Estimation of net ecosystem carbon exchange at climate sites by combing remote sensing data and FLUXNET2015 data with machine learning algorithms

The Eddy Covariance (EC) flux stations have great limitations in the evaluation of the global Net ecosystem carbon exchange (NEE) and in the uncertainty reduction due to their sparse and uneven distribution and spatial representation. If the EC stations are linked with widely distributed meteorological stations using machine learning (ML) and remote sensing, it will play a big role in effectively improving the accuracy of the global NEE assessment and reducing the uncertainty. In this study, we first optimized the hyperparameters and input variables of the ML model based on the adaptive genetic algorithm. Then, we developed 566 random forest (RF)-based NEE estimation models by the strategy of spatial leave-out-one cross- validation (SLOOCV). We innovatively established the Euclidean distance-based accuracy projection algorithm of the R square (R2), which could test the accuracy for each model to estimate the NEE of the specific flux at the weather station. Only the model with the highest R2 was selected from the models with a prediction accuracy of R2>0.5 for the specific meteorological stations to estimate its NEE. 4,674 out of 10,289 weather stations around the world might match at least one of the 566 NEE estimation models with a projected accuracy of R2 > 0.5. The NEE estimation models we screened for the meteorological stations showed a reliable performance and a higher accuracy than former studies. The NEE values of the most (96.9%) screened meteorological stations around the world are negative (carbon sink) and most (65.3%) of those showed an increasing trend in the mean annual NEE (carbon sink). The FLUXCOM NEE estimation denoted larger values than our estimations at the corresponding meteorological stations. The NEE dataset produced at the meteorological stations could be used as a supplement to the EC observations and quasi-observation data to assess the NEE products of the global grid. The results of this work will provide theoretical and technical support for the climate change policy formulation and the terrestrial carbon sink assessments.