Author(s): Seongwook Choi; Hyeongsik Kang

Linked Author(s): Hyeongsik Kang, Seongwook Choi

Keywords: Rtificial neural network Adaptive neuro fuzzy inference system Floating debris Dam reservoir

Abstract: In Korea, due to flooding, a large amount of floating debris, including driftwood and household waste, flows into rivers in the summer and accumulates in places where the flow is weak or flows out into the sea. More than 90% of the floating waste flowing in from rivers is made up of deadwood and grass (Jin et al., 2020). The debris accumulated in the river crossing structure or discharged into the ocean blocks sunlight from the water body, destroying the river and marine ecosystem and causing damage to the appearance. In addition, debris easily accumulates around the hydraulic structure and causes problems such as rising flood levels or expanding riverbed scouring, so it is very important to manage the occurrence of debris in the river from the perspective of river and marine management. The research objective is to propose a model that can predict the amount of floating debris generated in the reservoir and to examine the prediction performance. For the study, an artificial neural network (ANN) and adaptive neuro fuzzy inference system (ANFIS) were used, and the collected floating debris data was trained and verified to examine the performance of the model.

DOI:

Year: 2025