当前位置: X-MOL 学术Bull. Eng. Geol. Environ. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Landslide spatial probability prediction: a comparative assessment of naïve Bayes, ensemble learning, and deep learning approaches
Bulletin of Engineering Geology and the Environment ( IF 4.2 ) Pub Date : 2021-04-08 , DOI: 10.1007/s10064-021-02194-6
Ba-Quang-Vinh Nguyen , Yun-Tae Kim

The aim of this study is to evaluate and compare the performances of 5 machine learning (ML) techniques for predicting the spatial probability of landslide at Atsuma, Japan, and Mt. Umyeon, Korea. 5 ML models used are Naïve Bayes (NB), ensemble learning (random forest (RF) and adaboost (AB)), and deep learning (multilayer perceptron (MLP) and convolutional neural network (CNN)) models. Real landslide events at the study areas are randomly separated to the training set for landslide mapping and the validation set for assessing performance. To assess the performance of the used models, the resulting models are validated using receiver operating characteristic (ROC) curve. The success rate curves show that the areas under the curve (AUC) for the NB, RF, AB, MLP, and CNN are 85.1, 88.8, 88.6, 87.5, and 95.0%, respectively, at Atsuma and 68.7, 85.6, 90.5, 81.6, and 92.0%, respectively, at Mt. Umyeon. Similarly, the validation results show that the areas under the curve for the NB, RF, AB, MLP, and CNN are 84.3, 87.1, 87.1, 86.7, and 89.7%, respectively, at Atsuma and 64.9, 85.5, 83.9, 84.7, and 90.5%, respectively, at Mt. Umyeon. In addition, statistical tests such as Chi-square test and difference of proportions test show that all classified landslide susceptibility maps have statistical significance and the significant difference in classified landslide susceptibility maps from different ML models. The comparison results among 5 ML models show that the CNN model had the best performance and NB model had the worst performance in both study areas.



中文翻译:

滑坡空间概率预测:朴素贝叶斯,集成学习和深度学习方法的比较评估

这项研究的目的是评估和比较5种机器学习(ML)技术的性能,这些技术用于预测日本的Atsuma,Mt和Mt的滑坡的空间概率。韩国Umyeon。使用的5种ML模型是朴素贝叶斯(NB),集成学习(随机森林(RF)和adaboost(AB))和深度学习(多层感知器(MLP)和卷积神经网络(CNN))模型。研究区域中的真实滑坡事件被随机分为用于滑坡测绘的训练集和用于评估性能的验证集。为了评估所用模型的性能,使用接收器工作特性(ROC)曲线对所得模型进行了验证。成功率曲线显示,NB,RF,AB,MLP和CNN的曲线下面积(AUC)分别在Atsuma和68.7、85.6、90处分别为85.1%,88.8、88.6、87.5和95.0%。分别为5、81.6和92.0%。雨妍 同样,验证结果表明,NB,RF,AB,MLP和CNN的曲线下面积分别为Atsuma和64.9、85.5、83.9、84.7、84.3、87.1、87.1、86.7和89.7%,和90.5%,分别在山。雨妍 此外,卡方检验和比例差异检验等统计检验表明,所有分类的滑坡敏感性图均具有统计意义,不同ML模型的分类滑坡敏感性图具有显着差异。5个ML模型之间的比较结果表明,在两个研究领域中,CNN模型的性能最佳,而NB模型的性能最差。CNS和CNN在Atsuma分别为84.3、87.1、87.1、86.7和89.7%,在Mt.分别为64.9、85.5、83.9、84.7和90.5%。雨妍 此外,卡方检验和比例差异检验等统计检验表明,所有分类的滑坡敏感性图均具有统计意义,不同ML模型的分类滑坡敏感性图具有显着差异。5个ML模型之间的比较结果表明,在两个研究领域中,CNN模型的性能最佳,而NB模型的性能最差。CNS和CNN在Atsuma分别为84.3、87.1、87.1、86.7和89.7%,在Mt.分别为64.9、85.5、83.9、84.7和90.5%。雨妍 此外,卡方检验和比例差异检验等统计检验表明,所有分类的滑坡敏感性图均具有统计意义,不同ML模型的分类滑坡敏感性图具有显着差异。5个ML模型之间的比较结果表明,在两个研究领域中,CNN模型的性能最佳,而NB模型的性能最差。卡方检验和比例差异检验等统计检验表明,所有分类滑坡敏感性图均具有统计意义,不同ML模型分类滑坡敏感性图的显着性差异。5个ML模型之间的比较结果表明,在两个研究领域中,CNN模型的性能最佳,而NB模型的性能最差。卡方检验和比例差异检验等统计检验表明,所有分类滑坡敏感性图均具有统计意义,不同ML模型分类滑坡敏感性图的显着性差异。5个ML模型之间的比较结果表明,在两个研究领域中,CNN模型的性能最佳,而NB模型的性能最差。

更新日期:2021-04-08
down
wechat
bug