摘要
榆林地区新石器时代遗址丰富,同时在中国历史上占有重要地位,为了更有效的保护和发掘榆林地区的遗址,了解古遗址空间分布的不同规律,探讨研究古人类社会发展与自然环境演变的关系,本研究利用Maxent模型结合ArcGIS软件对榆林地区遗址分布进行预测研究,得出榆林地区潜在的遗址分布概率图,并利用Kvamme增益统计对模型精度进行验证。结果表明:①本次实验Maxent模型的AUC值为0.708,表明模型预测准确度较高;②由刀切图得出不同环境变量对遗址分布影响权重从大到小依次为:dem>离水距>剖面曲率>坡度>坡向;③模型的增益值为0.62,说明模型具有较高的精度。
Yulin region is rich in site.It occupies an important position in the history of China,in order to protect and excavate the Yulin sites more effectively and understand the spatial distribution of ancient sites.To explore the relationship between the development of ancient human society and the evolution of natural environment,then this research use Maxent model combining ArcGIS software to predict the distribution site in yulin,The distribution probability map of potential sites in yulin region is obtained.and by using the statistical Kvamme gain model accuracy validation.The results show that:(1)the AUC value of Maxent model in this experiment is 0.708,indicating that the prediction accuracy of the model is high;(2)according to the Jackknife map,the weight of the influence of different environment variables on the distribution of the site is as follows:dem>euclidean distance>curvature>slope>aspect;(3)the gain value of the model is 0.62,indicating that the model has high precision.
作者
吴瑞婵
甘淑
李强强
WU Rui-chan;GAN Shu;LI Qiang-qiang(College of Land and Resources Engineering,Kunming University of Science and Technology,Kunming 650032,China;Institute of Remote Sensing and Digital Earth,Chinese Academy of Science Joint Laboratory of Remote Sensing Archaeology,Beijing 100101)
出处
《软件》
2019年第9期148-152,共5页
Software
