Anthropogenic activities profoundly influence carbon sequestration in the Eurasian Steppe.  In particular, grazing has been identified as having a major effect on carbon sequestration.  However, the extent to which grazing affects regional patterns or carbon sequestration is unknown.  In this study, we evaluated the impact of regional grazing on grassland carbon sequestration using the Boreal Ecosystem Productivity Simulator (BEPS) and the Shiyomi grazing model.  Model performances were validated against the results from field measurements and eddy covariance (EC) sites.  Model outputs showed that in 2008, the regional net primary productivity (NPP) was 79.5 g C m^–2, and the net ecosystem productivity (NEP) was –6.5 g C m^–2, characterizing the region as a weak carbon source.  The Mongol Steppe (MS) was identified as a carbon sink, whereas the Kazakh Steppe (KS) was either carbon neutral or a weak carbon source.  The spatial patterns of grazing density are divergent between the MS and the KS.  In the MS, livestock was mainly distributed in China with relatively good management, while in the KS livestock was mainly concentrated in the southern countries (especially Uzbekistan and Turkmenistan) with harsh environments and poor management.  The consumption percentages of NPP in Turkmenistan, Tajikistan and Uzbekistan were 5.3, 3.3 and 1.2%, respectively, whereas the percentages in other countries were lower than 1%.  Correspondingly, grazing consumption contributed to the carbon sources of Turkmenistan, Tajikistan and Uzbekistan by 11.6, 6.3 and 4.3%, respectively, while it weakened the carbon sink in Inner Mongolia, China and Mongolia by 1.6 and 0.5%.  This regional pattern should be affected by different sub-regional characteristics, e.g., the continuous degradation of grassland in the southern part of the KS and the restoration of grassland in Inner Mongolia, China.

This research classified vegetation types and evaluated net primary productivity (NPP) of southern China’s grasslands based on the improved comprehensive and sequential classification system (CSCS), and proposed 5 thermal grades and 6 humidity grades. Four classes of grasslands vegetation were recognized by improved CSCS, namely, tundra grassland class, typical grassland class, mixed grassland class and alpine grassland class. At the type level, 14 types of vegetations (9 grasslands and 5 forests) were classified. The NPP had a trend to decrease from east to west and south to north, and the annual mean NPP was estimated to be 656.3 g C m-2 yr-1. The NPP value of alpine grassland class was relatively high, generally more than 1 200 g C m-2 yr-1. The NPP value of mixed grassland class was in a range from 1 000 to 1 200 g C m-2 yr-1. Tundra grassland class was located in southeastern Tibet with high elevation, and its NPP value was the lowest (<600 g C m-2 yr-1). The typical grassland class distributed in most of the area, and its NPP value was generally from 600 to 1 000 g C m-2 yr-1. The total NPP value in the study area was 68.46 Tg C. The NPP value of typical grassland class was the highest (48.44 Tg C), and mixed grassland class was the second (16.54 Tg C), followed by alpine grassland class (3.22 Tg C), with tundra grassland class being the lowest (0.25 Tg C). For all the grasslands types, the total NPP of forest meadow was the highest (34.81 Tg C), followed by sparse forest brush (16.54 Tg C), and montane meadow was the lowest (0.01 Tg C).