R-code for random forest models related to article 'Arctic soil methane sink increases with drier conditions and higher ecosystem respiration'
Creators
- 1. University of Eastern Finland, Universität Hamburg
- 2. University of Eastern Finland
Description
This folder contains two R-script to create Random Forest (RF) models that can be used to reproduce RF model outputs reported in the following article:
Voigt, C., Virkkala, A.-M., Hould Gosselin, G., Bennett, K.A., Black, T.A., Detto, M., Chevrier-Dion, C., Guggenberger, G., Hashmi, W., Kohl, L., Kou, D., Marquis, C., Marsh, P., Marushchak, M.E., Nesic, Z., Nykänen, H., Saarela, T., Sauheitl, L., Walker, B., Weiss, N., Wilcox, E.J., Sonnentag, O. (2023). Arctic soil methane sink increases with drier conditions and higher ecosystem respiration. Nature Climate Change. DOI: 10.1038/s41558-023-01785-3 [in press].
The flux datasets used in this script are available on PANGAEA database under the following DOI: https://doi.org/10.1594/PANGAEA.953120
Example datasets (.csv) with a subset of data are included with these R-scripts.
Please cite our work accordingly when using this script or associated data.
Script 1: RF models for all vegetation types at Trail Valley Creek, split between Shrub, Lichen, and Tussock
Script 2: RF models for individual chambers (18 chambers) at Trail Valley Creek, split by month (June, July, August).
Files
CH4_2019-21_summary_v3_mgCH4_forRandomForest_all-data.csv
Additional details
Related works
- Is cited by
- Journal article: 10.1038/s41558-023-01785-3 (DOI)
- References
- Dataset: 10.1594/PANGAEA.953120 (DOI)
Funding
- Methane uptake by permafrost-affected soils – an underestimated carbon sink in Arctic ecosystems? (MUFFIN) 332196
- Academy of Finland