Wyniki wyszukiwania - BazTech

1

Artificial Neural Networks vs Long Short-Term Memory Prediction of Solid Flow in Tafna Basin (North-West Algeria)

Medfouni Mohamed Nadjib, Korichi Khaled, Marouf Nadir

Ecological Engineering & Environmental Technology

|

2024

|

Vol. 25, iss. 3

275--286

EN

The main objective of this work is to select the most reliable machine learning model to predict the generated solid flow in the Tafna basin (North-West of Algeria). It is about the artificial neural networks (ANN) and long short-term memory (LSTM). The sediment load is recorded through three hydrometric stations. The efficiency and performance of the two models is verified using the correlation coefficient (R2), the Nash-Sutcliffe coefficient (NSC) and the root mean square error (RMSE). The obtained simulated solids load shows a very good correlation in terms of precision although the ANN model gave relatively better results compared to the LSTM model where low RMSE values were recorded, which confirms that the artificial intelligence models remain also effective for the treatment and the prediction of hydrological phenomena such as the estimation of the solid load in a such watershed.

2

A comparative assessment of meteorological drought in the Tafna basin, Northwestern Algeria

Bougara Hanane, Baba-Hamed Kamila, Borgemeister Christian, Tischbein Bernhard, Kumar Navneet

Journal of Water and Land Development

|

2021

|

no. 51

78--93

EN

The drought ranked first in terms the natural hazard characteristics and impacts followed by tropical cyclones, regional floods, earthquakes, and volcanoes. Drought monitoring is an important aspect of drought risk management and the assessment of drought is usually done through using various drought indices. The western region in Algeria is the most affected by the drought since the middle of the 70s.The current research focuses on the analysis and comparison of four meteorological drought indices (standardized precipitation index – SPI, percent of normal index – PN, decile index – DI, and rainfall anomaly index – RAI) in the Tafna basin for different time scales (annual, seasonal, and monthly) during 1979–2011. The results showed that the SPI and DI have similar frequencies for dry and wet categories. The RAI and PN were able to detect more drought categories. Meanwhile, all indices have strong positive correlations between each other, especially with Spearman correlation tests (0.99; 1.0), the meteorological drought indices almost showed consistent and similar results in the study area. It was determined in 1982 as the driest year and 2008 as the wettest year in the period of the study. The analysis of the trend was based on the test of Mann–Kendall (MK), a positive trend of the indices were detected on a monthly scale, this increasing of indices trend represent the increasing of the wet categories which explains the increasing trend of the rainfall in the last 2000s. These results overview of the understanding of drought trends in the region is crucial for making strategies and assist in decision making for water resources management and reducing vulnerability to drought.

3

Quantification and study of monthly variation of suspended sediment loads in Tafna basin – Algeria

Belarbi F., Bouchelkia H., Remini B., Benmansour A.

Journal of Water and Land Development

|

2018

|

no. 37

29--38

EN

The magnitude of the phenomenon is disproportionate in semi-arid or in temperate climates. Thus Algeria is one of the most affected countries by this phenomenon and its consequences. To enable a rapid response to the request of engineers and managers to quantify sediment transport at the outlet of a watershed, a simple, easy tool to implement was developed. The principle adopted is based on hydrometric data sets from gauging stations with seasonal and annual time steps to define a suitable method for estimating sediment production. The sediment study was conducted by analysing the daily flows. Pierre du Chat station at the outlet of the Tafna basin served as an application. The obtained results are entirely satisfactory because the correlation coefficients of model Qs = f(Q) range between 72 and 95%. This method, once refined can be generalized to all watersheds in northern Algeria.

PL

Rozmiary sedymentacji są nieporównywalne w klimacie półpustynnym i umiarkowanym. Algieria jest jednym z państw dotkniętych tym procesem i jego skutkami. Aby zapewnić szybką reakcję na wymagania inżynierów i zarządców co do ilościowej oceny transportu osadu, na odpływie ze zlewni skonstruowano proste i łatwe w użyciu narzędzie nadające się do wdrożenia. Przyjęte zasady opierają się na zestawie danych hydrometrycznych z posterunków pomiarowych z użyciem sezonowych i rocznych kroków czasowych w celu zdefiniowania odpowiedniej metody do oceny produkcji osadu. Badania prowadzono, analizując dobowe przepływy. Przykładem był posterunek Pierre du Chat zamykający zlewnię Tafna. Uzyskane wyniki są w pełni satysfakcjonujące, ponieważ współczynnik korelacji modelu Qs = f(Q) wynosił od 72 do 95%. Przedstawiona metoda, po udoskonaleniu, może zostać uogólniona na wszystkie zlewnie w północnej Algierii.