Upscaling Net Ecosystem Exchange Over Heterogeneous Landscapes With Machine Learning

This paper discusses different feature selection methods and CO2 flux data sets with a varying quality-quantity balance for the application of a Random Forest model to predict daily CO2 fluxes at 250 m spatial resolution for the Rur catchment area in western Germany between 2010 and 2018. Measurements from eddy covariance stations of different ecosystem types, remotely sensed vegetation data from MODIS, and COSMO-REA6 reanalysis data were used to train the model and predictions were validated by a spatial and temporal validation scheme. Results show the capabilities of a backwards feature elimination to remove irrelevant variables and an importance of high-quality-low-quantity flux data set to improve predictions. However, results also show that spatial prediction is more difficult than temporal prediction by reflecting the mean value accurately though underestimating the variance of CO2 fluxes. Vegetated parts of the catchment acted as a CO2 sink during the investigation period, net capturing about 237 g C m(-2) y(-1). Croplands, coniferous forests, deciduous forests and grasslands were all sinks on average. The highest uptake was predicted to occur in late spring and early summer, while the catchment was a CO2 source in fall and winter. In conclusion, the Random Forest model predicted a narrower distribution of CO2 fluxes, though our methodological improvements look promising in order to achieve high-resolution net ecosystem exchange data sets at the regional scale.

Automated summary

This study explores different feature selection methods and CO2 flux datasets to predict daily CO2 fluxes using a Random Forest model. While backward feature elimination was effective in removing irrelevant variables, high-quality-low-quantity flux datasets were important for improving predictions. Spatial prediction was more challenging than temporal prediction, with the model underestimating the variance of CO2 fluxes. Despite difficulties, the Random Forest model showed promise for predicting CO2 fluxes at a high spatial resolution.