4.7 Article

Landslide Detection Mapping Employing CNN, ResNet, and DenseNet in the Three Gorges Reservoir, China

出版社

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSTARS.2021.3117975

关键词

Terrain factors; Reservoirs; Convolutional neural networks; Soil; Indexes; Training; Rivers; Deep neural network; dense convolutional neural network (DenseNet); feature selection; landslide detection; Three Gorges Reservoir (TGR)

资金

  1. National Natural Science Foundation of China [62071439, 61871259]
  2. Opening Foundation of Qilian Mountain National Park Research Center (Qinghai) [GKQ2019-01]
  3. Opening Foundation of Beijing Key Laboratory of Urban Spatial Information Engineering [20210209]
  4. Opening Foundation of Geomatics Technology and Application Key Laboratory of Qinghai Province [QHDX-2019-01]

向作者/读者索取更多资源

In this study, an accurate Landslide Detection Mapping (LDM) model was constructed based on convolutional neural networks, residual neural networks, and DenseNets, considering ZY-3 high spatial resolution data and conditioning factors. The experimental results demonstrated that these models performed well, with accuracy above 0.95. DenseNet incorporating RS images and CFs outperformed other models in terms of evaluation metrics, with improvements in Kappa coefficients and ACC. Elevation factor was identified as the most important factor in the landslide model construction experiment.
Landslide detection mapping (LDM) is the basis of the field of landslide disaster prevention; however, it has faced certain difficulties. The Three Gorges Reservoir area of the Yangtze River has been one of the most intensively evaluated areas for landslide prevention in the world, due to the high frequency of landslide disasters here. In this article, we constructed an accurate LDM model based on convolutional neural networks, residual neural networks, and dense convolutional neural networks (DenseNets) that considers ZY-3 high spatial resolution (HSR) data and conditioning factors (CFs). In this article, 19 factors based on remote sensing (RS) images, topographical and geological data associated with historical landslide locations were randomly divided into training (70% of total) and testing (30%) datasets. The experimental results show that the accuracy (ACC) of these three LDM models is above 0.95, indicating that the deep neural networks aimed at landslide detection performed well. Furthermore, DenseNet with RS images and CFs can accurately detect landslides. Specifically, DenseNet with RS images and CFs outperforms the other five models by considering the evaluation metrics, which exhibited Kappa coefficient improvements of 0.01-0.04 and ACC improvements of 0.02-0.3%. Among all the factors, elevation factor has a high importance of 0.727, which is the most important factors found in this landslide model construction experiment.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据