深度学习的LSTM-GRU组合模型及其在水文模拟中的应用
DOI:
作者:
作者单位:

天津师范大学

作者简介:

通讯作者:

中图分类号:

TV11

基金项目:

国家自然科学基金项目(面上项目,重点项目,重大项目)


The LSTM-GRU combinatorial model of deep learning and its application to hydrological simulations
Author:
Affiliation:

Tianjin Normal University

Fund Project:

The National Natural Science Foundation of China (General Program, Key Program, Major Research Plan)

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    在深度学习方法中,长短期记忆网络(LSTM)和门控循环单元(GRU)是两种模拟时间序列的神经网络,其各有优缺点。为了弥补各自的不足,提高河流流量的预测精度,建立了LSTM-GRU组合模型,并将该模型应用于海河流域大清河水系白沟河流域流量预测。基于东茨村水文站2006-2019年的日观测数据,以8个水文气象因子(气压、水温、相对湿度、降水量、日照、地温、风速、水位)的观测数据为输入,河流流量为输出,建立了LSTM-GRU水文模型。其中2006-2015年数据为训练集,2016-2019年数据为验证集,采用均方根误差、确定性系数作为评价指标。为了验证模型优势,将LSTM-GRU的模拟结果分别与LSTM和GRU的结果进行比较。结果表明,LSTM-GRU组合模型的稳定性和精确度明显优于单一的LSTM与GRU模型,为河流流量的预测提供了一条新途径。

    Abstract:

    In deep learning methods, long and short-term memory networks (LSTM) and gated cycle units (GRU) are neural networks of two simulated time series, each with their advantages and disadvantages.In order to make up for their respective deficiencies and improve the prediction accuracy of river flow, the LSTM-GRU combination model is established and applied to the Baigou River basin of Daqing River system of Haihe River Basin.Based on the daily observation data of Dongci Village Hydrological Station from 2006-2019, the LSTM-GRU hydrological model was established with the observation data of 8 hydrometeorological factors (air pressure, water temperature, relative humidity, precipitation, sunshine, ground temperature, wind speed and water level) as the input and the river flow as the output.Among them, 2006-2015 data were the training set, 2016-2019 data were the validation set, and the root mean square error and deterministic coefficient were used as the evaluation indicators.To verify the model advantages, the simulation results of LSTM-GRU were compared with those of LSTM and GRU, respectively. The results show that the stability and accuracy of the LSTM-GRU combination model are significantly better than the single LSTM with GRU model, providing a new way for river flow prediction.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2021-11-06
  • 最后修改日期:2021-11-06
  • 录用日期:2022-05-30
  • 在线发布日期:
  • 出版日期: