loading page

Modeling the damming effect on hydrological alteration and prediction of discharge in Padma River by proposing PSO based novel hybrid machine learning algorithm
  • +9
  • Abu Reza Md. Towfiqul Islam,
  • Swapan Talukdar,
  • Shumona Akhter,
  • Kutub Uddin Eibek,
  • Md. Mostafizur Rahman,
  • Ashraf Dewan,
  • Quoc Pham,
  • Nguyen Thi Thuy Linh,
  • Swades Pal,
  • Thi Ngoc Canh DOAN,
  • Duong Tran Anh,
  • Sobhy M. Ibrahim
Abu Reza Md. Towfiqul Islam
Begum Rokeya University
Author Profile
Swapan Talukdar
University of Gour Banga
Author Profile
Shumona Akhter
Begum Rokeya University
Author Profile
Kutub Uddin Eibek
Begum Rokeya University
Author Profile
Md. Mostafizur Rahman
Jahangirnagar University
Author Profile
Ashraf Dewan
Curtin University
Author Profile
Quoc Pham
National Cheng-Kung University
Author Profile
Nguyen Thi Thuy Linh
Duy Tan University
Author Profile
Swades Pal
University of Gour Banga
Author Profile
Thi Ngoc Canh DOAN
The University of Danang University of Economics
Author Profile
Duong Tran Anh
Ton Duc Thang University
Author Profile
Sobhy M. Ibrahim
King Saud University
Author Profile

Abstract

This paper quantified the hydrological alteration of the Padma River basin caused by the construction of Ferakka Barrage (FB) using innovative trend analysis (ITA), range of variability approach (RVA), and continuous wavelet analysis (CWA). We also predict flow regime by proposing particle swarm optimization (PSO) based novel hybrid machine learning algorithms. Results of the ITA showed the negative trend of the average discharge in the dry season (January-May), while the RVA analysis indicated that average discharge was lower than environmental flows. The CWA demonstrated a substantial effect of the FB on the periodicity of the streamflow regime. Results showed that PSO-Reduced Error Pruning Tree (REPTree), PSO-random forest (RF), and PSO-M5P were the optimal fit for average, maximum, and minimum discharge prediction (RMSE = 0.14, 0.3, 0.18) respectively.