A novel ensemble classifier of rotation forest and Naïve Bayer for landslide susceptibility assessment at the Luc Yen district, Yen Bai Province (Viet Nam) using GIS
A novel ensemble classifier of rotation forest and Naïve Bayer for landslide susceptibility assessment at the Luc Yen district, Yen Bai Province (Viet Nam) using GIS
复制标题
DOI：
10.1080/19475705.2016.1255667
复制
发表时间：
2017-12
期刊：
影响因子：
--
通讯作者：
B. Pham;D. Bui;M. Dholakia;Indra Prakash;H. Pham;K. Mehmood;H. Q. Le;Thanh Xuân;Hà Nội;Việt Nam
中科院分区：
文献类型：
--
作者：
B. Pham;D. Bui;M. Dholakia;Indra Prakash;H. Pham;K. Mehmood;H. Q. Le;Thanh Xuân;Hà Nội;Việt Nam
摘要本研究的目的是尝试一种新的软计算方法，在Luc Yen区，Yen Bai省（越南）使用一种新的分类器集成模型的朴素贝叶斯和旋转森林的滑坡敏感性评估。首先，通过野外调查和航片判读，对95个滑坡点的历史进行了拜菲尔德识别。此外，共10个滑坡成因因素（坡度，方面，海拔，曲率，岩性，土地利用，距离道路，距离河流，距离断层，降雨量），以评估与滑坡发生的空间关系。信息增益技术被用来量化这些因素的预测能力。其次，利用新的分类器集成模型进行了滑坡敏感性评价。最后，采用受试者工作特征曲线技术和基于统计指标的评价方法对滑坡模型的性能进行了验证。新的分类器集成模型具有较高的预测能力（AUC = 0.846）和相对较高的准确率（ACC = 78.77%）。研究表明，该模型表现良好，与其他滑坡模型，如AdaBoost，Bagging，MultiBoost和随机森林。总体而言，新的分类器集成模型是一种很有前途的方法，可用于滑坡敏感性评价。
ABSTRACT The objective of this study is to attempt a new soft computing approach for assessment of landslide susceptibility in the Luc Yen district, Yen Bai province (Viet Nam) using a novel classifier ensemble model of Naïve Bayes and Rotation Forest. First, history of 95 landslide locations was identified byfield investigations and interpretation of aerial photos. Also, the total ten landslide causal factors were selected (slope, aspect, elevation, curvature, lithology, land use, distance to roads, distance to rivers, distance to faults, and rainfall) to evaluate the spatial relationship with landslide occurrences. Information Gain technique is carried out to quantify the predictive capability of these factors. Second, landslide susceptibility assessment was carried out utilizing the novel classifier ensemble model. Finally, the performance of landslide model was validated using receiver operating characteristic curve technique, and statistical index-based evaluations. The novel classifier ensemble model indicates high prediction capability (AUC = 0.846) and relatively high accuracy (ACC = 78.77%). The study reveals that this model performs well in comparison to the other landslide models such as AdaBoost, Bagging, MultiBoost, and Random Forest. Overall, the novel classifier ensemble model is a promising method that could be used for landslide susceptibility assessment.