01 Mar 2023
 | 01 Mar 2023
Status: this preprint is open for discussion.

Forecasting estuarine salt intrusion in the Rhine-Meuse delta using an LSTM model

Bas Johan Marinus Wullems, Claudia Catharina Brauer, Fedor Baart, and Albrecht Henricus Weerts

Abstract. Estuarine salt intrusion causes problems with freshwater availability in many deltas. Water managers require timely and accurate forecasts to be able to mitigate and adapt to salt intrusion. Data-driven models derived with machine learning are ideally suited for this, as they can mimic complex non-linear systems and are computationally efficient. We set up a Long Short Term Memory (LSTM) model to forecast salt intrusion in the Rhine-Meuse delta. It forecasts chloride concentrations up to 7 days ahead at Krimpen aan den IJssel, an important location for freshwater provision. The model forecasts baseline concentrations and peak timing well, but peak height is underestimated, a problem that becomes worse with increasing lead time. Between lead times of 1 and 7 days, forecast precision declines from 0.9 to 0.7 and forecast recall declines from 0.7 to 0.5 on average. Given these results, we aim to extend the model to other locations in the delta. We expect that a similar setup can work in other deltas, especially those with a similar or simpler channel network.

Bas Johan Marinus Wullems et al.

Status: open (until 26 Apr 2023)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Bas Johan Marinus Wullems et al.

Data sets

Salt LSTM Data Bas Wullems

Model code and software

Salt intrusion LSTM Bas Wullems

Bas Johan Marinus Wullems et al.


Total article views: 165 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
114 45 6 165 4 5
  • HTML: 114
  • PDF: 45
  • XML: 6
  • Total: 165
  • BibTeX: 4
  • EndNote: 5
Views and downloads (calculated since 01 Mar 2023)
Cumulative views and downloads (calculated since 01 Mar 2023)

Viewed (geographical distribution)

Total article views: 161 (including HTML, PDF, and XML) Thereof 161 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 29 Mar 2023
Short summary
In deltas, salt water sometimes intrudes far inland and causes problems with freshwater availability. We created a model to forecast salt concentrations at a critical location in the Rhine-Meuse delta in the Netherlands. It requires a rather small number of data to make a prediction and runs fast. It predicts the occurrence of salt concentration peaks well, but underestimates the highest peaks. Its speed gives water managers more time to reduce the problems caused by salt intrusion.