Mongolia grazing density dataset from 2006 to 2020

The health status of Mongolian grassland system is related to the benefit of animal husbandry and ecological security at home and abroad. It is of great significance to measure and control grazing density for maintaining the health of Mongolian grassland ecosystem and realizing the sustainable development of animal husbandry. The lack of spatial grazing density gradient information hinders the development of research on grassland carrying capacity. This study is based on the 2015 gridded livestock of the world (GLW) dataset, population density, soil moisture, average annual precipitation, average annual surface temperature and net primary productivity. Using the GEE cloud platform to run the random forest regression algorithm, the Mongolian grazing density estimation model was established. The accuracy of the model was tested based on the statistical data of livestock stocks in the province, and combined with the predictor data of different years, the spatial data set of grazing density in Mongolia from 2006 to 2020 was simulated. In order to ensure the accuracy of the data, three error measurement indexes of decision coefficient (R²), mean absolute error (MAE) and root mean square error (RMSE) were used to verify the data set. Finally, 1 km Mongolian grazing density data sets for 2006, 2010, 2015 and 2020 were obtained. This dataset solves the problem of lack of spatial data of grazing density in Mongolia, and provides important data support for subsequent research on sustainable development of grassland ecosystem and animal husbandry in this region.