基于贝叶斯层次时空模型的甘肃省土地利用程度演变分析

以甘肃省为例，在基于Google Earth Engine (GEE)平台实现1995年、2000年、2005年、2010年、2015年和2020年土地变化监测的基础上，利用贝叶斯层次时空模型(BHM)分析土地利用程度的时空变化特征。结果表明：① 研究期间内甘肃省土地利用程度呈增长趋势，其中1995―2000年和2010―2015年增长速度较明显；② 土地利用程度空间格局“东高西低”，热点区域主要分布在陇中、陇东和陇南地区；③ 土地利用程度局部变化呈现明显区域差异，整体表现为“东弱西强”，局部变化热点区域主要分布在河西地区；④ 影响土地利用程度变化的主要因素是经济规模和产业结构，其中经济因素影响程度最高。

Evolution of Land Use Degree in Gansu Province Based on Bayesian Hierarchical Spatio-temporal Model

Land use change has always been an important content of global change research. An in-depth understanding of the temporal and spatial characteristics of land use change can not only provide a direct decision-making basis for the optimal allocation of land resources, but also provide important data support for regulating ecosystem management and improving human social well-being. However, previous studies on land use change lack the analysis of the spatio-temporal coupling process. Taking Gansu Province as an example, based on the Google Earth Engine (GEE) platform to achieve land change monitoring in 1995, 2000, 2005, 2010, 2015 and 2020, and uses Bayesian hierarchical spatio?temporal model (BHM) to analyze the characteristics of temporal and spatial changes of land use degree. The results show that: 1) During the study period, the land use degree of Gansu Province showed an increasing trend, among which the growth rate was obvious from 1995 to 2000 and 2010 to 2015; 2) The spatial pattern of land use degree is “high in the east and low in the west”, hot spots mainly distributed in Longzhong, Longdong and Longnan regions; 3) The local changes of land use degree show obvious regional differences, and the overall performance is “weak in the east and strong in the west”. The hot spots of local changes are mainly distributed in the Hexi region; 4) The main factors affecting changes of land use degree are economic scale and industrial structure, among which economic factors have the highest degree of influence.