NEURAL NETWORK MODEL FOR IDENTIFYING THE COASTAL SAND AREA USING THE AERIAL PHOTOGRAPHS PICTURED BY UAV
PDF

How to Cite

Sato, D. (2020). NEURAL NETWORK MODEL FOR IDENTIFYING THE COASTAL SAND AREA USING THE AERIAL PHOTOGRAPHS PICTURED BY UAV. Coastal Engineering Proceedings, (36v), sediment.10. https://doi.org/10.9753/icce.v36v.sediment.10

Abstract

Small island states formed by atolls such as Marshall Islands, Kiribati and Tuvalu require useful and efficiency method of coastal monitoring for coastal management because of lack of human resources and budget. In atoll islands, the identification of shape of sandy beach and temporally accumulation area of sand has high importance in coastal management. In this study, neural network model to classify the aerial photographs pictured by UAV was established for identifying the sand area in the coastal zone of Fongafale island in Funafuti atoll, Tuvalu. Photographs of coastal sediments especially sand, in Fongafale island were collected by digital camera. These photographs were used to make the data set for training and testing of the constructed neural network model. Additionally, aerial photographs pictured by UAV were collected to apply to the constructed neural network model. In this study the convolution neural network was constructed to classify the aerial photographs.

Recorded Presentation from the vICCE (YouTube Link): https://youtu.be/trHQOmsFpD4
https://doi.org/10.9753/icce.v36v.sediment.10
PDF
Authors retain copyright and grant the Proceedings right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this Proceedings.