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.

Based on gridded temperature data from the China Meteorological Administration (CMA), two types of methods, i.e., absolute methods and relative methods, respectively, were used to identify heat waves in Mainland China. Four statistical indicators, including the occurrence frequency, duration days, earliest occurrence date, and latest extinction date, were constructed to analyze the spatial-temporal characteristics of heat waves, especially on the annual and decadal change trends. Firstly, we found that both the frequency and the duration of heat waves decreased in the period from 1960 to 1989 but increased in the 1990s and increased significantly from the early 2000s to the 2010s. Spatially, the frequency and the duration obtained by each type of method are significantly different among different regions when considering different facts, such as different regions that have different degrees of tolerance to heat waves. Secondly, the decadal distribution characteristics of the earliest occurrence date and the latest extinction date of heat waves well capture the hot summer, the stronger sensitivity of winter to warming than other seasons, and the gradually increasing intensity of heat waves. It provides a multidimensional reference for the cause analysis and prediction of extreme heat waves in China.

This study uses hourly surface wind direction and wind speed observations from 53 meteorological stations on the Tibetan Plateau (TP) (70–105° E, 25–45° N) between 1995 and 2017 to investigate diurnal variations in the surface wind. The results show large diurnal variations in surface wind on the TP. The minimum wind speed occurs in the morning and the maximum in the afternoon. In all four seasons, the prevailing meridional wind is a southerly, and this is typically evident for more than two-thirds of each day. However, in the mornings during December–February and September–November, this southerly wind is replaced by a northerly, but remains southerly in the afternoon. The TP shows remarkable regional characteristics with respect to diurnal variations in wind speed. In the eastern region, the minimum and maximum daily wind speeds occur about 1 h later than in the west. Among the 53 meteorological stations, 79% observed that it took less time for the minimum speed to rise to the maximum speed than for the maximum to drop to the minimum. The blocking effect of the high surrounding terrain causes the diurnal variations seen in the surface winds at the three stations in the Qaidam Basin to differ significantly from those observed at the other stations elsewhere on the plateau. These Qaidam Basin stations recorded their maximum wind speeds around noon, with the minimum at dusk, which is around 1900 LST. The EOF1 (EOF = empirical orthogonal function) of the hourly wind speed on the TP indicates the key daily circulation feature of the region; i.e., the wind speed is high in the afternoon and low in the morning. The EOF2 reflects the regional differences in the diurnal variations of wind speed on the TP; i.e., the eastern region reaches the daily maximum and minimum wind speeds slightly later than the western region.

Snow cover over the Tibetan Plateau plays a vital role in the regional and global climate system because it affects not only the climate but also the hydrological cycle and ecosystem. However, high-quality snow data are hindered due to the sparsity of observation networks and complex terrain in the region. In this study, a nonlinear time series analysis method called phase space reconstruction was used to obtain the Tibetan Plateau snow depth by combining the FY-3C satellite data andin situdata for the period 2014–2017. This method features making a time delay reconstruction of a phase space to view the dynamics. Both of the grids and their nearbyin situsnow depth time series were reconstructed with two appropriate parameters called time delay and embedding dimension. The values of the snow depth for grids were averaged over thein situobservations and retrieval of the satellite if their two parameters were the same. That implies that the two trajectories of the time series had the same evolution trend. Otherwise, the snow depth values for grids were averaged over thein situobservation. If there were noin situsites within the grids, the retrieval of the satellite remained. The results show that the integrated Tibetan Plateau snow depth (ITPSD) had an average bias of –1.35 cm and 1.14 cm, standard deviation of the bias of 3.96 cm and 5.67 cm, and root mean square error of 4.18 cm and 5.79 cm compared with thein situdata and FY-3C satellite data, respectively. ITPSD expressed the issue that snow depth is usually overestimated in mountain regions by satellites. This is due to the introduction of more station observations using a dynamical statistical method to correct the biases in the satellite data.