Conservation prioritization with machine learning predictions for the black-necked crane Grus nigricollis, a flagship species on the Tibetan Plateau for 2070

Abstract

Ongoing global climate change greatly alters the distribution of species, and such impacts are even amplified on the Tibetan Plateau. The black-necked crane (Grus nigricollis) is perceived as an environmental indicator and flagship species in the alpine wetland ecosystems. However, scientifically, sound knowledge about global change impact on its breeding habitats is still lacking. Therefore, based on the best available species data further linked with powerful machine learning methods (ensemble random forest model), we predicted the breeding distribution of the black-necked crane under 2070 climate scenarios and provided associated conservation solutions. Our models for 2070 showed that its breeding range would expand in the hinterland of the Tibetan Plateau, with the current breeding habitats slightly shrinking from exterior margins, and in 2070, the overall habitat suitability would be jeopardized by the dwindling high-suitability habitats. Furthermore, conservation prioritization analyses indicated that global change would impact future-focused conservation and management, whereas the conservation effectiveness of the existing reserve networks would be instead improved with aggravating climate change and that the missing high conservation value areas are also spatially consistent on the Tibetan Plateau. Consequently, one elaborately designed reserve network could be feasible to secure this unique alpine crane lineage as well as the overwhelming majority of water birds on the Tibetan Plateau, despite the serious climate change impacts in the next realizable 50 years.