3D semantic labeling is a fundamental task in airborne laser scanning (ALS) point clouds processing. The complexity of observed scenes and the irregularity of point distributions make this task quite challenging. Existing methods rely on a large number of features for the LiDAR points and the interaction of neighboring points, but cannot exploit the potential of them. In this paper, a convolutional neural network (CNN) based method that extracts the high-level representation of features is used. A point-based feature image-generation method is proposed that transforms the 3D neighborhood features of a point into a 2D image. First, for each point in the ALS data, the local geometric features, global geometric features and full-waveform features of its neighboring points within a window are extracted and transformed into an image. Then, the feature images are treated as the input of a CNN model for a 3D semantic labeling task. Finally, to allow performance comparisons with existing approaches, we evaluate our framework on the publicly available datasets provided by the International Society for Photogrammetry and Remote Sensing Working Groups II/4 (ISPRS WG II/4) benchmark tests on 3D labeling. The experiment results achieve 82.3% overall accuracy, which is the best among all considered methods.

Injection‐induced seismicity is thought to be due primarily to increase in fluid pore pressure, which reduces the shear strength of a nearby fault. We address the modeling and prediction of the hydromechanical response due to fluid injection, mainly as wastewater disposal. We consider the full poroelastic effects, including the changes in porosity and permeability of the medium due to changes in local volumetric strains. Our results consider effects of the fault architecture (low‐permeability fault core and anisotropic high‐permeability damage zones) on the pressure diffusion and the fault poroelastic response. We show that the high‐permeable damage zone, the poroelastic response, and the permeability evolution can accelerate the pore pressure diffusion process during and after wastewater injection. By studying a geologically based model of the Guy‐Greenbrier fault and of the earthquake sequence induced along it in Arkansas, United States, from October 2010 to July 2011, we show that the existence of highly permeable damage zones facilitates the pressure diffusion and results in a sharp increase in pore pressure at levels much deeper than the injection wells, while the anisotropic permeability in the damage zone can act as a barrier to cross‐fault fluid flow. Furthermore, by computing the change ΔCFS of Coulomb failure stress, our simulations show that ΔCFS increases starting from the top of the Guy‐Greenbrier fault and then propagates toward greater depth and toward the southwest direction, which is consistent with the seismicity migration.

The classification of point clouds is a basic task in airborne laser scanning (ALS) point cloud processing. It is quite a challenge when facing complex observed scenes and irregular point distributions. In order to reduce the computational burden of the point-based classification method and improve the classification accuracy, we present a segmentation and multi-scale convolutional neural network-based classification method. Firstly, a three-step region-growing segmentation method was proposed to reduce both under-segmentation and over-segmentation. Then, a feature image generation method was used to transform the 3D neighborhood features of a point into a 2D image. Finally, feature images were treated as the input of a multi-scale convolutional neural network for training and testing tasks. In order to obtain performance comparisons with existing approaches, we evaluated our framework using the International Society for Photogrammetry and Remote Sensing Working Groups II/4 (ISPRS WG II/4) 3D labeling benchmark tests. The experiment result, which achieved 84.9% overall accuracy and 69.2% of average F1 scores, has a satisfactory performance over all participating approaches analyzed.