Articles | Volume 20, issue 4
https://doi.org/10.5194/bg-20-897-2023
https://doi.org/10.5194/bg-20-897-2023
Research article
 | 
02 Mar 2023
Research article |  | 02 Mar 2023

Spatiotemporal lagging of predictors improves machine learning estimates of atmosphere–forest CO2 exchange

Matti Kämäräinen, Juha-Pekka Tuovinen, Markku Kulmala, Ivan Mammarella, Juha Aalto, Henriikka Vekuri, Annalea Lohila, and Anna Lintunen

Model code and software

Gradient boosting and random forest tools for modeling the NEE M. Kämäräinen, A. Lintunen, M. Kulmala, J. Tuovinen, I. Mammarella, J. Aalto, H. Vekuri, and A. Lohila https://doi.org/10.5281/zenodo.7333975

Download
Short summary
In this study, we introduce a new method for modeling the exchange of carbon between the atmosphere and a study site located in a boreal forest in southern Finland. Our method yields more accurate results than previous approaches in this context. Accurately estimating carbon exchange is crucial for gaining a better understanding of the role of forests in regulating atmospheric carbon and addressing climate change.
Altmetrics
Final-revised paper
Preprint