Explaining climatic drivers of yield anomalies in global crop models through metamodel-based attribution

Oberleitner, T., Baklanov, A. ORCID: https://orcid.org/0000-0003-1599-3618, Ferreira, T.B., Hoogenboom, G., Jägermeyr, J., Jain, A., Lin, T.-S., Mialyk, O., Müller, C., Ruane, A.C., Zabel, F., Balkovič, J. ORCID: https://orcid.org/0000-0003-2955-4931, Wang, C., Faye, B., Guarin, J.R., Iizumi, T., Khabarov, N. ORCID: https://orcid.org/0000-0001-5372-4668, Liu, W., Okada, M., Rabin, S.S., et al. (2025). Explaining climatic drivers of yield anomalies in global crop models through metamodel-based attribution. ESS Open Archive 10.22541/essoar.176071967.73925210/v1. (Submitted)

Preview

Text 1050287_0_merged_1760008420.pdf - Submitted Version Available under License Creative Commons Attribution. Download (2MB) | Preview

Abstract

Global gridded crop models (GGCMs) are important tools for assessing climate impacts on agriculture, yet significant divergence in their projections limits interpretability, and impact studies often treat GGCMs as black boxes. Targeted ensemble sensitivity analyses are demanding and not transferable to different ensembles. Here, we comprehensively evaluate climatic and soil drivers of crop yield anomalies in a state-of-the-art GGCM ensemble, using maize as a representative crop. Gradient boosting classifiers detect anomalies, SHapley Additive exPlanations (SHAP) values quantify feature importance, and methods are applied to a recent GGCM experiment driven by reanalysis climate data. We find broadly similar climatic drivers across the ensemble, though feature importance distributions differ. Low precipitation dominates under rainfed conditions, while solar radiation typically ranks second, highlighting that drought impacts depend on atmospheric water demand often omitted from sensitivity analyses. In some GGCMs, excess rather than insufficient water drives anomalies. With irrigation, low solar radiation or adverse temperatures become the main drivers. In (semi-)arid regions, some GGCMs respond more to cool conditions, others to warm ones. Soil features usually rank lowest but can be moderately important in some models. Our findings demonstrate that evaluating opportunistic data—experiments produced for other purposes—yields vital insights into GGCM divergence in impact studies. Code is publicly available on GitHub to support future attribution analyses and inform broad audiences about drivers of observed results.

Actions (login required)

View Item