River Water Level Prediction Using a Deep Neural Network

• 발행기관: 한국방재학회
• 저자명: Le Xuan Hien Lee Giha
• 간행물 정보: 『3. 한국방재학회 학술대회논문집』2018년, 352~353쪽, 전체 2쪽
• 주제분류: 공학 > 기타공학
• 파일형태: PDF
• 발행일자: 2018.02.27

영문 초록

In this article, we aim to introduce a simple yet very efficient data-driven model based on a deep neural network model, LSTM (Long Short Term Memory) to predict the river water level at Okcheon Station of the Guem River without utilization of rainfall - forecast information. The proposed model is based only on the observed water levels at 4 stations: upstream stations (Sutong, Hotan and Songcheon) and the forecasting-target station (Okcheon). For LSTM modeling, hourly water level data at the 4 stations were collected for 15 years from 2002 to 2016. The proposed model uses an open source software library: TensorFlow, developed for the purposes of conducting very complex machine learning and deep neural network applications. However, the system is general enough to be applicable in a wide variety of other domains as well. The LSTM model was formulated to predict Okcheon Station water level for many cases from 3 hours to 24 hours of lead time. Although the model does not require many input data such as climate, geography, land-use for rainfall-runoff simulation the prediction is very stable and reliable up to 9 hours of lead time: the Nash - Sutcliffe efficiency (NSE) is higher than 0.90 and the root mean square error (RMSE) is lower than 12cm for the cases of 3, 6 and 9 hours of lead time prediction. The analysis indicated that the LSTM model is able to produce the river water level time series and be applicable for the practical flood forecasting instead of hydrologic modeling approaches.

키워드

data-driven model deep neural network LSTM Tensorflow water level prediction