2026-10-13T05:28:21Z https://www.scidb.cn/oai

10.57760/sciencedb.29839 2026-06-22T16:25:41Z

2026-06-22 A dataset of annual land use/land cover in the Turpan-Hami Basin (1990–2025) doi:10.57760/sciencedb.29839 en Turpan-Hami (Tuha) Basin, as an ecologically fragile zone in the arid region of northwestern China, serves as an important energy base and a key area for forestry and fruit production in Xinjiang. In recent decades, land use types in the basin have undergone significant transformations due to energy development and the expansion of forestry and fruit industries. These changes have profound implications for regional ecological security, water resource allocation, and the sustainable development of the Silk Road Economic Belt. To gain an in-depth understanding of the characteristics of land use evolution in the region over the past 30 years, this study utilized the Google Earth Engine (GEE) cloud platform to integrate annual Landsat series remote sensing images (30 m resolution) from 1990 to 2025. By combining field survey samples and multi-dimensional remote sensing indices, the first 30-year high-resolution land use dataset for the Tuha Basin was constructed. The dataset was generated using a supervised classification approach with the Random Forest algorithm, which integrated original spectral bands and typical remote sensing indices (such as NDVI, NWI, NDBBI, etc.). Training data were derived from field-sampled land class points and high-resolution image interpretations, effectively improving classification accuracy and regional adaptability. Accuracy assessment results demonstrated that the dataset achieved high overall accuracy (82%) and a Kappa coefficient (0.76). This dataset provides scientific data support for land use simulation, ecological risk assessment, carbon storage estimation, and spatial planning optimization in the region. Turpan-Hami (Tu-Ha) Basin; GEE; Landsat image; Land use/cover shi qing qing Yin Benfeng Huang Jixia Yin Yuanyuan Yang Ao Zhang Yuanming PUBLIC https://creativecommons.org/licenses/by-nc/4.0/ dataset http://www.doi.org/10.11922/11-6035.csd.2025.0186.zh Science Data Bank