Estimating Global GPP From the Plant Functional Type Perspective Using a Machine Learning Approach

The long‐term monitoring of gross primary production (GPP) is crucial to the assessment of the carbon cycle of terrestrial ecosystems. In this study, a well‐known machine learning model (random forest, RF) is established to reconstruct the global GPP data set named ECGC_GPP. The model distinguished nine functional plant types, including C3 and C4 crops, using eddy fluxes, meteorological variables, and leaf area index (LAI) as training data of RF model. Based on ERA5_Land and the corrected GEOV2 data, global monthly GPP data set at a 0.05° resolution from 1999 to 2019 was estimated. The results showed that the RF model could explain 74.81% of the monthly variation of GPP in the testing data set, of which the average contribution of LAI reached 41.73%. The average annual and standard deviation of GPP during 1999–2019 were 117.14 ± 1.51 Pg C yr−1, with an upward trend of 0.21 Pg C yr−2 (p < 0.01). By using the plant functional type classification, the underestimation of cropland is improved. Therefore, ECGC_GPP provides reasonable global spatial pattern and long‐term trend of annual GPP.

[1]  H. Dolman,et al.  Land Management Explains the Contrasting Greening Pattern Across China‐Russia Border Based on Paired Land Use Experiment Approach , 2022, Journal of Geophysical Research: Biogeosciences.

[2]  Irene E. Teubner,et al.  VODCA2GPP – a new, global, long-term (1988–2020) gross primary production dataset from microwave remote sensing , 2022, Earth System Science Data.

[3]  Tiexi Chen,et al.  A Framework to Assess the Potential Uncertainties of Three FPAR Products , 2021, Journal of Geophysical Research: Biogeosciences.

[4]  J. Thepaut,et al.  Supplementary material to "ERA5-Land: A state-of-the-art global reanalysis dataset for land applications" , 2021, Earth System Science Data.

[5]  S. Piao,et al.  Worldwide impacts of atmospheric vapor pressure deficit on the interannual variability of terrestrial carbon sinks , 2021, National science review.

[6]  B. Fu,et al.  Accelerated increase in vegetation carbon sequestration in China after 2010: A turning point resulting from climate and human interaction , 2021, Global change biology.

[7]  W. Ju,et al.  Tracking the seasonal and inter-annual variations of global gross primary production during last four decades using satellite near-infrared reflectance data. , 2020, The Science of the total environment.

[8]  K. Davis,et al.  Analysis of the 21-years long carbon dioxide flux dataset from a Central European tall tower site , 2020 .

[9]  G. Jia,et al.  Integrating a PhenoCam-derived vegetation index into a light use efficiency model to estimate daily gross primary production in a semi-arid grassland , 2020 .

[10]  Jonas Ardö,et al.  The FLUXNET2015 dataset and the ONEFlux processing pipeline for eddy covariance data , 2020, Scientific Data.

[11]  Yao Zhang,et al.  Performance of four state-of-the-art GPP products (VPM, MOD17, BESS and PML) for grasslands in drought years , 2020, Ecol. Informatics.

[12]  P. Ciais,et al.  Characteristics, drivers and feedbacks of global greening , 2019, Nature Reviews Earth & Environment.

[13]  Atul K. Jain,et al.  Global Carbon Budget 2019 , 2019, Earth System Science Data.

[14]  Atul K. Jain,et al.  Scaling carbon fluxes from eddy covariance sites to globe: synthesis and evaluation of the FLUXCOM approach , 2019, Biogeosciences.

[15]  S. Liang,et al.  Improved estimate of global gross primary production for reproducing its long-term variation, 1982–2017 , 2019, Earth System Science Data.

[16]  Atul K. Jain,et al.  Increased atmospheric vapor pressure deficit reduces global vegetation growth , 2019, Science Advances.

[17]  Roselyne Lacaze,et al.  Harmonization of GEOV2 fAPAR time series through MODIS data for global drought monitoring , 2019, Int. J. Appl. Earth Obs. Geoinformation.

[18]  Josep Peñuelas,et al.  Drought impacts on terrestrial primary production underestimated by satellite monitoring , 2019, Nature Geoscience.

[19]  H. Tani,et al.  Evaluating and comparing remote sensing terrestrial GPP models for their response to climate variability and CO2 trends. , 2019, The Science of the total environment.

[20]  Joachim Denzler,et al.  Deep learning and process understanding for data-driven Earth system science , 2019, Nature.

[21]  Bo Yu,et al.  NPP estimation using random forest and impact feature variable importance analysis , 2019 .

[22]  Christopher B. Field,et al.  Terrestrial gross primary production: Using NIRV to scale from site to globe , 2019, Global change biology.

[23]  Tao Wang,et al.  Spatiotemporal pattern of gross primary productivity and its covariation with climate in China over the last thirty years , 2018, Global change biology.

[24]  D. Qin,et al.  Influence of Vegetation Growth on the Enhanced Seasonality of Atmospheric CO2 , 2018 .

[25]  Jinwei Dong,et al.  A global moderate resolution dataset of gross primary production of vegetation for 2000–2016 , 2017, Scientific Data.

[26]  Ling Zou,et al.  Evaluation of the Latest MODIS GPP Products across Multiple Biomes Using Global Eddy Covariance Flux Data , 2017, Remote. Sens..

[27]  Atul K. Jain,et al.  Compensatory water effects link yearly global land CO2 sink changes to temperature , 2017, Nature.

[28]  Youngryel Ryu,et al.  Multi-scale evaluation of global gross primary productivity and evapotranspiration products derived from Breathing Earth System Simulator (BESS) , 2016 .

