Examination of predictability of drifting debris accumulation point in Ise Bay by Artificial Neural Network method

Yoshifumi UCHIDA; Kazuhiko HONDA; Hisanori YOSHIMURA; Hajime MASE; Hideki KATO; Mika KATAYAMA; Yasuo YONEZAWA

doi:10.2208/kaigan.67.I_1366

Abstract

In the Ise Bay, there is a problem of drifting debris. This study examines the validity to use an Artificial Neural Network (ANN) for the prediction of collection position of the drifting debris. The ANN model predicting the positions of debris generation and debris accumulation is constructed by checking suitable input data and ANN parameters and transfer function. The resulting ANN gives good predictions: 1) The fit ratio of the drifting debris generation positions is 83%; 2) The fit ratio of drifting debris accumulation positions is more than 50%; and 3) In front of Yokkaichi city and southward of Centrair (The central Japan International Airport) are the main places where drifting debris gathers.

Content from these authors

Favorites & Alerts

Corresponding author

Register with J-STAGE for free!