Estimating the aboveground biomass of the Hulunbuir Grassland and exploring its spatial and temporal variations over the past ten years

• DOI: 10.1016/j.ecolind.2024.112010
• Publication Date: 2024-04-09T04:39:42Z
• Authors: Chang Chang; Yu Chang; Zaiping Xiong; Hongshun Liu; Rencang Bu
• Keywords: Vegetation indices; Ecology; Aboveground biomass; 0401 agriculture, forestry, and fisheries; 04 agricultural and veterinary sciences; Spatiotemporal variation; Grassland; QH540-549.5; Random forest

In the past 10 years, extreme weather phenomena have increased, and global warming has markedly advanced; moreover, intensity of human activity gradually increased. These an impact on growth vegetation. Related studies focused Tibetan Plateau some northern provinces China to estimate grassland AGB at a large scale but low resolution. Hulunbuir Grassland is important supplier livestock products, therefore, it precisely map explore response climate change activities high resolution identify complex spatial details. this study, we selected vegetation indices from Landsat 8 OLI topographic used multiple linear regression machine learning algorithms distribution 2013 2022. Then, analyzed correlations between cumulative precipitation daily average temperature in summer population density pixel level. Our results demonstrated that RF model performed well, with RMSE 28.23 R2 value 0.74; was positively correlated 94.45 % area negatively 96.32 area. We suggest necessary reduce grazing future warm drought years adjust sources income adapt decrease under conditions. This study will provide reference for countries or regions depend temperate grasslands husbandry.