Search

A rip current is a strong, localized current of water which moves along and away from the shore. Recent studies have suggested that drownings due to rip currents are still a major threat to beach safety. Identification of rip currents is important for lifeguards when making decisions on where to designate patrolled areas. The public also require information while deciding where to swim when lifeguards are not on patrol. In the present study we present an artificial intelligence (AI) algorithm that both identifies whether a rip current exists in images/video, and also localizes where that rip current occurs. While there have been some significant advances in AI for rip current detection and localization, there is a lack of research ensuring that an AI algorithm can generalize well to a diverse range of coastal environments and marine conditions. The present study made use of an interpretable AI method, gradient-weighted class-activation maps (Grad-CAM), which is a novel approach for amorphous rip current detection. The training data/images were diverse and encompass rip currents in a wide variety of environmental settings, ensuring model generalization. An open-access aerial catalogue of rip currents were used for model training. Here, the aerial imagery was also augmented by applying a wide variety of randomized image transformations (e.g., perspective, rotational transforms, and additive noise), which dramatically improves model performance through generalization. To account for diverse environmental settings, a synthetically generated training set, containing fog, shadows, and rain, was also added to the rip current images, thus increased the training dataset approximately 10-fold. Interpretable AI has dramatically improved the accuracy of unbounded rip current detection, which can correctly classify and localize rip currents about 89% of the time when validated on independent videos from surf-cameras at oblique angles. The novelty also lies in the ability to capture some shape characteristics of the amorphous rip current structure without the need of a predefined bounding box, therefore enabling the use of remote technology like drones. A comparison with well-established coastal image processing techniques is also presented via a short discussion and easy reference table. The strengths and weaknesses of both methods are highlighted and discussed. [ABSTRACT FROM AUTHOR]

Sea-level rise will cause erosion of land, deeper and increasingly frequent flooding and will eventually permanently inundate low-elevation land, forcing the adaptation of seaside communities to avoid or reduce risk. To inform adaptation planning, we quantified the effects of incremental relative sea-level rise (RSLR) on exposed land area, number and replacement value of buildings within Tauranga Harbour, New Zealand. The assessment compared three coastal hazards: flooding, permanent inundation and erosion. Increasingly frequent coastal flooding will be the dominant trigger for adaptation in Tauranga. In the absence of adaptation, coastal flooding, recurring at least once every 5 years on average, will overtake erosion as the dominant coastal hazard after about 0.15–0.2 m RSLR, which is likely to occur between the years 2038–2062 in New Zealand and will rapidly escalate in frequency and consequence thereafter. Coastal erosion will remain the dominant hazard for the relatively-few properties on high-elevation coastal cliffs. It will take 0.8 m more RSLR for permanent inundation to reach similar impact thresholds to coastal flooding, in terms of the number and value of buildings exposed. For buildings currently within the mapped 1% annual exceedance probability (AEP) zone, the flooding frequency will transition to 20% AEP within 2–3 decades depending on the RSLR rate, requiring prior adaptive action. We also compared the performance of simple static-planar versus complex dynamic models for assessing coastal flooding exposure. Use of the static-planar model could result in sea level thresholds being reached 15–45 years earlier than planned for in this case. This is compelling evidence to use dynamic models to support adaptation planning. [ABSTRACT FROM AUTHOR]