Multi temporal vegetation mapping of the Tibetan Plateau via machine learning model simulation and experiential knowledge

<p indent="0mm">Understanding long-term trends in vegetation distribution and its responses to climate change and human activities requires vegetation distribution data from multiple periods. At present, the vegetation maps of the Tibetan Plateau mainly exist for periods of time surrounding 2000 and 2020, during which time they were based on field survey data, and 10-year periods from 1990 to 2020, during which time they were based on random forest classifiers and Landsat imagery. These maps were created though manual mapping based on ground observation data and automatic mapping based on ground observation data, remote sensing data, terrain data and climate data, with machine learning models used for classification. There are problems, such as confusion among some vegetation types, and map accuracy needs to be improved. Moreover, there is a lack of vegetation distribution data from earlier periods. This study developed artificial mapping techniques based on random forest machine learning models, integrating observation data, remote sensing data, terrain data, climate data, etc., and obtained vegetation distribution maps of the Tibetan Plateau in the 1980s and 2020. On the basis of zonal vegetation analysis and the 1980s vegetation map, an approximated original vegetation map of the Tibetan Plateau was obtained. On the basis of the vegetation map of the Tibetan Plateau from 2020, a random forest model was used to simulate the vegetation distribution maps of the Tibetan Plateau in 2035 and 2050. The spatial resolution of the approximated original vegetation map, the 1980s vegetation map and the 2020 vegetation map was approximately<sc> 100 m.</sc> The approximated original vegetation map, the 1980s vegetation map and the 2020 vegetation map contain 11 vegetation groups, 43 vegetation types, and 2 vegetation subtypes. Owing to the influences of climate, terrain, soil and other conditions, the vegetation distribution patterns of forests, shrubs, grasslands, and deserts on the Tibetan Plateau from southeast to northwest did not change across the five periods, but the areas and distribution ranges of various types of vegetation changed. In the approximated original vegetation map, the vegetation type with the largest area was alpine grass and <italic>Carex</italic> steppe, totaling<sc>588400 km²,</sc> followed by alpine <italic>Kobresia</italic> spp. and forb meadows, totaling<sc> 574700 km².</sc> There were more than 15 other vegetation types with areas exceeding<sc> 10000 km².</sc> In areas without vegetation, the areas covered by glaciers and snow were the largest, followed by water bodies. The areas of bare rocky hills, bare gobi hills, yardan hills, and bare salt licks also exceeded <sc>10000 km².</sc>The areas of alpine vegetation types decreased, with the greatest reduction in cold-temperate and temperate mountain needleleaf forests, reaching 36.9%, and a decrease of 7.2% in cold-temperate and temperate swamps. In addition, the areas of temperate grass, <italic>Carex</italic> and forb swamp meadows decreased by 97.1%, whereas those of temperate grass and forb meadows and subtropical and tropical grass forb communities decreased by more than 50%. The areas of subtropical broadleaf evergreen forests, temperate dwarf semiarboreous deserts, and temperate broadleaf deciduous scrubs increased by 109.9%, 50.5%, and 29.0%, respectively. The area of glaciers and snow decreased by 2.8%, the area of water bodies increased by 34.3%, the area of bare salt licks increased by 9.1%, and the area of salt crust increased by 7.4%. Compared with the widely recognized and reliable <italic>Vegetation Map of the People’s Republic of China</italic> (1:100000), the vegetation map in the 1980s and 2020 obtained in this study provides a more accurate depiction of vegetation type boundaries, increasing the number of vegetation patches several folds, which is conducive to a more accurate understanding and simulation of the response of vegetation on the Tibetan Plateau to climate change.