No abstract

Floods are one of the most often occurring and damaging natural hazards. They impact the society on a massive scale and result in significant damages. To reduce the impact of floods, society needs to keep benefiting from the latest technological innovations. Drones equipped with sensors and latest algorithms (e.g., computer vision and deep learning) have emerged as a potential platform which may be useful for flood monitoring, mapping and detection activities in a more efficient way than current practice. To better understand the scope and recent trends in the domain of drones for flood management, we performed a detailed bibliometric analysis. The intent of performing the bibliometric analysis waws to highlight the important research trends, co-occurrence relationships and patterns to inform the new researchers in this domain. The bibliometric analysis was performed in terms of performance analysis (i.e., publication statistics, citations statistics, top publishing countries, top publishing journals, top publishing institutions, top publishers and top Web of Science (WoS) categories) and science mapping (i.e., citations by country, citations by journals, keyword co-occurrences, co-authorship, co-citations and bibliographic coupling) for a total of 569 records extracted from WoS for the duration 2000–2022. The VOSviewer open source tool has been used for generating the bibliographic network maps. Subjective discussions of the results explain the obtained trends from the bibliometric analysis. In the end, a detailed review of top 28 most recent publications was performed and subjected to process-driven analysis in the context of flood management. The potential active areas of research were also identified for future research in regard to the use of drones for flood monitoring, mapping and detection activities.

Blockage of culverts by transported debris materials is reported as the salient contributor in originating urban flash floods. Conventional hydraulic modeling approaches had no success in addressing the problem primarily because of the unavailability of peak floods hydraulic data and the highly non-linear behavior of debris at the culvert. This article explores a new dimension to investigate the issue by proposing the use of intelligent video analytics (IVA) algorithms for extracting blockage related information. The presented research aims to automate the process of manual visual blockage classification of culverts from a maintenance perspective by remotely applying deep learning models. The potential of using existing convolutional neural network (CNN) algorithms (i.e., DarkNet53, DenseNet121, InceptionResNetV2, InceptionV3, MobileNet, ResNet50, VGG16, EfficientNetB3, NASNet) is investigated over a dataset from three different sources (i.e., images of culvert openings and blockage (ICOB), visual hydrology-lab dataset (VHD), synthetic images of culverts (SIC)) to predict the blockage in a given image. Models were evaluated based on their performance on the test dataset (i.e., accuracy, loss, precision, recall, F1 score, Jaccard Index, region of convergence (ROC) curve), floating point operations per second (FLOPs) and response times to process a single test instance. Furthermore, the performance of deep learning models was benchmarked against conventional machine learning algorithms (i.e., SVM, RF, xgboost). In addition, the idea of classifying deep visual features extracted by CNN models (i.e., ResNet50, MobileNet) using conventional machine learning approaches was also implemented in this article. From the results, NASNet was reported most efficient in classifying the blockage images with the 5-fold accuracy of 85%; however, MobileNet was recommended for the hardware implementation because of its improved response time with 5-fold accuracy comparable to NASNet (i.e., 78%). Comparable performance to standard CNN models was achieved for the case where deep visual features were classified using conventional machine learning approaches. False negative (FN) instances, false positive (FP) instances and CNN layers activation suggested that background noise and oversimplified labelling criteria were two contributing factors in the degraded performance of existing CNN algorithms. A framework for partial automation of the visual blockage classification process was proposed, given that none of the existing models was able to achieve high enough accuracy to completely automate the manual process. In addition, a detection-classification pipeline with higher blockage classification accuracy (i.e., 94%) has been proposed as a potential future direction for practical implementation.

No abstract

No abstract