Automatic Segmentation of Sinkholes Using a Convolutional Neural Network
Automatic Segmentation of Sinkholes Using a Convolutional Neural Network
复制标题
DOI：
10.1029/2021ea002195
复制
发表时间：
2021-12
影响因子：
3.1
通讯作者：
M. U. Rafique;Junfeng Zhu;Nathan Jacobs
中科院分区：
文献类型：
--
作者：
M. U. Rafique;Junfeng Zhu;Nathan Jacobs
天坑是世界范围内岩溶地区最丰富的地表特征。了解天坑的发生和特征对于研究岩溶含水层和减轻天坑相关危害至关重要。大多数天坑出现在陆地表面的凹陷或覆盖塌陷，通常是从高程数据，如数字高程模型（DEM）映射。从DEM中识别天坑的现有方法通常需要两个步骤：定位表面凹陷和将天坑与非天坑凹陷分离。在这项研究中，我们探索了深度学习，以直接从DEM数据和航空图像中识别天坑。我们的研究的一个关键贡献是评估这两种类型的栅格数据集成的各种方式。我们使用图像分割模型U-Net来定位天坑。我们基于四个输入的高程数据图像训练了单独的U-Net模型：DEM图像、坡度图像、DEM梯度图像和DEM阴影地貌图像。三种归一化技术（全局，高斯和实例）被应用于提高模型性能。模型结果表明，深度学习是一种直接从高程数据图像中识别天坑的可行方法。特别是，DEM梯度数据为U‐net图像分割模型提供了最佳输入，以定位天坑。使用高斯归一化的DEM梯度图像的模型在看不见的测试集上实现了最佳性能，其天坑交叉联合（IoU）为45.38%。然而，航拍图像在训练天坑的深度学习模型时并不有用，因为使用航拍图像作为输入的模型实现了低于3%的天坑IoU。
Sinkholes are the most abundant surface features in karst areas worldwide. Understanding sinkhole occurrences and characteristics is critical for studying karst aquifers and mitigating sinkhole‐related hazards. Most sinkholes appear on the land surface as depressions or cover collapses and are commonly mapped from elevation data, such as digital elevation models (DEMs). Existing methods for identifying sinkholes from DEMs often require two steps: locating surface depressions and separating sinkholes from non‐sinkhole depressions. In this study, we explored deep learning to directly identify sinkholes from DEM data and aerial imagery. A key contribution of our study is an evaluation of various ways of integrating these two types of raster data. We used an image segmentation model, U‐Net, to locate sinkholes. We trained separate U‐Net models based on four input images of elevation data: a DEM image, a slope image, a DEM gradient image, and a DEM‐shaded relief image. Three normalization techniques (Global, Gaussian, and Instance) were applied to improve the model performance. Model results suggest that deep learning is a viable method to identify sinkholes directly from the images of elevation data. In particular, DEM gradient data provided the best input for U‐net image segmentation models to locate sinkholes. The model using the DEM gradient image with Gaussian normalization achieved the best performance with a sinkhole intersection‐over‐union (IoU) of 45.38% on the unseen test set. Aerial images, however, were not useful in training deep learning models for sinkholes as the models using an aerial image as input achieved sinkhole IoUs below 3%.