Abstract. 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 the after-storm recovery of an eroded beach on the Texas coast. We analyze high-temporal resolution images of the beach using Convolutional Neural Network (CNN)-based semantic segmentation to study the stochastic properties of runup-driven flooding events. In the first part of this work, we focus on the application of semantic segmentation to identify water and runup events. We train and validate a CNN with over 500 manually classified images, and introduce a post-processing method to reduce false positives. We find that the accuracy of CNN predictions of water pixels is around 90% and strongly depend on the number and diversity of images used for training.

Abstract. Low-intensity but high-frequency coastal flooding, also known as nuisance flooding, can negatively affect low-lying coastal communities with potentially large socioeconomic effects. This flooding also can greatly affect post-storm coastal dune recovery and reduce the long-term resilience of the back-barrier ecosystem. Recent analytical work has hypothesized that these frequent flooding events are uncorrelated in time and can be modeled as a marked Poisson process with exponentially distributed sizes, a result with important implications for the prediction of coastal flooding. Here we test this proposition using high-temporal-resolution field measurements of an eroding beach on the Texas coast. A time series of the flooded area was obtained from pictures using Convolutional Neural Network (CNN)-based semantic segmentation methods. After defining the flooding events using a peak-over-threshold method, we found that the size of the flooding events indeed followed an exponential distribution as hypothesized. Furthermore, the flooding events were uncorrelated with one another at daily time scales, but correlated at hourly time scales. Finally, we found relatively good statistical agreement between our CNN-based empirical flooding data and run-up predictions. Our results formalize the first probabilistic model of coastal flooding events driven by wave run-up which can be used in coastal risk management and landscape evolution models.

No abstract