[1]郭宝椿,李佐勇,陈健,等.融合长短时记忆与图结构学习的水库水位预测[J].福建理工大学学报,2024,22(01):90-94.[doi:10.3969/j.issn.2097-3853.2024.01.013]
　GUO Baochun,LI Zuoyong,CHEN Jian,et al.Reservoir level prediction via integrating long short-term memory and graph structure learning[J].Journal of Fujian University of Technology;,2024,22(01):90-94.[doi:10.3969/j.issn.2097-3853.2024.01.013]
点击复制

融合长短时记忆与图结构学习的水库水位预测
分享到：

《福建理工大学学报》[ISSN:2097-3853/CN:35-1351/Z]

卷:
第22卷
期数:
2024年01期
页码:
90-94
栏目:
出版日期:
2024-02-25

文章信息/Info

Title:
Reservoir level prediction via integrating long short-term memory and graph structure learning
作者:
郭宝椿; 李佐勇; 陈健; 卢维楷; 马森标
福建理工大学电子电气与物理学院
Author(s):
GUO Baochun;  LI Zuoyong;  CHEN Jian;  LU Weikai;  MA Senbiao
School of Electronic, Electrical and Physics, Fujian University of Technology
关键词:
水库水位预测; 长短期记忆网络; 图神经网络; 深度学习
Keywords:
reservoir level prediction;  long short-term memory network;  graph neural network;  deep learning
分类号:
TP389.1
DOI:
10.3969/j.issn.2097-3853.2024.01.013
文献标志码:
A
摘要:
水库水位变化受降雨、泄洪、蒸发等众多因素影响,现有水库水位预测方法的预测精度有待提升。为此,提出一种融合长短期记忆网络( long short-term memory,LSTM) 和图卷积神经网络( graphconvolution neural network,GCN)的水库水位预测模型。该模型首先借助LSTM 提取水位与相关影响因素的时序依赖特征;随后,设计图结构学习模块,自动捕捉水位及不同影响因素间的关联关系;最后利用GCN 进行表征学习和预测。在三峡大坝数据集及合作企业提供的数据集上开展了广泛实验,实验结果证实了所提模型的有效性和优越性。
Abstract:
The water level change of reservoirs is affected by many factors such as rainfall, flood discharge, and evaporation. The prediction accuracy of existing reservoir water level prediction methods needs to be improved. Therefore, a reservoir water level prediction model was proposed integrating long short-term memory (LSTM) and graph convolution neural network (GCN). The proposed model first extracts time-series dependent features of water level and related influencing factors by using LSTM. Then, a graph structure learning module is designed to automatically capture the correlation between water level and different influencing factors. Finally, GCN is used for feature learning and prediction. Extensive experiments were conducted on the Three Gorges Dam dataset and datasets provided by cooperative enterprises. The experimental results demonstrated the effectiveness and superiority of the proposed model.

参考文献/References:

［1］ 安新代. 黄河小浪底水库防洪减淤作用与效益跟踪分析［J］. 人民黄河，2023，45（8）：37-42. ［2］ 郭生练，刘攀，王俊，等. 再论水库汛期水位动态控制的必要性和可行性［J］. 水利学报，2023，54（1）：1-12.［3］ 李捷，陈俊英，苏晓，等. 基于圣维南方程组的水位流量单值关系应用［J］. 人民黄河，2016，38（1）：22-27. ［4］ NE?瘙塁 F，DEMIRCI M，TA?瘙塁AR B，et al. Estimating dam reservoir level fluctuations using data-driven techniques［J］. Polish Journal of Environmental Studies，2019，28（5）：3451-3462.［5］ 刘晓阳，姚华明，张海荣，等. 基于机器学习的三峡水库小时尺度坝前水位预测［J］. 人民长江，2023，54（2）：147-151.［6］ 纪国良，周曼，刘涛，等. 基于循环神经网络的水库水位预测方法［J］. 长江科学院院报，2022，39（3）：80-85.［7］ PARK K，SEONG Y，JUNG Y，et al. Development of water level prediction improvement method using multivariate time series data by GRU model［J］. Water，2023，15（3）：587.［8］ IBAEZ S C，DAJAC C V G，LIPONHAY M P，et al. Forecasting reservoir water levels using deep neural networks：a case study of angat dam in the Philippines［J］. Water，2021，14（1）：34.［9］ LI T F，ZHAO Z B，SUN C A，et al. Domain adversarial graph convolutional network for fault diagnosis under variable working conditions［J］. IEEE Transactions on Instrumentation and Measurement，2021，70：1-10.［10］ 张静，刘增进，肖伟华，等. 三峡水库蓄水后库区气候要素变化趋势分析［J］. 人民长江，2019，50（3）：113-116，165.［11］ LAI G K，CHANG W C，YANG Y M，et al. Modeling longand shortterm temporal patterns with deep neural networks［C］∥SIGIR 18：The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval. New York：ACM，2018：95-104.

更新日期/Last Update: 2024-02-25