Articles | Volume 22, issue 5
Hydrol. Earth Syst. Sci., 22, 2987–3006, 2018
https://doi.org/10.5194/hess-22-2987-2018
Hydrol. Earth Syst. Sci., 22, 2987–3006, 2018
https://doi.org/10.5194/hess-22-2987-2018

Research article 22 May 2018

Research article | 22 May 2018

Framework for developing hybrid process-driven, artificial neural network and regression models for salinity prediction in river systems

Jason M. Hunter et al.

Viewed

Total article views: 3,160 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
2,375 736 49 3,160 79 50 58
  • HTML: 2,375
  • PDF: 736
  • XML: 49
  • Total: 3,160
  • Supplement: 79
  • BibTeX: 50
  • EndNote: 58
Views and downloads (calculated since 25 Sep 2017)
Cumulative views and downloads (calculated since 25 Sep 2017)

Viewed (geographical distribution)

Total article views: 2,926 (including HTML, PDF, and XML) Thereof 2,905 with geography defined and 21 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Latest update: 23 Oct 2021
Download
Short summary
This research proposes a generalised hybrid model development framework and applies it to a case study of salinity prediction in a reach of the Murray River. The hybrid model combines five sub-models which describe one process of salt entry each and are developed based on the amount of system knowledge and data that are available to support each individual process. The model demonstrates increased performance over two benchmark models and has implications for future model development processes.