An open workflow for creating machine learning models for estimating the global biospheric CO2 exchange.
Using this workflow we aim to better constrain the CO2 exchange in terrestrial ecosystems on longer timescales using estimates from inverse models (e.g., CarbonTracker) as additional input data.
A more detailed description on the workflow is available on the documentation pages.
The documentation has instructions on;
The workflow itself consists on notebooks (viewable here) that guide you through each step.
This workflow was developed under Netherlands eScience Center grant NLESC.OEC.2022.017.