文献类型：期刊文献

英文题名：Memory effects of climate and vegetation affecting net ecosystem CO2 fluxes in global forests

作者：Besnard, Simon[1,2] Carvalhais, Nuno[1,3] Arain, M. Altaf[4,5] Black, Andrew[6] Brede, Benjamin[2] Buchmann, Nina[7] Chen, Jiquan[8] Clevers, Jan G. P. W.[2] Dutrieux, Loic P.[9] Gans, Fabian[1] Herold, Martin[2] Jung, Martin[1] Kosugi, Yoshiko[10] Knohl, Alexander[11] Law, Beverly E.[12] Paul-Limoges, Eugenie[7] Lohila, Annalea[13] Merbold, Lutz[14] Roupsard, Olivier[15,16] Valentini, Riccardo[17] Wolf, Sebastian[18] Zhang, Xudong[19] Reichstein, Markus[1]

第一作者：Besnard, Simon

通信作者：Besnard, S[1];Besnard, S[2]

机构：[1]Max Planck Inst Biochem, Dept Biogeochem Integrat, Jena, Germany;[2]Wageningen Univ, Lab Geoinformat Sci & Remote Sensing, Wageningen, Netherlands;[3]Univ Nova Lisboa, Fac Ciencias & Tecnol, Dept Ciencias & Engn Ambiente, CENSE, Caparica, Portugal;[4]McMaster Univ, Sch Geog & Earth Sci, Hamilton, ON, Canada;[5]McMaster Univ, McMaster Ctr Climate Change, Hamilton, ON, Canada;[6]Univ British Columbia, Fac Land & Food Syst, Vancouver, BC, Canada;[7]Swiss Fed Inst Technol, Dept Environm Syst Sci, Zurich, Switzerland;[8]Michigan State Univ, CGCEO Geog, E Lansing, MI 48824 USA;[9]Natl Commiss Knowledge & Use Biodivers CONABIO, Mexico City, DF, Mexico;[10]Kyoto Univ, Grad Sch Agr, Lab Forest Hydrol, Kyoto, Japan;[11]Univ Goettingen, Fac Forest Sci, Gottingen, Germany;[12]Oregon State Univ, Coll Forestry, Corvallis, OR 97331 USA;[13]Finnish Meteorol Inst, Helsinki, Finland;[14]ILRI, Mazingira Ctr, Nairobi, Kenya;[15]CIRAD, UMR Eco&Sols, LMI IESOL, Dakar, Senegal;[16]Univ Montpellier, Montpellier SupAgro, CIRAD, INRA,IRD,Eco&Sols, Montpellier, France;[17]Univ Tuscia, Dept Innovat Biol Agrofood & Forest Syst DIBAF, Viterbo, Italy;[18]Swiss Fed Inst Technol, Dept Environm Syst Sci, Phys Environm Syst, Zurich, Switzerland;[19]Chinese Acad Forestry, Res Inst Forestry, Beijing, Peoples R China

年份：2019

卷号：14

期号：2

外文期刊名：PLOS ONE

收录：;WOS:【SCI-EXPANDED(收录号:WOS:000457874000068)】；

语种：英文

摘要：Forests play a crucial role in the global carbon (C) cycle by storing and sequestering a substantial amount of C in the terrestrial biosphere. Due to temporal dynamics in climate and vegetation activity, there are significant regional variations in carbon dioxide (CO2) fluxes between the biosphere and atmosphere in forests that are affecting the global C cycle. Current forest CO2 flux dynamics are controlled by instantaneous climate, soil, and vegetation conditions, which carry legacy effects from disturbances and extreme climate events. Our level of understanding from the legacies of these processes on net CO2 fluxes is still limited due to their complexities and their long-term effects. Here, we combined remote sensing, climate, and eddy-covariance flux data to study net ecosystem CO2 exchange (NEE) at 185 forest sites globally. Instead of commonly used non-dynamic statistical methods, we employed a type of recurrent neural network (RNN), called Long Short-Term Memory network (LSTM) that captures information from the vegetation and climate's temporal dynamics. The resulting data-driven model integrates interannual and seasonal variations of climate and vegetation by using Landsat and climate data at each site. The presented LSTM algorithm was able to effectively describe the overall seasonal variability (Nash-Sutcliffe efficiency, NSE = 0.66) and across-site (NSE = 0.42) variations in NEE, while it had less success in predicting specific seasonal and interannual anomalies (NSE = 0.07). This analysis demonstrated that an LSTM approach with embedded climate and vegetation memory effects outperformed a non-dynamic statistical model (i.e. Random Forest) for estimating NEE. Additionally, it is shown that the vegetation mean seasonal cycle embeds most of the information content to realistically explain the spatial and seasonal variations in NEE. These findings show the relevance of capturing memory effects from both climate and vegetation in quantifying spatio-temporal variations in forest NEE.