《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (6): 1756-1761.DOI: 10.11772/j.issn.1001-9081.2021061366

• 2021年全国开放式分布与并行计算学术年会(DPCS 2021)论文 • 上一篇    

基于时域卷积网络的水文模型

聂青青1, 万定生1(), 朱跃龙1, 李致家2, 姚成2   

  1. 1.河海大学 计算机与信息学院,南京 211100
    2.河海大学 水文水资源学院,南京 210098
  • 收稿日期:2021-08-02 修回日期:2021-11-15 接受日期:2021-11-15 发布日期:2022-01-10 出版日期:2022-06-10
  • 通讯作者: 万定生
  • 作者简介:聂青青(1997—),女,安徽安庆人,硕士研究生,主要研究方向:数据管理、数据挖掘
    朱跃龙(1959—),男,江苏建湖人,教授,博士,CCF会员,主要研究方向:智能信息处理、数据挖掘
    李致家(1962—),男,山西运城人,教授,博士, 主要研究方向:水文物理规律模拟与预报、数据挖掘
    姚成(1982—),男,江苏扬州人,副教授,博士,主要研究方向:水文模型、水文预报、数据挖掘、数值模拟。
  • 基金资助:
    国家重点研发计划项目(2018YFC1508100)

Hydrological model based on temporal convolutional network

Qingqing NIE1, Dingsheng WAN1(), Yuelong ZHU1, Zhijia LI2, Cheng YAO2   

  1. 1.College of Computer and Information,Hohai University,Nanjing Jiangsu 211100,China
    2.College of Hydrology and Water Resources,Hohai University,Nanjing Jiangsu 210098,China
  • Received:2021-08-02 Revised:2021-11-15 Accepted:2021-11-15 Online:2022-01-10 Published:2022-06-10
  • Contact: Dingsheng WAN
  • About author:NIE Qingqing,born in 1997,M. S. candidate. Her research interests include data management,data mining.
    ZHU Yuelong,born in 1959,Ph. D.,professor. His research interests include intelligent information processing,data mining
    LI Zhijia,born in 1962,Ph. D.,professor. His research interests include simulation and prediction of hydrological physical laws,data mining.
    YAO Cheng,born in 1982,Ph. D.,associate professor. His research interests include hydrological model,hydrological forecast,data mining,numerical simulation.
  • Supported by:
    National Key Research and Development Program of China(2018YFC1508100)

摘要:

水位预测是防洪预警工作的辅助决策支持。为了进行准确的水位预测,为预防自然灾害提供科学依据,提出一种结合改进的灰狼优化(MGWO)算法与时域卷积网络(TCN)的预测模型MGWO-TCN。针对标准灰狼优化(GWO)算法存在早熟停滞的不足引入差分进化(DE)算法,扩展灰狼种群的多样性;改进灰狼种群更新时的收敛因子和变异时的变异算子,以自适应的形式对参数进行调整,提升算法的收敛速度,均衡算法的全局与局部搜索能力;利用MGWO算法对TCN的重要参数寻优,提升TCN的预测性能。将MGWO-TCN预测模型用于河流水位预测,预测结果的均方根误差(RMSE)为0.039。实验结果表明,与对比模型相比,MGWO-TCN预测模型具有更好的寻优能力和更高的预测精度。

关键词: 水文预测, 灰狼优化算法, 时域卷积网络, 差分进化算法, 收敛因子

Abstract:

Water level prediction is an auxiliary decision support for flood warning work. For accurate water level prediction and providing scientific basis for natural disaster prevention, a prediction model combining Modified Gray Wolf Optimization (MGWO) algorithm and Temporal Convolutional Network (TCN) was proposed, namely MGWO-TCN. In view of the shortage of premature and stagnation in the original Gray Wolf Optimization (MGWO) algorithm, the idea of Differential Evolution (DE) algorithm was introduced to extend the diversity of the grey wolf population. The convergence factor during update and the mutation operator during mutation of the grey wolf population were improved to adjust the parameters in the adaptive manner, thereby improving the convergence speed and balancing the global and local search capabilities of the algorithm. The proposed MGWO algorithm was used to optimize the important parameters of TCN to improve the prediction performance of TCN. The proposed prediction model MGWO-TCN was used for river water level prediction, and the Root Mean Square Error (RMSE) of the model’s prediction results was 0.039. Experimental results show that compared with the comparison model, the proposed MGWO-TCN has better optimization ability and higher prediction accuracy.

Key words: hydrological prediction, Grey Wolf Optimization (GWO) algorithm, Temporal Convolutional Network (TCN), Differential Evolution (DE) algorithm, convergence factor

中图分类号: