Accurate estimation of regional-scale terrestrial carbon budgets is of great importance but remains challenging. With particular advantages, the Long Short-Term Memory (LSTM) networks method show potential in improving regional carbon budget upscaling estimations. Here, based on LSTM, we upscale regional net ecosystem carbon exchange (NEE) with available flux tower measurements and satellite land surface observations in North America. With well-established ecosystem-specific LSTMs, we produced monthly NEE at a spatial resolution of 0.1°×0.1° over 2001–2021 (labeled as CROSS2023). Our estimate pointed the largest carbon sink to the Midwest Corn-Belt area during peak growing seasons and to the Southeast on an annual basis, agreeing with empirical knowledges. Moreover, the estimated seasonal variations of NEE by CROSS2023 coincided well with those by atmospheric inversions, i.e., the ensemble mean of Orbiting Carbon Observatory-2 Model Intercomparison Project (OCO-2 v10 MIP; r = 0.95, p < 0.001) and CarbonTracker2022 (CT2022) (r = 0.97, p < 0.001). The mean annual NEE was estimated at -1.27 ± 0.12 Pg C yr-1, aligning more closely with the inversions (-0.70 to -0.63 Pg C yr-1) than with existing upscaling estimates (-3.30 to -1.81 Pg C yr-1). In addition, our estimate plausibly captured the NEE spatial anomalies caused by all the recent extreme drought and flood events. We further confirmed that considering memory effects was critical for better indicating interannual variability and spatial anomalies of NEE induced by climate extremes. This study provides an improved bottom-up estimation of North American NEE, largely narrowing the gap with top-down inversions.

Extreme climate events are becoming more frequent, with poorly understood implications for carbon sequestration by terrestrial ecosystems. A better understanding will critically depend on accurate and precise quantification of ecosystems responses to these events. Taking the 2019 US Midwest floods as a case study, we investigate current capabilities for tracking regional flux anomalies with “top-down” inversion analyses that assimilate atmospheric CO2 observations. For this analysis, we develop a regionally nested version of the NASA Carbon Monitoring System-Flux (CMS-Flux) that allows high resolution atmospheric transport (0.5° × 0.625°) over a North America domain. Relative to a 2018 baseline, we find US Midwest growing season net carbon uptake is reduced by 11-57 TgC (3-16%) for 2019 (inversion mean estimates across experiments). These estimates are found to be consistent with independent “bottom-up” estimates of carbon uptake based on vegetation remote sensing. We then investigate current limitations in tracking regional carbon emissions and removals by ecosystems using “top-down” methods. In a set of observing system simulation experiments, we show that the ability to recover regional carbon flux anomalies is still limited by observational coverage gaps for both in situ and satellite observations. Future space-based missions that allow for daily observational coverage across North America would largely mitigate these observational gaps, allowing for improved top-down estimates of ecosystem responses to extreme climate events.

Solar-induced fluorescence (SIF) shows enormous promise as a proxy for photosynthesis and as a tool for modeling variability in gross primary productivity (GPP) and net biosphere exchange (NBE). In this study, we explore the skill of SIF and other vegetation indicators in predicting variability in global atmospheric CO2 observations, and thus global variability in NBE. We do so using a four-year record of global CO2 observations from NASA’s Orbiting Carbon Observatory 2 (OCO-2) satellite and using a geostatistical inverse model. We find that existing SIF products closely correlate with space-time variability in atmospheric CO2 observations in the extra-tropics but show weaker explanatory power across the tropics. In the extra-tropics, all SIF products exhibit greater skill in explaining variability in atmospheric CO2 observations compared to an ensemble of process-based CO2 flux models and other vegetation indicators. Furthermore, we find that using SIF as a predictor variable in the geosatistical inverse model shifts the seasonal cycle of estimated NBE and yields an earlier end to the growing season relative to other vegetation indicators. In tropical biomes, by contrast, the seasonal cycles of SIF products and estimated NBE are out of phase, and existing respiration and biomass burning estimates do not reconcile this discrepancy. Overall, our results highlight several advantages and challenges of using SIF products to help predict global variability in GPP and NBE.