ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Influence of Pre-Processing Algorithms on Surface Water TDS Estimation Using Artificial Intelligence Models: A Case Study of the Karoon River

Panahi, Javad; Mastouri, Reza*; Shabanlou, Saeid
Iranian Journal of Science and Technology-Transactions of Civil Engineering2023-2DOI: 10.1007/s40996-022-00928-4
6被引7阅读
引用收藏
分享

摘要

One of the essential indicators of surface water quality is total dissolved solids (TDS) that is prominent for both short- and long-term water resources management. In this study, in order to resolve the non-stationarity challenges faced by water quality parameters (WQPs), variational mode decomposition (VMD) combined with two unsupervised artificial intelligence (AI) models, artificial neural network (ANN) and extreme learning machine (ELM), was used. Crow search algorithm (CSA) was recruited to train the ANN and ELM networks and find the optimum weight and bias values. To validate the constructed hybrid VMD-ANN/ELM-CSA models, Molasani station in Karoon River was considered to model TDS at monthly timescale. The WQPs time-series data are simultaneously factorized into respective intrinsic mode functions (IMFs) using VMD algorithm. The proposed VMD-ELM-CSA model shows the best performance at considered station, in comparison with the comparative standalone and hybrid models, with maximum values of R-2 = 0.97 and E-ns = 0.96 at testing period. Results show that using VMD could reduce RMSE about 37 and 12% when coupled with ANN-CSA and ELM-CSA, respectively, at Molasani station. It was concluded that the CSA optimization algorithm and VMD data decomposition technique could improve the prediction accuracy of the AI models and may be recommended for accurate WQPs prediction.

学科与关键词

关键词
Surface water TDSWater quality parametersData decomposition algorithmCrow search algorithmHybrid artificial intelligence model
相关
加载中…

文献加载失败,请重试

重试

发表信息

论文状态
公开发表
期刊
Iranian Journal of Science and Technology-Transactions of Civil Engineering
发表日期
2023-02
卷期
第 47 卷, 第 1 期
页码
585-598
DOI
10.1007/s40996-022-00928-4
语言
ENGLISH
成果收录
SCIE

作者

  • P

    Panahi, Javad (第一作者)

  • M

    Mastouri, Reza (通讯)

查看全部 3 位作者收起作者
  • S

    Shabanlou, Saeid

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417