Publications by authors named "Motoki Amagasaki"
Article Synopsis
- A deep learning model called CNNsLSTM is introduced for modeling hourly rainfall-runoff by combining a one-dimensional convolutional neural network (1D-CNN) with a long short-term memory (LSTM) network.
- The model processes long-term meteorological data with the CNN while the LSTM focuses on short-term data, using features extracted from the CNN.
- Testing in the Ishikari River watershed showed that CNNsLSTM significantly improved accuracy compared to existing models, achieving a higher Nash-Sutcliffe efficiency and reducing root mean square error (RMSE) across a variety of approaches.
This study investigates the relationships which deep learning methods can identify between the input and output data. As a case study, rainfall-runoff modeling in a snow-dominated watershed by means of a long short-term memory (LSTM) network is selected. Daily precipitation and mean air temperature were used as model input to estimate daily flow discharge.
View Article and Find Full Text PDFIn this study, a coastal sea level estimation model was developed at an hourly temporal scale using the long short-term memory (LSTM) network, which is a type of recurrent neural networks. The model incorporates the effects of various phenomena on the coastal sea level such as the gravitational attractions of the sun and the moon, seasonality, storm surges, and changing climate. The relative positions of the moon and the sun from the target location at each hour were utilized to reflect the gravitational attractions of the sun and the moon in the model simulation.
View Article and Find Full Text PDF