Why choose Random Forest to predict rare species distribution with few samples in large undersampled areas? Three Asian crane species models provide supporting evidence

• Published in: PeerJ (San Francisco, CA) CA), 2017-01, Vol.5, p.e2849-e2849, Article e2849
• Main Authors: Mi, Chunrong, Huettmann, Falk, Guo, Yumin, Han, Xuesong, Wen, Lijia
• Format: Article
• Language: English
• Subjects: 21st century; Accuracy; Algorithms; Animal behavior; Artificial intelligence; Biodiversity; Biogeography; Biology; Case studies; Climate change; Conservation; Conservation Biology; Data mining; Ecology; Entropy; Forecasts and trends; Generality (transferability); Gruidae; Grus monacha; Grus nigricollis; Grus vipio; Learning algorithms; Machine learning; Random Forest; Rare species; Regression analysis; Sample size; Software; Spatial distribution; Species distribution models (SDMs); Stochasticity; Undersampled areas; White-naped crane (Grus vipio); Wilderness areas; Zoology
• ISSN: 2167-8359; 2167-8359
• DOI: 10.7717/peerj.2849

Species distribution models (SDMs) have become an essential tool in ecology, biogeography, evolution and, more recently, in conservation biology. How to generalize species distributions in large undersampled areas, especially with few samples, is a fundamental issue of SDMs. In order to explore this issue, we used the best available presence records for the Hooded Crane ( ,  = 33), White-naped Crane ( ,  = 40), and Black-necked Crane ( ,  = 75) in China as three case studies, employing four powerful and commonly used machine learning algorithms to map the breeding distributions of the three species: TreeNet (Stochastic Gradient Boosting, Boosted Regression Tree Model), Random Forest, CART (Classification and Regression Tree) and Maxent (Maximum Entropy Models). In addition, we developed an ensemble forecast by averaging predicted probability of the above four models results. Commonly used model performance metrics (Area under ROC (AUC) and true skill statistic (TSS)) were employed to evaluate model accuracy. The latest satellite tracking data and compiled literature data were used as two independent testing datasets to confront model predictions. We found Random Forest demonstrated the best performance for the most assessment method, provided a better model fit to the testing data, and achieved better species range maps for each crane species in undersampled areas. Random Forest has been generally available for more than 20 years and has been known to perform extremely well in ecological predictions. However, while increasingly on the rise, its potential is still widely underused in conservation, (spatial) ecological applications and for inference. Our results show that it informs ecological and biogeographical theories as well as being suitable for conservation applications, specifically when the study area is undersampled. This method helps to save model-selection time and effort, and allows robust and rapid assessments and decisions for efficient conservation.