Visual examination of the workplace and in‐time reminder to the failure of wearing a safety helmet is of particular importance to avoid injuries of workers at the construction site. Video monitoring systems provide a large amount of unstructured image data on‐site for this purpose, however, requiring a computer vision‐based automatic solution for real‐time detection. Although a growing body of literature has developed many deep learning‐based models to detect helmet for the traffic surveillance aspect, an appropriate solution for the industry application is less discussed in view of the complex scene on the construction site. In this regard, we develop a deep learning‐based method for the real‐time detection of a safety helmet at the construction site. The presented method uses the SSD‐MobileNet algorithm that is based on convolutional neural networks. A dataset containing 3261 images of safety helmets collected from two sources, i.e., manual capture from the video monitoring system at the workplace and open images obtained using web crawler technology, is established and released to the public. The image set is divided into a training set, validation set, and test set, with a sampling ratio of nearly 8 : 1 : 1. The experiment results demonstrate that the presented deep learning‐based model using the SSD‐MobileNet algorithm is capable of detecting the unsafe operation of failure of wearing a helmet at the construction site, with satisfactory accuracy and efficiency.

Landslides pose a serious threat to the safety of human life and property in mountainous regions. Susceptibility assessment for landslides is critical in landslide management strategy. Recent studies indicate that the traditional assessment models in many previous studies commonly assume a fixed relationship between influencing factors and landslide occurrence within an area, resulting in an inadequate evaluation for the local landslides susceptibility. To address this issue, in this paper we propose a spatial proximity-based geographically weighted regression (S-GWR) model considering spatial non-stationarity of landslide data for assessing the landslide susceptibility. Spatial proximity is the basic input condition for the proposed S-GWR model. The challenge lies in defining the spatial proximity expression that shows the geographical features of landslides and therefore affects the model ability of S-GWR. Our solution chooses the slope unit as spatial adjacency, rather than the grid unit in DTM. The multicollinearity between landslide influencing factors is then eliminated through variance inflation factor (VIF) method and principal component analysis (PCA). The proposed model is subsequently validated by using data in Qingchuan County, southwestern China. Spatial non-stationary is identified for landslide data. A comparison with grid unit and four traditional evaluation models is conducted. Validation results using the area under the ROC (receiver operating characteristic) curve and success rate curve indicate that the spatial proximity-based GWR model with slope unit has the highest predictive accuracy (0.859 and 0.850 respectively).

The Sichuan-Tibet Railway (STR) in China is of profound significance for Tibet's long-term development. Construction of railway reshapes the landscape it passes through and consequently influences the geological hazard risk. Despite the importance of railway construction, there remains a paucity of previous studies involving this factor. In this paper, we make a straightforward development on our previous study that a novel index system, notably considering the effect of railway construction is proposed for geological hazard assessment. Different from regional assessment, the concept of the line element is introduced, and the geological hazard risk along STR is comprehensively evaluated using matter-element extension model (MEEM), gray correlation model (GCM), and support vector machine (SVM). Receiver operating characteristic curve (ROC) analysis demonstrates that SVM performs better among the models. Results further indicate that a reduced performance of SVM in the ROC test appears to accompany with the absence of the construction factor. This finding highlights the essential role of construction in geological hazard assessment for the railway.

The China–Pakistan Economic Corridor (CPEC) project passes through the Karakoram Highway in northern Pakistan, which is one of the most hazardous regions of the world. The most common hazards in this region are landslides and debris flows, which result in loss of life and severe infrastructure damage every year. This study assessed geohazards (landslides and debris flows) and developed susceptibility maps by considering four standalone machine-learning and statistical approaches, namely, Logistic Regression (LR), Shannon Entropy (SE), Weights-of-Evidence (WoE), and Frequency Ratio (FR) models. To this end, geohazard inventories were prepared using remote sensing techniques with field observations and historical hazard datasets. The spatial relationship of thirteen conditioning factors, namely, slope (degree), distance to faults, geology, elevation, distance to rivers, slope aspect, distance to road, annual mean rainfall, normalized difference vegetation index, profile curvature, stream power index, topographic wetness index, and land cover, with hazard distribution was analyzed. The results showed that faults, slope angles, elevation, lithology, land cover, and mean annual rainfall play a key role in controlling the spatial distribution of geohazards in the study area. The final susceptibility maps were validated against ground truth points and by plotting Area Under the Receiver Operating Characteristic (AUROC) curves. According to the AUROC curves, the success rates of the LR, WoE, FR, and SE models were 85.30%, 76.00, 74.60%, and 71.40%, and their prediction rates were 83.10%, 75.00%, 73.50%, and 70.10%, respectively; these values show higher performance of LR over the other three models. Furthermore, 11.19%, 9.24%, 10.18%, 39.14%, and 30.25% of the areas corresponded to classes of very-high, high, moderate, low, and very-low susceptibility, respectively. The developed geohazard susceptibility map can be used by relevant government officials for the smooth implementation of the CPEC project at the regional scale.