Annual high-resolution grazing intensity maps on the Qinghai-Tibet Plateau from 1990 to 2020

作者：Jia Zhou, Jin Niu, Ning Wu, Tao Lu · 年份：2023 · DOI：10.5194/essd-2023-403 · 被引用次数：15 · 研究领域：Rangeland Management and Livestock Ecology、Remote Sensing in Agriculture、Land Use and Ecosystem Services

Abstract. Grazing activities constitute the paramount challenge to grassland conservation over the Qinghai-Tibet Plateau (QTP), underscoring the urgency for obtaining detailed extent, patterns, and trends of grazing information to access efficient grassland management and sustainable development. Here, to inform these issues, we provided the first annual Gridded Dataset of Grazing Intensity maps (GDGI) with a resolution of 100 meters from 1990 to 2020 for the QTP. Five most commonly used machine learning algorithms were leveraged to develop livestock spatialization model, which spatially disaggregate the livestock census data at the county level into a detailed 100 m× 100 m grid, based on seven key predictors from terrain, climate, land cover and socioeconomic factors. Among these algorithms, the extreme trees (ET) model performed the best in representing the complex nonlinear relationship between various environmental factors and livestock intensity, with an average absolute error of just 0.081 SU/hm2, a rate outperforming the other models by 21.58 %~414.60 %. By using the ET model, we further generated the GDGI dataset for the QTP to reveal the spatio-temporal heterogeneity and variation in grazing intensities. The GDGI indicates grazing intensity decreased from 1990 to 2001 period, and fluctuated thereafter. Encouragingly, comparing with other open-access datasets for grazing distribution on the QTP, the GDGI has the highest accuracy, with the determinant coefficient (R2) ...