2026-10-14T17:30:46Z https://www.scidb.cn/oai

10.57760/sciencedb.26573 2025-06-19T09:09:40Z

2025-06-19 Qinghai Province Natural Grassland Fire Prone Data Set doi:10.57760/sciencedb.26573 en This data is based on the historical fire data of forest, grassland, and emergency management departments at all levels of state government in Qinghai Province from 2000 to 2020, which have identified the causes of natural grassland fires. It is combined with historical precipitation data with a resolution of 1km in Qinghai Province from 2000 to 2020 NDVI、 By constructing a maximum entropy model, the average wind speed, relative humidity, slope, aspect, vegetation type, and distance from the river data are simulated and predicted to predict the susceptibility of natural grassland fires in Qinghai Province. To improve the spatial partitioning accuracy, the Kvamme gain statistical model was used to validate the partitioning accuracy simulated by the maximum entropy model. The AUC value of the model accuracy was 0.947, and the G value was close to 1, indicating that the constructed natural grassland fire susceptibility evaluation model can effectively identify high-risk areas where natural grassland fires occur. The dataset has a resolution of 1km and the file format is GeoTIFF. The dataset provides data support and scientific basis for grassland fire prevention and management in Qinghai Province, and can also serve as an important basis for financial institutions and insurance companies to optimize insurance pricing and design disaster bonds.  Maximum Entropy Model; Natural grassland fires; Qinghai Province; Susceptibility Xu Wenjing Zhou Qiang Ma Weidong Huang Yongsheng Zhang Ziqian Zhou Juan Yu Qin PUBLIC https://creativecommons.org/licenses/by-nc/4.0/ dataset Science Data Bank