Articles | Volume 16, issue 4
The Cryosphere, 16, 1447–1468, 2022
https://doi.org/10.5194/tc-16-1447-2022
The Cryosphere, 16, 1447–1468, 2022
https://doi.org/10.5194/tc-16-1447-2022
Research article
22 Apr 2022
Research article | 22 Apr 2022

Convolutional neural network and long short-term memory models for ice-jam predictions

Fatemehalsadat Madaeni et al.

Related authors

Multi-scale spatialization of snow water equivalent (SWE) according to their spatial structures in eastern Canada
Noumonvi Yawu Sena, Karem Chokmani, Erwan Gloaguen, and Monique Bernier
The Cryosphere Discuss., https://doi.org/10.5194/tc-2020-316,https://doi.org/10.5194/tc-2020-316, 2020
Manuscript not accepted for further review
Combining TerraSAR-X and time-lapse photography for seasonal sea ice monitoring: the case of Deception Bay, Nunavik
Sophie Dufour-Beauséjour, Anna Wendleder, Yves Gauthier, Monique Bernier, Jimmy Poulin, Véronique Gilbert, Juupi Tuniq, Amélie Rouleau, and Achim Roth
The Cryosphere, 14, 1595–1609, https://doi.org/10.5194/tc-14-1595-2020,https://doi.org/10.5194/tc-14-1595-2020, 2020
Short summary
ESTIMATING CANOLA’S BIOPHYSICAL PARAMETERS FROM TEMPORAL, SPECTRAL, AND POLARIMETRIC IMAGERY USING MACHINE LEARNING APPROACHES
O. Reisi Gahrouei, S. Homayouni, and A. Safari
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-4-W18, 885–889, https://doi.org/10.5194/isprs-archives-XLII-4-W18-885-2019,https://doi.org/10.5194/isprs-archives-XLII-4-W18-885-2019, 2019
IcePAC – a probabilistic tool to study sea ice spatio-temporal dynamics: application to the Hudson Bay area
Charles Gignac, Monique Bernier, and Karem Chokmani
The Cryosphere, 13, 451–468, https://doi.org/10.5194/tc-13-451-2019,https://doi.org/10.5194/tc-13-451-2019, 2019
Short summary
River predisposition to ice jams: a simplified geospatial model
Stéphane De Munck, Yves Gauthier, Monique Bernier, Karem Chokmani, and Serge Légaré
Nat. Hazards Earth Syst. Sci., 17, 1033–1045, https://doi.org/10.5194/nhess-17-1033-2017,https://doi.org/10.5194/nhess-17-1033-2017, 2017
Short summary

Related subject area

Discipline: Other | Subject: Natural Hazards
The 2020 glacial lake outburst flood at Jinwuco, Tibet: causes, impacts, and implications for hazard and risk assessment
Guoxiong Zheng, Martin Mergili, Adam Emmer, Simon Allen, Anming Bao, Hao Guo, and Markus Stoffel
The Cryosphere, 15, 3159–3180, https://doi.org/10.5194/tc-15-3159-2021,https://doi.org/10.5194/tc-15-3159-2021, 2021
Short summary

Cited articles

Alipanahi, B., Delong, A., Weirauch, M. T., and Frey, B. J.: Predicting the sequence specificities of DNA-and RNA-binding proteins by deep learning, Nat. Biotechnol., 33, 831–838, 2015. 
Althoff, D., Rodrigues, L. N., and Bazame, H. C.: Uncertainty quantification for hydrological models based on neural networks: the dropout ensemble, Stoch. Env. Res. Risk A., 35, 1051–1067, 2021. 
Anaconda Software Distribution​​​​​​​: Anaconda Documentation, Version 2-2.4,​ https://docs.anaconda.com/ (last access: 10 February 2022)​​​​​, 2016. 
Apaydin, H., Feizi, H., Sattari, M. T., Colak, M. S., Shamshirband, S., and Chau, K. W.: Comparative analysis of recurrent neural network architectures for reservoir inflow forecasting, Water, 12, 1500, https://doi.org/10.3390/w12051500, 2020. 
Barnes-Svarney, P. L. and Montz, B. E.: An ice jam prediction model as a tool in floodplain management, Water Resour. Res., 21, 256–260, 1985. 
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 hydro-meteorological 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.