Different sampling strategies for predicting landslide susceptibilities are deemed less consequential with deep learning
Different sampling strategies for predicting landslide susceptibilities are deemed less consequential with deep learning
复制标题
DOI：
10.1016/j.scitotenv.2020.137320
复制
发表时间：
2020-06-10
影响因子：
9.8
通讯作者：
Yamagishi, Hiromitsu
中科院分区：
文献类型：
--
作者：
Dou, Jie;Yunus, Ali P.;Yamagishi, Hiromitsu
假设滑坡易感性的预测能力随着不同的抽样技术而有所不同，例如(A)滑坡陡坎质心，(B)滑坡体质心，(C)代表陡坡多边形的碎屑区域样本，以及(D)代表整个滑坡体的滑坡体样本。然而，统计学和机器学习算法的新进展不断更新滑坡易感性范例。随着人工智能应用的日益广泛，本文探讨了不同抽样技术在滑坡易感性制图中的预测能力。我们使用Logistic回归(LR)、神经网络(NNET)和深度学习神经网络(DNN)模型对模型进行测试和验证。这些测试应用于2018年北海道地震受灾地区，使用了一组11个预测变量(地震、地形和水文)。我们发现，无论抽样技术如何(AuC：0.904-0.919)，DNN模型的预测率都是不重要的。然而，使用LR(AuC：0.825-0.785)和NNet(AuC：0.882-0.858)进行测试，在四个数据集之间的精度方面产生了更大的差异。尽管如此，在滑坡陡坡区内的样本获得了最高的成功率。这一类比随后被发布的2015年高尔卡地震的滑坡清单所验证。因此，我们建议DNN模型作为一种适当的技术来提高滑坡易感性的预测性能，如果在清单中没有正确地描述滑坡陡坎和坡体的话。(C)2020爱思唯尔B.V.保留所有权利。
Predictive capability of landslide susceptibilities is assumed to be varied with different sampling techniques, such as (a) the landslide scarp centroid, (b) centroid of landslide body, (c) samples of the scrap region representing the scarp polygon, and (d) samples of the landslide body representing the entire landslide body. However, new advancements in statistical and machine learning algorithms continuously being updated the landslide susceptibility paradigm. This paper explores the predictive performance power of different sampling techniques in landslide susceptibility mapping in the wake of increased usage of artificial intelligence. We used logistic regression (LR), neural network (NNET), and deep learning neural network (DNN) model for testing and validation of the models. The tests were applied to the 2018 Hokkaido Earthquake affected areas using a set of 11 predictor variables (seismic, topographic, and hydrological). We found that the prediction rates are inconsequential with the DNN model irrespective of the sampling technique (AUC: 0.904 - 0.919). Whereas, testing with LR (AUC: 0.825 - 0.785) and NNET (AUC: 0.882 - 0.858) produces larger differences in the accuracies between the four datasets. Nonetheless, the highest success rates were obtained for samples within the landslide scarp area. The analogy was then validated with a published landslide inventory from the 2015 Gorkha earthquake. We, therefore, suggest that DNN models as an appropriate technique to increase the predictive performance of landslide susceptibilities if the landslide scarp and body are not characterized properly in an inventory. (C) 2020 Elsevier B.V. All rights reserved.