Publications internationales

2020
Besma Boudiaf, Ismail Dabanli, Hamouda Boutaghane, Zekai Şen. (2020), Temperature and Precipitation Risk Assessment Under Climate Change Effect in Northeast Algeria. Earth Systems and Environment : Springer , https://link.springer.com/article/10.1007/s41748-019-00136-7

Résumé: Climate change impacts on social, economic, industrial, agricultural, and water resource systems tend to increase incrementally with each passing day. Therefore, it is necessary to plan to control its effects, especially with regard to temperature and rainfall events impacting future water resource operation, maintenance and management works. Climate change has a direct influence at the trend of both components temperature and precipitation in increasing or decreasing manner depending on the study area. This paper presents and interprets temperature and rainfall trends for Northeast Algeria. A trend analysis technique was employed along with risk assessment. The modified risks associated with 2-, 5-, 10-, 25-, 50-, 100-, 250, and 500-year return periods are then calculated for each station. This methodology has been applied to precipitation and temperature records for six different meteorological stations in Northeast Algeria. This study confirms that climate change has and will continue to have an impact on temperature and precipitation that should be considered for all infrastructure planning, design, construction, operation, maintenance and optimum management studies in future.

Tayeb Boulmaiz, Mowloud Guermoui, Hamouda Boutaghane. (2020), Impact of training data size on the LSTM performances for rainfall–runoff modeling. Modeling Earth Systems and Environment : Springer, https://link.springer.com/article/10.1007/s40808-020-00830-w

Résumé: For predicting catchment runoff with data-driven methods, a long historical database of measurements is required. The current study focuses on the assessment of a deep learning model named long short-term memory (LSTM) for rainfall–runoff relationship with different training data size. The developed model has been evaluated on twenty catchments with diverse hydrological conditions obtained from the freely available CAMELS dataset. In order to prove the efficiency of the proposed model for runoff prediction, we test its performances against the traditional feed-forward neural network model. The studied models have been trained with the same input parameters and different size of training data to show the effect of data length on the prediction performances. To this end, the length of training data was varied from 3 to 15 years, while the model was tested on 10 years of data. The results show that the deep LSTM outperforms the traditional model in terms of statistical indicators over different size of training sets. The proposed deep LSTM model can predict runoff with acceptable performances using 9 years of data length in the training procedure, a result that improves when using 12 years. In addition, it has been proven that the deep LSTM model may be efficient even when using small data size (3 years) compared to its benchmarked model which require 9 years for similar results. Thus, the LSTM network is a powerful deep learning model able to learn the behavior of rainfall–runoff relationship with a minimum data length.

2019
(2019), Identification of flow components with the trigonometric hydrograph separation method: a case study from Madjez Ressoul catchment, Algeria. Arabian Journal of Geoscience : Springer, https://doi.org/10.1007/s12517-019-4616-5.

Résumé: Madjez Ressoul catchment constitutes an important source of fresh water and arable land in northeastern Algeria. In order to achieve better management of the catchments’ natural resources, specifically water, an advanced flood recession analysis was conducted, using the recession analysis-based trigonometric approach, which was based completely on a mathematical solution. This approach provides very useful results for the master recession curves construction. The advantage of this method in the hydrograph separation is both its non-subjectivity related to the user, and then its viability for initial use in the hydrograph separation field. Results in this real case give a better indication of groundwater flow during different drought periods, using many assessed parameters of initial discharge and relative recession time. A particular review of existing hydrograph separation techniques is used to situate the recession analysis and show its case of application relative to other techniques.

2016
(2016), Development of peri-urban catchment hydrological model with the multi-outlet approach. Arabian Journal of Geoscience. : springer, https://link.springer.com/article/10.1007/s12517-016-2590-8

Résumé: The peri-urban catchments are distinguished by discontinuous urban extensions. They extend between the margins of the city and the borders of the rural space forming a mid-urban, mid rural mosaic. They experience unprecedented expansion movement since the end of the 60 years. When hydrological models for urban and for rural catchments have been developed, it was until recently impossible to apply those principles in a concrete manner to peri-urban catchments. The representation of the hydrological functioning of these surfaces can be done by considering both urban processes and rural processes. In this paper, we present the simulation model named “Multi-Outlets model”. This model allows taking into account the mixed nature of peri-urban areas. The model was applied to Yzeron catchment located in Lyon, France. Keywords Peri-urban Evapotranspiration Infiltration Hydrological modeling

(2016), Single neural network and neuro-updating conceptual model for forecasting runoff. International Journal of Hydrology Science and Technology : InderScience, https://www.inderscienceonline.com/doi/abs/10.1504/IJHST.2016.079344?journalCode=ijhst

Résumé: Abstract Application of artificial neural network (ANN) becomes an alternative or complementary technique for forecasting runoff, which is an important operation for water management or flood protection. Two using approaches of ANN are applied in this study. The first is to use a nonlinear autoregressive with exogenous inputs network (NARXN) as a single model with rainfall data as inputs to forecast runoff, while the second is to use a feedforward ANN to update the outputs of a global conceptual model (GR4J). Trial and error procedure has been used for both ANNs in order to search combinations that give the best accuracy. The results show that the second approach performs better for forecasting daily flow (mean square error in test period = 0.19) and is more efficient in terms of water resources with an annual mean supply error of 0.56 Hm3 compared to NARXN model (5.29 Hm3). Keywords: Algeria, artificial neural networks, ANNs, conce ptual models, runoff forecasting, GR4J, hydrology, NARXN model, Oued Rassoul, output updating, rainfall runoff, water resources, modelling, water management, flood protection.