本文已被：浏览 781次 下载 339次
投稿时间：2021-08-16 修订日期：2021-11-07
投稿时间：2021-08-16 修订日期：2021-11-07
中文摘要: 在利用机器学习（machine learning，ML）模型预测滑坡易发性时，选择合理的负样本对预测结果具有重要影响。现有研究大多从整个研究区或低坡度等特定属性区内随机选择负样本，往往不够准确或以偏概全，降低了易发性制图的可靠性。为解决这一问题，提出基于耦合信息量法（information value，IV）的ML模型开展易发性建模。以江西省瑞金市为例，采用IV法将环境因子的属性值转化为对滑坡贡献的信息量值，划定极低和低易发区，并从中随机选择出ML模型训练验证用的负样本数据，构建全新的信息量–支持向量机（IV–SVM）、信息量–随机森林（IV–RF）耦合模型，并预测瑞金滑坡易发性。进一步地，与从全区随机选择负样本的单独SVM和RF模型，以及从坡度小于2°的特定属性区内随机选择负样本的低坡度SVM和RF模型开展对比研究。最后，采用Kappa系数和ROC曲线等指标验证和比较建模结果，IV–SVM和IV–RF模型的Kappa系数分别为0.828和0.876 ，且对应的ROC曲线的AUC值分别为0.920和0.988，均高于单独SVM、RF和低坡度SVM、RF模型；同时，IV–SVM和IV–RF模型易发性概率分布的平均值较小而标准差较大。结果表明：1）IV–SVM和IV–RF模型具有比单独SVM和RF模型，以及低坡度SVM和RF模型更高的滑坡易发性预测精度，且更有效地反映了瑞金滑坡易发性分布规律；2）RF模型相较于SVM模型具有更高的预测精度；3）IV–RF等耦合模型能够解决单独模型存在的负样本采样不准确和低坡度模型存在的坡度因子对模型贡献度有误差的问题，其滑坡易发性预测精度更高，更加合适区域滑坡易发性预测建模。本文研究为机器学习预测滑坡易发性的负样本采样方法提供了新思路。
Abstract:For the landslide susceptibility prediction (LSP) based on machine learning (ML) models, the reasonable selection of negative samples has an important influence on the LSP performance. Generally, the main selection methods include randomly selecting from the whole study area or from the specific attribute areas such as low slopes. The negative samples selected by the above methods are often inaccurate or biased, resulting in low accuracy and low reliability of LSP. To solve this problem, the coupling model of ML and information value (IV) method was proposed for LSP. Taking Ruijin City as the study area, the attribute values of the environmental factors were transformed into the IV values of the contribution to the landslide to obtain the very low and low susceptibility areas. The negative samples were randomly selected in the above areas for the training and validation of machine learning models. The new coupling models of IV–SVM and IV–RF were constructed for the LSP of Ruijin. Further, IV–SVM and IV–RF models were compared with the single SVM and RF model with negative samples randomly selected from the whole study area, as well as the low-slope SVM and RF model with negative samples randomly selected from specific attribute areas with a slope less than 2°. Finally, Kappa coefficient (KC) and receiver operating characteristic (ROC) curve were used to verify and compare the modeling results. The AUC values of the ROC curve and KC of IV–SVM and IV–RF models were 0.828, 0.920 and 0.876, 0.988, which were higher than those of single SVM, RF model and low-slope SVM, RF model, respectively. Meanwhile, IV–SVM and IV–RF models have a smaller mean value and larger standard deviation of a susceptibility probability distribution. Results showed that: 1) IV–SVM and IV–RF models had the higher LSP accuracies than those of the single SVM, RF model and low-slope SVM, RF model, respectively; 2) RF model had higher LSP accuracy compared to the SVM model; 3) The coupling model such as IV–RF could address the inaccuracy of negative sample sampling existing in the single model and the shortcomings of the low slope model in the selection of slope interval, thus improving the LSP accuracy. In conclusion, this study provided a new idea for the negative sample sampling method for LSP using ML models.
keywords: landslide susceptibility prediction negative samples selection information value random forest support vector machine
文章编号：202100808 中图分类号：P642.22 文献标志码：
基金项目:国家自然科学青年基金项目（41807285）；2019年江西省“双千计划”项目（900/2120800004）；东华理工大学2018高层次人才科研启动基金项目（DHTP2018001）
作者简介:第一作者：周晓亭（1989—），女，博士生. 研究方向：环境地质与灾害地质. E-mail：201900818004@ecut.edu.cn;通信作者：吴伟成, E-mail：wuwch@ecut.edu.cn
引用文本：
周晓亭,黄发明,吴伟成,周创兵,曾诗怡,潘李含.基于耦合信息量法选择负样本的区域滑坡易发性预测[J].工程科学与技术,2022,54(3):25-35.
ZHOU Xiaoting,HUANG Faming,WU Weicheng,ZHOU Chuangbing,ZENG Shiyi,PAN Lihan.Regional Landslide Susceptibility Prediction Based on Negative Sample Selected by Coupling Information Value Method[J].Advanced Engineering Sciences,2022,54(3):25-35.
引用文本：
周晓亭,黄发明,吴伟成,周创兵,曾诗怡,潘李含.基于耦合信息量法选择负样本的区域滑坡易发性预测[J].工程科学与技术,2022,54(3):25-35.
ZHOU Xiaoting,HUANG Faming,WU Weicheng,ZHOU Chuangbing,ZENG Shiyi,PAN Lihan.Regional Landslide Susceptibility Prediction Based on Negative Sample Selected by Coupling Information Value Method[J].Advanced Engineering Sciences,2022,54(3):25-35.