Benggang is a typical erosional landform in southern and southeastern China. Since benggang poses significant risks to local ecological environments and economic infrastructure, it is vital to accurately detect benggang-eroded areas. Relying only on remote sensing imagery for benggang detection cannot produce satisfactory results. In this study, we propose integrating high-resolution Digital Orthophoto Map (DOM) and Digital Surface Model (DSM) data for efficient and automatic benggang discovery. The fusion of complementary rich information hidden in both DOM and DSM data is realized by a two-stream convolutional neural network (CNN), which integrates aggregated terrain and activation image features that are both extracted by supervised deep learning. We aggregate local low-level geomorphic features via a supervised diffusion-convolutional embedding branch for expressive representations of benggang terrain variations. Activation image features are obtained from an image-oriented convolutional neural network branch. The two sources of information (DOM and DSM) are fused via a gated neural network, which learns the most discriminative features for the detection of benggang. The evaluation of a challenging benggang dataset demonstrates that our method exceeds several baselines, even with limited training examples. The results show that the fusion of DOM and DSM data is beneficial for benggang detection via supervised convolutional and deep fusion networks.

The automatic identification of construction projects, which can be considered as complex scenes, is a technical challenge for the supervision of soil and water conservation in urban areas. Construction projects in high-resolution remote sensing images have no unified semantic definition, thereby exhibiting significant differences in image features. This paper proposes an identification method for construction projects based on the detection of detailed ground objects, which construction projects comprise, including movable slab houses, buildings under construction, dust screens, and bare soil (rock). To create the training data set, we select highly informative detailed ground objects from high-resolution remote sensing images. Then, the Faster RCNN (region-based convolutional neural network) algorithm is used to detect construction projects and the highly informative detailed ground objects separately. The merging of detection boxes and the correction of detailed ground object combinations are used to jointly improve the confidence of construction project detection results. The empirical experiments show that the accuracy evaluation indicators of this method on a data set of Wuhan construction projects outperform other comparative methods, and its AP value and F1 score reached 0.773 and 0.417, respectively. The proposed method can achieve satisfactory identification results for construction projects with complex scenes, and can be applied to the comprehensive supervision of soil and water conservation in construction projects.

Temporary vegetation measures are the most common methods for reducing soil erosion of spoil heaps during construction; however, their regulatory mechanisms on soil and water loss have not been sufficiently studied. This study compared the impacts of five temporary vegetation measures (turfing 300 cm (TF-300 cm), turfing 75 cm (TF-75 cm), grass seeding 300 cm (GS-300 cm), grass seeding 75 cm (GS-75 cm), and synthetic turf (ST)) on the dynamic processes of runoff and sediment yield as well as hydraulic parameters under simulated rainfall experiments. A 30° bare slope (BS) was set up as the control. The results indicated that (1) all measures delayed the onset of runoff by 57–233%, effectively decreasing the runoff rate and the average erosion rate by 45–49% and 91–99%, respectively; (2) these measures reduced the average Reynolds number by 45–52% and diminished both the average runoff shear force and runoff power by 44–60%; and (3) the effectiveness in reducing runoff and sediment loss ranked as follows: turfing > synthetic turf > grass seeding, When these measures are applied locally to the bottom 25% of the slope, the efficiency of runoff and sediment reduction can exceed 89% for the entire slope. Our findings provide valuable insights for designing temporary vegetation measures in construction.