基于RBF神经网络−信息量耦合模型的滑坡易发性评价--以甘肃岷县为例

Landslide susceptibility assessment by the coupling method of RBF neural network and information value:A case study in Min Xian,Gansu Province

滑坡易发性评价是滑坡灾害管理的基础工作,也是制定各项防灾减灾措施的重要依据。针对传统的信息量模型在评价过程中确定权重值存在准确性不高的缺点,文章提出RBF神经网络和信息量耦合模型。以甘肃省岷县为研究区,筛选坡度等9个指标因子构建了滑坡灾害易发性评价指标体系,应用RBF神经网络-信息量耦合模型(RBFNN-I)进行滑坡灾害易发性评价,利用合理性检验和ROC曲线对模型的评价结果进行精度检验。结果表明:(1)RBFNN-I模型的AUC值为0.853,相比单一的RBFNN和I模型分别提高了6.3%和9.7%,说明RBFNN-I模型具有更好的评价精度;(2)岷县滑坡灾害的极高易发区和高易发区主要分布在临潭—宕昌断裂带、洮河及其支流、闾井河和蒲麻河两侧河谷地带,距断层距离、降雨量、距道路距离和NDVI是影响岷县滑坡灾害分布的主控因子。

The landslide susceptibility evaluation is the basic work of landslide management,and it is also an important basis for formulating various disaster prevention and mitigation measures.In view of the low accuracy of the traditional information model in determining the weight value in the evaluation process,this paper proposes a coupling model of RBF neural network and Information value model.9 index factors such as slope are selected to build the evaluation index system of landslide susceptibility in Min Xian of Gansu Province.The RBF neural network information value coupling model(RBFNN-I)is used to carry out the landslide hazard susceptibility evaluation.Rationality test and ROC curve are used to test the accuracy of the evaluation results of the model.The results show that:(1)the AUC value of RBFNN-I model is 0.853,which is 6.3%and 9.7%higher than that of single RBFNN and I model,respectively,indicating that RBFNN-I model has better evaluation accuracy;(2)the extremely high and high susceptible areas of landslide disasters in Min Xian are mainly distributed along Lintan-Dangchang fault zone,Tao He and its tributaries,and the valleys on both sides of Lyuning River and Puma River.