Articles | Volume 25, issue 12
https://doi.org/10.5194/hess-25-6185-2021
https://doi.org/10.5194/hess-25-6185-2021
Research article
 | 
06 Dec 2021
Research article |  | 06 Dec 2021

In-stream Escherichia coli modeling using high-temporal-resolution data with deep learning and process-based models

Ather Abbas, Sangsoo Baek, Norbert Silvera, Bounsamay Soulileuth, Yakov Pachepsky, Olivier Ribolzi, Laurie Boithias, and Kyung Hwa Cho

Viewed

Total article views: 2,570 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
1,709 790 71 2,570 235 41 52
  • HTML: 1,709
  • PDF: 790
  • XML: 71
  • Total: 2,570
  • Supplement: 235
  • BibTeX: 41
  • EndNote: 52
Views and downloads (calculated since 08 Apr 2021)
Cumulative views and downloads (calculated since 08 Apr 2021)

Viewed (geographical distribution)

Total article views: 2,570 (including HTML, PDF, and XML) Thereof 2,490 with geography defined and 80 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Latest update: 23 Nov 2024
Download

The requested paper has a corresponding corrigendum published. Please read the corrigendum first before downloading the article.

Short summary
Correct estimation of fecal indicator bacteria in surface waters is critical for public health. Process-driven models and recently data-driven models have been applied for water quality modeling; however, a systematic comparison for simulation of E. coli is missing in the literature. We compared performance of process-driven (HSPF) and data-driven (LSTM) models for E. coli simulation. We show that LSTM can be an alternative to process-driven models for estimation of E. coli in surface waters.