RIP CURRENT DETECTION IN AN OPEN AREA AND ALONG JETTY USING AI
ICCE 2022
PDF (Inglés)

Cómo citar

RIP CURRENT DETECTION IN AN OPEN AREA AND ALONG JETTY USING AI. (2023). Coastal Engineering Proceedings, 37, papers.7. https://doi.org/10.9753/icce.v37.papers.7

Resumen

The occurrence of drowning accidents on beaches is mainly caused by rip currents. In this study, we created a single AI model that can detect two types of rip currents with different characteristics: a flash rip current that occurs intermittently in open areas, and a fixed rip current that occurs along jetty. As a result of creating the AI model under various conditions, it was possible to detect the rip currents at each location with high accuracy at the stage of making the AI model. At the final point of the model’s evolution, the accuracy, the precision and the recall rates of the rip current detection were 87 percent, 48 percent and 100 percent, respectively. As a result of actually operating this AI model on the study beach, the single AI model could detect rip currents along the jetty and in the open area. However, it was confirmed that the AI model could not detect all rip currents which were continuously generated along the jetty.
PDF (Inglés)

Referencias

Brighton, B., Sherker, S., Brander, R., Thompson, M., & Bradstreet, A. 2013. “Rip current related

drowning deaths and rescues in Australia 2004-2011.” Natural. Hazards and Earth System

Sciences, 13, 1069-1075.

Ishikawa, T., Komine, T., Aoki, S. and Okabe, T. 2014. Characteristics of Rip Current Drowning on

the Shores of Japan, Journal of Coastal Research, Special Issue 72, 44-49.

Ishikawa, T., Shimada, R., Sawagashira, R. and Komine, T. 2021. Proposal and Verification of Rip

Current Detection using AI, Coastal Dynamics 2021 Conference proceedings.

https://repository.tudelft.nl/islandora/object/uuid%3A8859f64c-2204-455d-a9a7-dfdacc4c2117

Lippmann, T. C. and Holman, R. A. 1989. Quantification of Sand Bar Morphology; A Video

Technique Based on Wave Dissipation, JGR, Vol.94, pp.995-1011, 1989.

Redmon, J. and Farhadi, A. 2017. “Yolo9000: Better, faster, stronger.” In Computer Vision and Pattern

Recognition (CVPR), IEEE Conference, 6517-6525.

Shimada, R., Ishikawa, T., Ryosuke, S., Komine, T. 2022. Study of Method for Detecting Occurrence

of Rip Current Using Image Analysis, Proc. JSCE, B3 (Ocean engineering), Vol.78, I_229-I_234.

Creative Commons License

Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0.

Derechos de autor 2023 Toshinori Ishikawa, Ryo Shimada, Tsutomu Komine