Plant species diversity (PSD) has always been an essential component of biodiversity and plays an important role in ecosystem functions and services. However, it is still a huge challenge to simulate the spatial distribution of PSD due to the difficulties of data acquisition and unsatisfactory performance of predicting algorithms over large areas. A surge in the number of remote sensing imagery, along with the great success of machine learning, opens new opportunities for the mapping of PSD. Therefore, different machine learning algorithms combined with high-accuracy surface modeling (HASM) were firstly proposed to predict the PSD in the Xinghai, northeastern Qinghai-Tibetan Plateau, China. Spectral reflectance and vegetation indices, generated from Landsat 8 images, and environmental variables were taken as the potential explanatory factors of machine learning models including least absolute shrinkage and selection operator (Lasso), ridge regression (Ridge), eXtreme Gradient Boosting (XGBoost), and Random Forest (RF). The prediction generated from these machine learning methods and in situ observation data were integrated by using HASM for the high-accuracy mapping of PSD including three species diversity indices. The results showed that PSD was closely associated with vegetation indices, followed by spectral reflectance and environmental factors. XGBoost combined with HASM (HASM-XGBoost) showed the best performance with the lowest MAE and RMSE. Our results suggested that the fusion of heterogeneous data and the ensemble of heterogeneous models may revolutionize our ability to predict the PSD over large areas, especially in some places limited by sparse field samples.

Temperature changes have a major impact on all aspects of human society and have attracted global attention. The scarcity of observation data and the inaccuracy of the models make obtaining accurate temperature distributions a challenge. This study introduces high-accuracy surface modeling (HASM) combined with temperature simulations from the Weather Research and Forecasting (WRF) model and temperature records from observation stations to investigate the spatiotemporal characteristics of temperature in the Beijing-Tianjin-Hebei region during the period of 1956–2005. Leave-one-out cross-validation is applied to verify the temperature fields before and after the fusion of the models. The results indicate that the WRF model has a limited ability to simulate temperature conditions, but the overall deviation across the region is relatively large. The fusion results of the HASM decrease the mean absolute error (MAE) and the root-mean-square error (RMSE) by half in most instances, and the correlation between the fusion data and observation data is approximately 0.01–0.03 higher than that with the WRF simulation data. Based on the fusion data, obvious warming trends are observed during 1976–2005. In general, temperatures in spring, summer, and autumn increase rapidly from 1996 to 2005 but from 1976 to 1995 in winter. The substantial fluctuations in the interannual temperature during 1996–2005 in summer, autumn, and winter may be related to the frequent occurrence of extreme weather. The spatial distribution of temperature change differs in each season during 1956–1995. A dramatic increase in temperature occurs in the western part of the study area during 1996–2005 but with no seasonal difference.