Estimating Global Gross Primary Production from Sun-Induced Chlorophyll Fluorescence Data and Auxiliary Information Using Machine Learning Methods

Abstract

The gross primary production (GPP) is important for regulating the global carbon cycle and climate change. Recent studies have shown that sun-induced chlorophyll fluorescence (SIF) is highly advantageous regarding GPP monitoring. However, using SIF to estimate GPP on a global scale is limited by the lack of a stable SIF-GPP relationship. Here, we estimated global monthly GPP at 0.05° spatial resolution for the period 2001–2017, using the global OCO-2-based SIF product (GOSIF) and other auxiliary data. Large amounts of flux tower data are not available to the public and the available data is not evenly distributed globally and has a smaller measured footprint than the GOSIF data. This makes it difficult to use the flux tower GPP directly as an input to the model. Our strategy is to scale in situ measurements using two moderate-resolution satellite GPP products (MODIS and GLASS). Specifically, these two satellite GPP products were calibrated and eventually integrated by in situ measurements (FLUXNET2015 dataset, 83 sites), which was then used to train a machine learning model (GBRT) that performed the best among five evaluated models. The GPP estimates from GOSIF were highly accurate coefficient of determination (R2) = 0.58, root mean square error (RMSE) = 2.74 g C·m−2, bias = –0.34 g C·m−2) as validated by in situ measurements, and exhibited reasonable spatial and seasonal variations on a global scale. Our method requires fewer input variables and has higher computational efficiency than other satellite GPP estimation methods. Satellite-based SIF data provide a unique opportunity for more accurate, near real-time GPP mapping in the future.

Revisiting the cumulative effects of drought on global gross primary productivity based on new long‐term series data (1982–2018)

“…The spatial resolution of the NIRv‐GPP is 0.05°. Recent studies have indicated the excellence of the NIRv‐GPP (Bai et al, 2021; Wang et al, 2020). This data set was downloaded from the National Tibetan Plateau Data Center (http://data.tpdc.ac.cn).…”

Different Satellite Products Revealing Variable Trends in Global Gross Primary Production

“…The Moderate Resolution Imaging Spectroradiometer (MODIS) GPP is widely used for global and regional change analysis because of its continuous estimation (Chen et al., 2019; Ding et al., 2020; Jiao et al., 2021). Although MODIS collection 6 (C6) GPP has resolved the problem of aging of sensors (Lyapustin et al., 2014), it currently remains some controversy regarding the use of MODIS GPP; for example, it underestimates the vegetation GPP (Bai et al., 2021; Du et al., 2018; Qiu et al., 2020; Zhang et al., 2017). In addition, Zhang et al.…”

“…numerous models have been developed to simulate GPP (e.g., light energy use efficiency (LUE) models and process-based models), and several global GPP products have been derived (Bai et al, 2021;Jiang & Ryu, 2016;Jung et al, 2011;Running et al, 2015;Tagesson et al, 2021;Tramontana et al, 2016;Wang et al, 2021;Yuan et al, 2010;Zhang et al, 2017). For example, the Global LAnd Surface Satellite (GLASS) GPP is a long-time series, high accuracy, global surface GPP product derived from multi-source data and ground-based observations (Yuan et al, 2007(Yuan et al, , 2010.…”

“…The Moderate Resolution Imaging Spectroradiometer (MODIS) GPP is widely used for global and regional change analysis because of its continuous estimation (Chen et al, 2019;Ding et al, 2020;Jiao et al, 2021). Although MODIS collection 6 (C6) GPP has resolved the problem of aging of sensors (Lyapustin et al, 2014), it currently remains some controversy regarding the use of MODIS GPP; for example, it underestimates the vegetation GPP (Bai et al, 2021;Du et al, 2018;Qiu et al, 2020;Zhang et al, 2017). In addition, Zhang et al (2017) developed a vegetation photosynthesis model (VPM) based on the improved LUE theory which used the energy absorbed by chlorophyll and also produced a global GPP product, which showed good performance when compared with ground observation data.…”

Use of auxiliary information in estimation of the finite population mean: An exponential type of estimator

“…The use of auxiliary information to enhance the performance of estimation procedures is well documented in the statistical and allied sciences literature, see for example, Zhang and Chambers (2004), Chou et al (2017) and Bai et al (2021). In practice auxiliary information is obtainable from various sources, such as census, survey reports and expert opinion, see also Rao et al (1990) and Biemer and Peytchev (2013).…”