Preprints
https://doi.org/10.5194/tc-2021-194
https://doi.org/10.5194/tc-2021-194

  23 Jul 2021

23 Jul 2021

Review status: this preprint is currently under review for the journal TC.

Convolutional Neural Network and Long Short-Term Memory Models for Ice-Jam Prediction

Fatemehalsadat Madaeni1, Karem Chokmani1, Rachid Lhissou1, Saeid Homayuni1, Yves Gauthier1, and Simon Tolszczuk-Leclerc2 Fatemehalsadat Madaeni et al.
  • 1INRS-ETE, Université du Québec, Québec City, G1K 9A9, Canada
  • 2EMGeo Operations, Natural Resources Canada, Ottawa, K1S 5K2, Canada

Abstract. In cold regions, ice-jam events result in severe flooding due to a rapid rise in water levels upstream of the jam. These floods threaten human safety and damage properties and infrastructures as the floods resulting from ice-jams are sudden. Hence, the ice-jam prediction tools can give an early warning to increase response time and minimize the possible corresponding damages. However, the ice-jam prediction has always been a challenging problem as there is no analytical method available for this purpose. Nonetheless, ice jams form when some hydro-meteorological conditions happen, a few hours to a few days before the event. The ice-jam prediction problem can be considered as a binary multivariate time-series classification. Deep learning techniques have been successfully applied for time-series classification in many fields such as finance, engineering, weather forecasting, and medicine. In this research, we successfully applied CNN, LSTM, and combined CN-LSTM networks for ice-jam prediction for all the rivers in Quebec. The results show that the CN-LSTM model yields the best results in the validation and generalization with F1 scores of 0.82 and 0.91, respectively. This demonstrates that CNN and LSTM models are complementary, and a combination of them further improves classification.

Fatemehalsadat Madaeni et al.

Status: open (until 30 Sep 2021)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on tc-2021-194', John Quilty, 14 Aug 2021 reply
  • CC1: 'Comment on tc-2021-194', Rahim Barzegar, 22 Aug 2021 reply
  • RC2: 'Comment on tc-2021-194', Rahim Barzegar, 24 Aug 2021 reply

Fatemehalsadat Madaeni et al.

Fatemehalsadat Madaeni et al.

Viewed

Total article views: 352 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
269 72 11 352 4 2
  • HTML: 269
  • PDF: 72
  • XML: 11
  • Total: 352
  • BibTeX: 4
  • EndNote: 2
Views and downloads (calculated since 23 Jul 2021)
Cumulative views and downloads (calculated since 23 Jul 2021)

Viewed (geographical distribution)

Total article views: 348 (including HTML, PDF, and XML) Thereof 348 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 21 Sep 2021
Download
Short summary
We developed three deep learning models (CNN, LSTM, and combined CN-LSTM networks) to predict breakup ice-jam events to be used as an early warning system of possible flooding in rivers. In the models, we used hydrometeorological data associated with breakup ice jams. The models show excellent performance and the main finding is that the CN-LSTM model is superior to the CNN-only and LSTM-only networks in both training and generalization accuracy.