Resumen de Rip Current: A Potential Hazard Zones Detection in SaintMartin’s Island using Deep Learning and Machine LearningApproach
Md. Ariful Islam, Mosa. Tania Alim Shampa
Rip current, or reverse current of the sea, is a type of wave that pushes against the shore and movesin the opposite direction, that is, towards the deep sea. The research suggests an approach for somethinglike the automatic detection of rip currents with waves crashing based on convolutional neural networks(CNNs) and machine learning algorithms (MLAs) for classification. Security cameras can be placed at anyelevated position around the beach near the coastguard’s office, and mobile phones from a certain heighthave still images of something like the shoreline and represent a possible cause of rip current measurementsand management to handle this hazard appropriately. This work is about using CNN and MLAs to builddetection systems from still beach images, bathymetric images, and beach parameters. The CNN-baseddetection model for beach images and bathymetric images has already been put into place. MLAs have beenapplied to detect rip currents based on beach parameters. Compared to other detection models, detectionmodels based on bathymetric images are much more accurate and precise. The VGG16 model of CNN showsa maximum accuracy of 91.13% (recall = 0.94, F1-score = 0.87) for beach images. For the bathymetricimages, the best performance has been found with an accuracy of 96.89% (recall = 0.97, F1-score = 0.92)for the DenseNet model of CNN. The MLA-based model shows an accuracy of 86.98% (recall = 0.89, F1-score = 0.90) for the random forest classifier. Once the potential zone of continuously generating rip currenthas been identified, the coastal region can be managed accordingly to prevent accidents due to this coastalhazard.
