Mathematical and Deep Learning Models Forecasting for Hydrological Time Series

Lhoussaine El Mezouary, Bouabid El Mansouri, Samir Kabbaj

2021

Abstract

Conventional hydrological models are based on a large number of readily accessible parameters. The use of models with a small number of variables, cabals to treat the nonlinearity of these parameters is necessary. With this in mind, we chose to develop a hydrological time series predictive model of flow based on the use of Deep Learning models, the approach based on an ANN Method with a multilayer network without feedback driven by the backpropagation algorithm errors. it is inspired by the principal mode of operation of the human neurons with a function that transforms the activation response of non-linear type. The developed, unlike the conventional statistical methods model, requires no assumptions on the variables used.

Paper Citation

in Harvard Style

El Mezouary L., El Mansouri B. and Kabbaj S. (2021). Mathematical and Deep Learning Models Forecasting for Hydrological Time Series. In Proceedings of the 2nd International Conference on Big Data, Modelling and Machine Learning - Volume 1: BML, ISBN 978-989-758-559-3, pages 249-254. DOI: 10.5220/0010732000003101

in Bibtex Style

@conference{bml21,
author={Lhoussaine El Mezouary and Bouabid El Mansouri and Samir Kabbaj},
title={Mathematical and Deep Learning Models Forecasting for Hydrological Time Series},
booktitle={Proceedings of the 2nd International Conference on Big Data, Modelling and Machine Learning - Volume 1: BML,},
year={2021},
pages={249-254},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010732000003101},
isbn={978-989-758-559-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Conference on Big Data, Modelling and Machine Learning - Volume 1: BML,
TI - Mathematical and Deep Learning Models Forecasting for Hydrological Time Series
SN - 978-989-758-559-3
AU - El Mezouary L.
AU - El Mansouri B.
AU - Kabbaj S.
PY - 2021
SP - 249
EP - 254
DO - 10.5220/0010732000003101