Figure 6 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Examples of image segmentation during flooding conditions for cameras 1 (top) and 3 (bottom), showing the occurrence of false positives when the CNN mislabels wet sand as water. The red line superimposed on the CNN prediction represents the actual extension of water measured manually (center panels).
Source publication
The frequency and intensity of coastal flooding is expected to accelerate in low-elevation coastal areas due to sea level rise. Coastal flooding due to wave runup affects coastal ecosystems and infrastructure, however it can be difficult to monitor in remote and vulnerable areas. Here we use a camera-based system to monitor wave runup as part of th...
Context in source publication
Context 1
... 2% error in the fraction of true positives, as given by δb, which suggests most of 170 the CNN uncertainty comes from false positives. Indeed, the average fraction of false positives (r − b) is about 22% as some regions have been mislabeled as water instead of background, for example, some frosts, wooden pieces, or wet sand areas nearby water (Fig. 6). One likely explanation is that the algorithm is trained in a manner that it tries to avoid false negatives while still allowing for false positives. ...
Similar publications
The frequency and intensity of coastal flooding is expected to accelerate in low-elevation coastal areas due to sea level rise. Coastal flooding due to wave overtopping affects coastal communities and infrastructure; however, it can be difficult to monitor in remote and vulnerable areas. Here we use a camera-based system to measure beach and back-b...
Citations
... We chose the Deeplab v3+ architecture, which incorporates a Resnet-18 model pretrained on ImageNet, to form the backbone of our CNN analysis for semantic segmentation. Of the 156 high-quality images, we used 132 to train Resnet-18, following previous studies that indicated over 100 images sufficient for reliable semantic segmentation prediction via transfer learning [19]. ...
Coastal erosion due to extreme events can cause significant damage to coastal communities and deplete beaches. Post-storm beach recovery is a crucial natural process that rebuilds coastal morphology and reintroduces eroded sediment to the subaerial beach. However, monitoring the beach recovery, which occurs at various spatiotemporal scales, presents a significant challenge. This is due to, firstly, the complex interplay between factors such as storm-induced erosion, sediment availability, local topography, and wave and wind-driven sand transport; secondly, the complex morphology of coastal areas, where water, sand, debris and vegetation co-exists dynamically; and, finally, the challenging weather conditions affecting the long-term small-scale data acquisition needed to monitor the recovery process. This complexity hinders our understanding and effective management of coastal vulnerability and resilience. In this study, we apply Convolutional Neural Networks (CNN)-based semantic segmentation to high-resolution complex beach imagery. This model efficiently distinguishes between various features indicative of coastal processes, including sand texture, water content, debris, and vegetation with a mean precision of 95.1% and mean Intersection of Union (IOU) of 86.7%. Furthermore, we propose a new method to quantify false positives and negatives that allows a reliable estimation of the model’s uncertainty in the absence of a ground truth to validate the model predictions. This method is particularly effective in scenarios where the boundaries between classes are not clearly defined. We also discuss how to identify blurry beach images in advance of semantic segmentation prediction, as our model is less effective at predicting this type of image. By examining how different beach regions evolve over time through time series analysis, we discovered that rare events of wind-driven (aeolian) sand transport seem to play a crucial role in promoting the vertical growth of beaches and thus driving the beach recovery process.
