Understanding the spatial distribution of rare species is fundamental to biodiversity conservation. The Black-necked Crane (Grus nigricollis), a flagship species of alpine wetlands and a first-class nationally protected wildlife in China, serves as an important indicator for ecosystem health. Based on the distribution site data and ecological environment data of Black-necked Crane, this study used the Maximum Entropy model (MaxEnt) and Random Forest model (RF) to predict the suitable distribution area of Black-necked Crane. Model performance evaluation through the area under the receiver operating characteristic curve (AUC) demonstrated that the Random Forest model achieved superior predictive accuracy (AUC=0.945), showing strong concordance with known crane distributions. Key environmental determinants of habitat suitability were identified as distance to buildings (d_b), distance to roads (d_r), and isothermality (Bio3), with average contribution rates of 15.1%, 15.05%, and 5.85%, respectively. High-probability suitable areas were primarily concentrated in riparian wetlands of Nyingchi City, with an optimal habitat core at the T-shaped valley confluence of the Yarlung Tsangpo and Nyang rivers. Through comparative analysis of MaxEnt and RF, this study significantly reduced spatial uncertainties in habitat suitability predictions.These findings provide critical spatial baselines for targeted conservation strategies of this sacred plateau species, particularly in maintaining connectivity of critical wetland habitats under climate change scenarios.

Understanding the spatial and temporal distributions of rare species is important for informed management. The black-necked crane Grus nigricollis, a rare bird in China and flagship species in alpine wetlands, is nationally protected. Using site and environmental data, we use Maximum Entropy (MEM) and Random Forest (RFM) models to predict suitable habitat for this bird. Environmental variables that most affect its distribution are distance from buildings and roads, and isothermality, with contribution rates of 15.1%, 15.05%, and 5.85%, respectively. Using the AUC (area under curve) coefficient as an index to evaluate model precision, the predictions of the RFM are most consistent with the known distribution of these cranes, predicting the highest match with known crane sites (AUC = 0.945). Suitable habitat for this crane occurs mainly in Nyingchi city riverine wetland, where the centre of distribution is located in a valley where the Yarlung Tsangpo and Niyang rivers converge. A comparison between MEM and RFM outputs reduces uncertainty in predictions of black-necked crane spatial distribution, and filters optimal results for the distribution area. These results enable more-informed protection of habitat for this sacred crane.