A global map of human visitation in 2017

Understanding global patterns of human visitation is crucial for monitoring anthropogenic pressures on ecological integrity, optimizing tourism management, and informing decision-making in various domains. However, existing datasets on human visitation are insufficient and primarily limited to local scales. We combined massive geotagged microblogs and multi-covariates to infer the global human visitation in 2017 at a fine spatial resolution of 0.01 degrees. Specifically, we proposed a Classified Visitation Indicator (CVI) to quantify human visitation. It categorizes the intensity of human visitation at a location in four levels based on year-long statistics of geotagged data. CVI-0, CVI-1, CVI-2, and CVI-3 represent never visited grids, rarely visited grids, frequently visited grids, and consistently visited grids, respectively. The model achieved a macro-F1 score of 0.72 on a test set comprising over 1.9 million grids in China and 0.84 on manually labeled samples worldwide. Cross-validation with external datasets, including geotagged social media data from X and global human settlement and population data, corroborated the model's effectiveness. The related article is currently under review.