Rapidly changing climate makes humans realize that there is a critical need to rethink the current conservation and incorporate climate change adaptation into conservation planning. Whether Great Bustards’ (Otis tarda dybowskii), a globally endangered species whose population is approximately 1,500~2,200 individuals in China, would survive in a changing climate environment is an important protection issue. In this study, we selected the most suitable species distribution model for bustards from four machine learning models, combining two modelling approaches (TreeNet and Random Forest) with two sets of variables (correlated variables removed or not), using common evaluation methods (AUC, Kappa and TSS) and independent testing data. We found Random Forest with all environmental variables outperformed in all assessment methods. Projected the best model to the latest IPCC-CMIP5 climate scenarios (RCP 2.6, 4.5 and 8.5 in BCC-CSM1-1), we found suitable wintering habitats in the current bustards distribution would increase during the 21st century, and dramatically extend eastwards, lightly northwards and westwards, with ongoing climate change. Northeast Plain and the south of North China and the North of East China would become two major suitable wintering habitats of bustards. However, some current suitable habitats will experience a reduction, such as in Middle and Lower Yangtze. Although our results suggest the habitats quantity and quality would widen with climate changing, greater efforts should be undertaken on human disturbance, such as pollution, hunting, unsuitable agriculture development, infrastructure construction, habitat fragmentation, oil and mine exploitation. All of which are negatively and intensely linked with global change.