altitude permafrost areas and help for accurate projection of permafrost C‐climate feedback.
44
Leo Breiman · Machine Learning · 2001 · 126.2K citations · Full text
Scikit-learn: Machine Learning in Python
Fabián Pedregosa, Gaël Varoquaux, Alexandre Gramfort et al. · arXiv (Cornell University) · 2012 · 63.7K citations · Full text
Scikit-learn: Machine Learning in Python
PedregosaFabian, VaroquauxGaël, GramfortAlexandre et al. · Journal of Machine Learning Research · 2011 · 8.2K citations
Permafrost is warming at a global scale
Boris K. Biskaborn, Sharon L. Smith, Jeannette Noetzli et al. · Nature Communications · 2019 · 2.1K citations · Full text
Natural Sciences, Earth Sciences, Environmental Sciences +17