[29]  I. C. Prentice,et al.  Recent pause in the growth rate of atmospheric CO2 due to enhanced terrestrial carbon uptake , 2016, Nature Communications.

[30]  Simon F. B. Tett,et al.  Global evaluation of gross primary productivity in the JULES land surface model v3.4.1 , 2016 .

[31]  Markus Reichstein,et al.  Predicting carbon dioxide and energy fluxes across global FLUXNET sites with regression algorithms , 2016 .

[32]  L. Guanter,et al.  Consistency Between Sun-Induced Chlorophyll Fluorescence and Gross Primary Production of Vegetation in North America , 2016 .

[33]  Xing Chen,et al.  Advantages of Using Microwave Satellite Soil Moisture over Gridded Precipitation Products and Land Surface Model Output in Assessing Regional Vegetation Water Availability and Growth Dynamics for a Lateral Inflow Receiving Landscape , 2016, Remote. Sens..

[34]  Shaoqing Liu,et al.  Evaluating atmospheric CO2 effects on gross primary productivity and net ecosystem exchanges of terrestrial ecosystems in the conterminous United States using the AmeriFlux data and an artificial neural network approach , 2016 .

[35]  Mariana Belgiu,et al.  Random forest in remote sensing: A review of applications and future directions , 2016 .

[36]  Jinwei Dong,et al.  Effects of in-situ and reanalysis climate data on estimation of cropland gross primary production using the Vegetation Photosynthesis Model , 2015 .

[37]  Gustau Camps-Valls,et al.  Uncertainty analysis of gross primary production upscaling using Random Forests, remote sensing and eddy covariance data , 2015 .

[38]  P. Ciais,et al.  Spatiotemporal patterns of terrestrial gross primary production: A review , 2015 .

[39]  Atul K. Jain,et al.  The dominant role of semi-arid ecosystems in the trend and variability of the land CO2 sink , 2015, Science.

[40]  W. Oechel,et al.  Improved global simulations of gross primary product based on a new definition of water stress factor and a separate treatment of C3 and C4 plants , 2015 .

[41]  N. Gobron,et al.  Global cropland monthly gross primary production in the year 2000 , 2014 .

[42]  Dan Liu,et al.  Global comparison of light use efficiency models for simulating terrestrial vegetation gross primary production based on the LaThuile database , 2014 .

[43]  Frédéric Baret,et al.  Near Real-Time Vegetation Monitoring at Global Scale , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[44]  Atul K. Jain,et al.  Climate‐driven uncertainties in modeling terrestrial gross primary production: a site level to global‐scale analysis , 2014, Global change biology.

[45]  V. Arora,et al.  The effect of driving climate data on the simulated terrestrial carbon pools and fluxes over North America , 2014 .

[46]  Frédéric Baret,et al.  GEOV1: LAI and FAPAR essential climate variables and FCOVER global time series capitalizing over existing products. Part1: Principles of development and production , 2013 .

[47]  S. Seneviratne,et al.  Climate extremes and the carbon cycle , 2013, Nature.

[48]  M. Lomas,et al.  Evaluation of terrestrial carbon cycle models for their response to climate variability and to CO2 trends , 2013, Global change biology.

[49]  Philippe Ciais,et al.  Terrestrial biosphere model performance for inter‐annual variability of land‐atmosphere CO2 exchange , 2012 .

[50]  A. Arneth,et al.  Global patterns of land-atmosphere fluxes of carbon dioxide, latent heat, and sensible heat derived from eddy covariance, satellite, and meteorological observations , 2011 .

[51]  Tiexi Chen,et al.  Evaluation of cropland maximum light use efficiency using eddy flux measurements in North America and Europe , 2011 .

[52]  Markus Reichstein,et al.  Improving canopy processes in the Community Land Model version 4 (CLM4) using global flux fields empirically inferred from FLUXNET data , 2011 .

[53]  Maosheng Zhao,et al.  Drought-Induced Reduction in Global Terrestrial Net Primary Production from 2000 Through 2009 , 2010, Science.

[54]  F. Woodward,et al.  Terrestrial Gross Carbon Dioxide Uptake: Global Distribution and Covariation with Climate , 2010, Science.

[55]  A. Arneth,et al.  Separation of net ecosystem exchange into assimilation and respiration using a light response curve approach: critical issues and global evaluation , 2010 .

[56]  P. Ciais,et al.  Spatiotemporal patterns of terrestrial carbon cycle during the 20th century , 2009 .

[57]  N. Ramankutty,et al.  Farming the planet: 2. Geographic distribution of crop areas, yields, physiological types, and net primary production in the year 2000 , 2008 .

[58]  W. Cohen,et al.  Evaluation of MODIS NPP and GPP products across multiple biomes. , 2006 .

[59]  Hirofumi Hashimoto,et al.  Modeling the interannual variability and trends in gross and net primary productivity of tropical forests from 1982 to 1999 , 2005 .

[60]  P. Ciais,et al.  Europe-wide reduction in primary productivity caused by the heat and drought in 2003 , 2005, Nature.

[61]  T. Vesala,et al.  On the separation of net ecosystem exchange into assimilation and ecosystem respiration: review and improved algorithm , 2005 .

[62]  Maosheng Zhao,et al.  Improvements of the MODIS terrestrial gross and net primary production global data set , 2005 .

[63]  L. Breiman.  Random Forests , 2001, Encyclopedia of Machine Learning and Data Mining.

[64]  Tin Kam Ho,et al.  The Random Subspace Method for Constructing Decision Forests , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[65]  G. Collatz,et al.  Coupled Photosynthesis-Stomatal Conductance Model for Leaves of C4 Plants , 1992 .