A Study on Inferring Daytime Variations of XCO 2 ${\text{XCO}}_{2}$ From Current and Future Space-Based Missions

Net ecosystem exchange (NEE) measures the net transfer of carbon between terrestrial ecosystems and the atmosphere, and is an important quantity for understanding land-atmosphere feedbacks and constraining the land carbon sink. Atmospheric inverse models and biophysical models provide regional and global net ecosystem exchange (NEE) estimates, but validation of these models is limited by the sparsity of flux towers. NEE can also be calculated from the change in ${\text{XCO}}_2$ over the course of a day. ${\text{XCO}}_2$ is observed by the Orbiting Carbon Observatory 2 and 3 (OCO-2 and -3) satellites, which working together have the potential to observe locations between $\sim$52°S and 52°N twice a day but at a sparse temporal frequency. Here, we investigate the possibility of using machine learning (ML) to extrapolate the variation in ${\text{XCO}}_2$ over daytime hours, which could be in turn be used to derive NEE. We find that the current temporal sampling from OCO-2 and -3 is not ideal for this purpose, and our ML approach is not able to reliably infer either the daily patterns of ${\text{XCO}}_2$ or the difference of ${\text{XCO}}_2$ across solar noon. A thrice-daily observation pattern, such as could be achieved with a GeoCarb-like (geosynchronous) instrument, provides much better performance. It is also essential that systematic biases between observations at different times of day be minimized, as the ability to predict daily variation or morning to afternoon differences decreases when the standard error between the means of observations at different times of day exceeds $\sim$0.1 ppm.