(本网站及其内含博文均有三种语言版本,可在菜单栏地球图标处进行选择)
(This website and all the blog contents in it are available in three language versions, which can be selected from the globe icon on the menu bar)
(このウェブサイト及びその中のすべてのブログコンテンツは3つの言語バージョンがあり、メニューバーの地球アイコンから選択できます。)
Hello there! This is Willis’ personal website. Recently I have found that it is cool to make such a website. I would like to share some interesting things that I have thought or experienced in here.
Now I am affiliated to Gifu University as a researcher and assistant professor. I have taken part in researches related to remote sensing, geographic information system, hydrology and deep learning. Please check my ORCID or ResearchGate page for more detailed academic information from the links in this page.
I am also taking pictures and making video clips as a part of my hobbies. You can see my works from my Bilibili page and public account page of WeChat from the links in this page. Although I am not a professional programmer and still learning about programming, I love writing different kinds of interesting programs using Python. If you have any good idea about programming, feel free to share with me.
Besides, I like challenging works in different fields. I would like to share my challenging experiences in this website later.
PhD in Engineering, 2022
Gifu University
MS in Agricultural and Environmental Science, 2015
Gifu University
BS in Geographical Science, 2012
Inner Mongolia Normal University
Responsibilities include:
Missing observational data pose an unavoidable problem in the hydrological field. Deep learning technology has recently been developing rapidly, and has started to be applied in the hydrological field. Being one of the network architectures used in deep learning, Long Short-Term Memory (LSTM) has been applied largely in related research, such as flood forecasting and discharge prediction, and the performance of an LSTM model has been compared with other deep learning models. Although the tuning of hyperparameters, which influences the performance of an LSTM model, is necessary, no sufficient knowledge has been obtained. In this study, we tuned the hyperparameters of an LSTM model to investigate the influence on the model performance, and tried to obtain a more suitable hyperparameter combination for the imputation of missing discharge data of the Daihachiga River. A traditional method, linear regression with an accuracy of 0.903 in Nash–Sutcliffe Efficiency (NSE), was chosen as the comparison target of the accuracy. The results of most of the trainings that used the discharge data of both neighboring and estimation points had better accuracy than the regression. Imputation of 7 days of the missing period had a minimum value of 0.904 in NSE, and 1 day of the missing period had a lower quartile of 0.922 in NSE. Dropout value indicated a negative correlation with the accuracy. Setting dropout as 0 had the best accuracy, 0.917 in the lower quartile of NSE. When the missing period was 1 day and the number of hidden layers were more than 100, all the compared results had an accuracy of 0.907–0.959 in NSE. Consequently, the case, which used discharge data with backtracked time considering the missing period of 1 day and 7 days and discharge data of adjacent points as input data, indicated better accuracy than other input data combinations. Moreover, the following information is obtained for this LSTM model: 100 hidden layers are better, and dropout and recurrent dropout levels equaling 0 are also better. The obtained optimal combination of hyperparameters exceeded the accuracy of the traditional method of regression analysis.