edu.ucar.opensky::articles:43933 UCAR/NCAR - Library OpenSky Support PO Box 3000 Boulder CO 80307-3000 opensky@ucar.edu http://opensky.ucar.edu/ homepage pointOfContact 2025-12-24T17:44:42.875740 ISO 19115-2 Geographic Information - Metadata - Part 2: Extensions for Imagery and Gridded Data ISO 19115-2:2009(E) https://n2t.net/ark:/85065/d7348qwt https://doi.org/10.48364/ISIMIP.842396.1 https Related Dataset #1 ISIMIP3b bias-adjusted atmospheric climate input data https://doi.org/10.5281/zenodo.14230951 https Related PeerReview #1 LPJ-GUESS Forest Carbon Emulator (Data, Models, SHAP values) https://doi.org/10.48550/arXiv.1612.01474 https Related Preprint #1 Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles https://doi.org/10.48550/arXiv.1705.07874 https Related Preprint #2 A Unified Approach to Interpreting Model Predictions https://doi.org/10.5281/zenodo.13989084 https Related Software #1 TensorFlow https://doi.org/10.5281/zenodo.14231373 https Related Software #2 natel-c/lpjg-forestC-emulator: Zenodo https://doi.org/10.5281/zenodo.15065248 https Related Software #3 natel-c/lpjg-modif-emulator: Zenodo Emulating grid-based forest carbon dynamics using machine learning: An LPJ-GUESS v4.1.1 application 2025-07-18T00:00:00Z publication https://n2t.net/ark:/85065/d7348qwt https://doi.org/10.5194/gmd-18-4317-2025 Natel, C. author Belda, D. M. author Anthoni, P. author Haß, N. author Rabin, Sam author Arneth, A. author UCAR/NCAR - Library publisher The assessment of forest-based climate change mitigation strategies relies on computationally intensive scenario analyses, particularly when dynamic vegetation models are coupled with socioeconomic models in multi-model frameworks. In this study, we developed surrogate models for the LPJ-GUESS dynamic global vegetation model to accelerate the prediction of carbon stocks and fluxes, enabling quicker scenario optimization within a multi-model coupling framework. We trained two machine learning methods: random forest and neural network. We assessed and compared the emulators using performance metrics and Shapley-based explanations. Our emulation approach accurately captured global and biome-specific forest carbon dynamics, closely replicating the outputs of LPJ-GUESS for both historical (1850–2014) and future (2015–2100) periods under various climate scenarios. Among the two trained emulators, the neural network extrapolated better at the end of the century for carbon stocks and fluxes and provided more physically consistent predictions, as verified by Shapley values. Overall, the emulators reduced the simulation execution time by 95 %, bridging the gap between complex process-based models and the need for scalable and fast simulations. This offers a valuable tool for scenario analysis in the context of climate change mitigation, forest management, and policy development. UCAR/NCAR - Library OpenSky Support PO Box 3000 Boulder CO 80307-3000 opensky@ucar.edu http://opensky.ucar.edu/ homepage pointOfContact PDF Text theme Resource Type 2016-01-01T00:00:00Z publication <span style="font-family:Arial;font-size:10pt;font-style:normal;font-weight:normal;" data-sheets-root="1">Copyright author(s). This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.</span> None eng geoscientificInformation