Soybean is one of the most important agricultural commodities in the world, thus making it important for global food security. However, widely used process-based crop models, such as the GIS-based Environmental Policy Integrated Climate (GEPIC) model, tend to underestimate the impacts of extreme climate events on soybean, which brings large uncertainties. This study proposed an approach of hybrid models to constrain such uncertainties by coupling the GEPIC model and extreme climate indicators using machine learning. Subsequently, the key extreme climate indicators for the globe and main soybean producing countries are explored, and future soybean yield changes and variability are analyzed using the proposed hybrid model. The results show the coupled GEPIC and Random Forest (GEPIC+RF) model (R: 0.812, RMSD: 0.716 t/ha and rRMSD: 36.62%) significantly eliminated uncertainties and underestimation of climate extremes from the GEPIC model (R: 0.138, RMSD: 1.401 t/ha and rRMSD: 71.57%) compared to the other five hybrid models (R: 0.365–0.612, RMSD: 0.928–1.021 and rRMSD: 47.48–52.24%) during the historical period. For global soybean yield and those in Brazil and Argentina, low-temperature-related indices are the main restriction factors, whereas drought is the constraining factor in the USA and China, and combined drought–heat disaster in India. The GEPIC model would overestimate soybean yields by 13.40–27.23%. The GEPIC+RF model reduced uncertainty by 28.45–41.83% for the period of 2040–2099. Our results imply that extreme climate events will possibly cause more losses in soybean in the future than we have expected, which would help policymakers prepare for future agriculture risk and food security under climate change.

Measuring the impacts of uncertainties identified from different global climate models (GCMs), representative concentration pathways (RCPs), and parameters of statistical crop models on the projected effects of climate change on crop yields can help to improve the availability of simulation results. The quantification and separation of different sources of uncertainty also help to improve understanding of impacts of uncertainties and provide a theoretical basis for their reduction. In this study, uncertainties of maize yield predictions are evaluated by using 30 sets of parameters from statistical crop models together with eight GCMs with reference to three emission scenarios for Jilin Province of northeastern China. Regression models using replicates based on bootstrap resampling reveal that yields are maximized when the optimum average growing season temperature is 20.1°C for 1990–2009. The results of multi-model ensemble simulations show a maize yield reduction of 11%, with 75% probability for 2040–69 relative to the baseline period of 1976–2005. We decompose the variance so as to understand the relative importance of different sources of uncertainty, such as GCMs, RCPs, and statistical model parameters. The greatest proportion of uncertainty (> 50%) is derived from GCMs, followed by RCPs with a proportion of 28% and statistical crop model parameters with a proportion of 20% of total ensemble uncertainty.