Dongting Lake Water Level Forecast and Its Relationship with the Three Gorges Dam Based on a Long Short-Term Memory Network

Chen Liang,Mingjun Lei,Qingyun Du,Hongqing Li

doi:10.3390/w10101389

Abstract

To study the Dongting Lake water level variation and its relationship with the upstream Three Gorges Dam (TGD), a deep learning method based on a Long Short-Term Memory (LSTM) network is used to establish a model that predicts the daily water levels of Dongting Lake. Seven factors are used as the input for the LSTM model and eight years of daily data (from 2003 to 2012) are used to train the model. Then, the model is applied to the test dataset (from 2011 to 2013) for forecasting and is evaluated using the root mean squared error (RMSE) and the coefficient of determination (R2). The test shows the LSTM model has better accuracy compared to the support vector machine (SVM) model. Furthermore, the model is adjusted to simulate the situation where the TGD does not exist to explore the dam’s impact. The experiment shows that the water level of Dongting Lake drops conspicuously every year from September to November during the TGD impounding period, and the water level increases mildly during dry seasons due to TGD replenishment. Additionally, the impact of the TGD results in a water level decline in Dongting Lake during flood peaks and a subsequent lagged rise. This research provides a tool for flood forecasting and offers a reference for TGD water regulation.

Highlights

The large freshwater lakes of the world are an extremely valuable resource, because 68%of the global liquid surface freshwater is contained within lakes and because of their importance to the economies, social structure, and viability of riparian countries [1]
Dongting Lake is on the south bank of the Jingjiang River, which is another name for the Yangtze River in a specific segment in the middle reach of the Yangtze River region
We explored the applicability of different optimization algorithms including SGD, algorithmsAdagrad, includingAdadelta, SGD, RMSprop, Adagrad,and

Summary

Introduction

The large freshwater lakes of the world are an extremely valuable resource, because 68%of the global liquid surface freshwater is contained within lakes and because of their importance to the economies, social structure, and viability of riparian countries [1]. The large freshwater lakes of the world are an extremely valuable resource, because 68%. Dongting Lake is the second largest freshwater lake in China and is renowned for its wetland resources [2]. Wetlands are an area of transition between dry land and water bodies, and wetlands are often described as kidneys of the earth for their great contributions to flood control, groundwater replenishment, water purification, agriculture, and biological diversity [3]. Wetlands vary seasonally because water bodies change dramatically between dry and wet seasons. The change in water levels could influence the biodiversity community patterns and functions in lake ecosystems [4].

Methods

Results

Discussion

Conclusion