ISSN 1000-3665 CN 11-2202/P
    陈航,刘惠军,王韬,等. 基于频率比-深度神经网络耦合模型的滑坡易发性评价−以盐源县为例[J]. 水文地质工程地质,2024,51(5): 161-171. DOI: 10.16030/j.cnki.issn.1000-3665.202305006
    引用本文: 陈航,刘惠军,王韬,等. 基于频率比-深度神经网络耦合模型的滑坡易发性评价−以盐源县为例[J]. 水文地质工程地质,2024,51(5): 161-171. DOI: 10.16030/j.cnki.issn.1000-3665.202305006
    CHEN Hang, LIU Huijun, WANG Tao, et al. Landslide susceptibility evaluation based on FR-DNN coupling model: A case study on Yanyuan County[J]. Hydrogeology & Engineering Geology, 2024, 51(5): 161-171. DOI: 10.16030/j.cnki.issn.1000-3665.202305006
    Citation: CHEN Hang, LIU Huijun, WANG Tao, et al. Landslide susceptibility evaluation based on FR-DNN coupling model: A case study on Yanyuan County[J]. Hydrogeology & Engineering Geology, 2024, 51(5): 161-171. DOI: 10.16030/j.cnki.issn.1000-3665.202305006

    基于频率比-深度神经网络耦合模型的滑坡易发性评价以盐源县为例

    Landslide susceptibility evaluation based on FR-DNN coupling model: A case study on Yanyuan County

    • 摘要: 盐源县位于青藏高原东南边缘,区域构造活动强烈,在内外动力共同作用下,境内滑坡灾害极其发育,已经造成了巨大的人员伤亡和经济损失,有必要开展滑坡易发性评价,对区域滑坡灾害进行科学管控。依据盐源县1∶5万地质灾害调查成果,选取高程、坡度、坡向、地形曲率、距断层距离、地层岩性、距水系距离、年平均降雨量、地形湿度指数、水流强度指数、归一化植被指数、距道路距离、土地利用类型等13个滑坡易发性评价因子,基于27596个滑坡灾害栅格点数据,将传统频率比(frequency ratio,FR)模型定量分析及数据量化优势,与新兴深度神经网络(deep neural network,DNN)模型强大的非线性学习和拟合能力相结合,构建FR-DNN耦合模型进行滑坡易发性评价,将研究区划分为极高易发区、高易发区、中易发区、低易发区、极低易发区5个等级,面积占比分别为11.90%、18.38%、18.34%、9.13%、42.25%,并与传统FR模型进行对比,用ROC曲线的AUC值进行精度验证。结果表明,FR模型与FR-DNN耦合模型的AUC值分别为0.754、0.859,FR-DNN耦合模型相对于FR模型预测精度提高了10.5%,由此说明FR-DNN耦合模型具有更好的预测能力,更适用于研究区滑坡易发性评价。

       

      Abstract: Yanyuan County is located on the southeastern edge of the Qinghai-Tibet Plateau, with strong regional tectonic activities. Under the internal and external dynamics actions, landslide disasters are extremely developed in the country, which has caused huge casualties and economic losses. It is necessary to carry out landslide susceptibility assessment and then control the regional landslide disasters scientifically. Based on the 1∶50000 geological disaster survey in Yanyuan County, this study selected 13 landslide susceptibility evaluation factors, including elevation, slope, slope direction, terrain curvature, distance from fault, stratigraphic lithology, distance from water body, average annual rainfall, topographic wetness index, stream power index, normalized difference vegetation index, distance from road, and land use type. Based on 27596 grid points of landslide disaster data, combining the traditional Frequency Ratio (FR) model with the advantages of quantitative analysis and data quantification and the emerging Deep Neural Network (DNN) model with the powerful nonlinear learning and fitting ability, The FR-DNN coupling model was constructed to evaluate landslide susceptibility. The study area is divided into five levels: extremely high susceptibility area, high susceptibility area, medium susceptibility area, low susceptibility area, and extremely low susceptibility area, with an area percentage of 11.90%, 18.38%, 18.34%, 9.13%, and 42.25%, respectively. The accuracy was verified by the AUC value of the ROC curve. The AUC values of the FR model and the FR-DNN coupling model are 0.754 and 0.859, respectively. The prediction accuracy of the FR-DNN coupling model is improved by 10.5% compared with that of the FR model, indicating that the FR-DNN coupling model has better prediction ability and is more suitable for landslide susceptibility evaluation in the study area.

       

    /

    返回文章
    返回