基于集成学习与径向基神经网络耦合模型的三峡库区滑坡易发性评价

准确的滑坡易发性评价结果是滑坡风险评价的重要基础.为提升滑坡易发性评价精度，以三峡库区龙驹坝为例，选取坡度等10个因子构建滑坡易发性评价指标体系，应用频率比方法定量分析各指标与滑坡发育的关系.在此基础上，随机选取70%/30%的滑坡数据作为训练/测试样本，应用径向基神经网络和Adaboost集成学习耦合模型(RBNN-Adaboost)，径向基神经网络和逻辑回归模型分别开展易发性评价.结果显示:水系距离、坡度等是滑坡发育的主控因素；RBNN-Adaboost耦合模型的预测精度最高(0.820)，优于RBNN模型和LR模型的0.781和0.748.Adaboost集成算法能进一步提升模型的预测性能，所提出的耦合模型结合了两者的优点，具有更强的预测能力，是一种可靠的滑坡易发性评价模型. 

Landslide Susceptibility Assessment by Applying the Coupling Method of Radial Basis Neural Network and Adaboost: A Case Study from the Three Gorges Reservoir Area

Accurate landslide susceptibility map is an important basis for landslide risk assessment. In order to improve the accuracy of landslide susceptibility assessment,Longjuba area in the Three Gorges reservoir area was taken as a case study,10 factors (i.e. slope) were selected and parepared,and the frequency ratio method was used to analyze the relationship between each factor and landslide development quantitatively. 70% landslides were randomly selected as training samples while the 30% were adopted for testing,the radial basis neural network and adaboost ensemble learning coupled model (RBNN-Adaboost),radial basis neural network (RBNN) and logistic regression (LR) model were used to make the assessment of landslide susceptibility,respectively. Results show that factors of distance to river,slope and so on are the main controlling factors of landslide development; RBNN-Adaboost shows the best prediction accuracy (0.820) than logistic regression model (0.748) and RBNN (0.781). The adaboost ensemble learning can further improve the prediction performance of the model. By combining the advantages of RBNN and adaboost,the proposed method achieves the highest prediction accuracy,which is a reliable assessment model of landslide susceptibility.