scholarly journals Using artificial neural network (ANN) for prediction of sediment loads, application to the Mellah catchment, northeast Algeria

2017 ◽  
Vol 33 (1) ◽  
pp. 47-55 ◽  
Author(s):  
Housseyn Bouzeria ◽  
Abderrahmane N. Ghenim ◽  
Kamel Khanchoul
Keyword(s):  
Suspended Sediment ◽  
Time Series Data ◽  
Water Discharge ◽  
Absolute Error ◽  
Coefficient Of Determination ◽  
Series Data ◽  
Sediment Discharge ◽  
Statistical Parameters ◽  
Discharge Data ◽  
Sediment Loads

AbstractIn this study, we present the performances of the best training algorithm in Multilayer Perceptron (MLP) neural networks for prediction of suspended sediment discharges in Mellah catchment. Time series data of daily suspended sediment discharge and water discharge from the gauging station of Bouchegouf were used for training and testing the networks. A number of statistical parameters, i.e. root mean square error (RMSE), mean absolute error (MAE), coefficient of efficiency (CE) and coefficient of determination (R2) were used for performance evaluation of the model. The model produced satisfactory results and showed a very good agreement between the predicted and observed data. The results also showed that the performance of the MLP model was capable to capture the exact pattern of the sediment discharge data in the Mellah catchment.

Neural networks approached for modelling river suspended sediment concentration due to tropical storms

2013 ◽  
Vol 11 (4) ◽  
pp. 457-466
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Suspended Sediment ◽  
Suspended Sediment Concentration ◽  
Time Series Data ◽  
Water Discharge ◽  
Sediment Concentration ◽  
Series Data ◽  
Generalized Regression Neural Network ◽  
Event Based

Artificial neural networks are one of the advanced technologies employed in hydrology modelling. This paper investigates the potential of two algorithm networks, the feed forward backpropagation (BP) and generalized regression neural network (GRNN) in comparison with the classical regression for modelling the event-based suspended sediment concentration at Jiasian diversion weir in Southern Taiwan. For this study, the hourly time series data comprised of water discharge, turbidity and suspended sediment concentration during the storm events in the year of 2002 are taken into account in the models. The statistical performances comparison showed that both BP and GRNN are superior to the classical regression in the weir sediment modelling. Additionally, the turbidity was found to be a dominant input variable over the water discharge for suspended sediment concentration estimation. Statistically, both neural network models can be successfully applied for the event-based suspended sediment concentration modelling in the weir studied herein when few data are available.

scholarly journals Forecasting suspended sediment load using regularized neural network: Case study of the Isser River (Algeria)

2016 ◽  
Vol 29 (1) ◽  
pp. 75-81 ◽  
Author(s):  
Salah E. Tachi ◽  
Lahbassi Ouerdachi ◽  
Mohamed Remaoun ◽  
Oussama Derdous ◽  
Hamouda Boutaghane
Keyword(s):  
Neural Network ◽  
Suspended Sediment ◽  
Sediment Load ◽  
Water Discharge ◽  
Back Propagation ◽  
Training Data ◽  
Coefficient Of Determination ◽  
Suspended Sediment Load ◽  
Early Stopping ◽  
Discharge Data

Abstract In the management of water resources in different hydro-systems it is important to evaluate and predict the sediment load in rivers. It is difficult to obtain an effective and fast estimation of sediment load by artificial neural network without avoiding over-fitting of the training data. The present paper comprises the comparison of a multi-layer perception network once with non-regularized network and the other with regularized network using the Early Stopping technique to estimate and forecast suspended sediment load in the Isser River, upstream of Beni Amran reservoir, northern Algeria. The study was carried out on daily sediment discharge and water discharge data of 30 years (1971–2001). The results of the Back Propagation based models were evaluated in terms of the coefficient of determination (R2) and the root mean square error (RMSE). Results of the comparison indicate that the regularizing ANN using the Early Stopping technique to avoid over-fitting performs better than non-regularized networks, and show that the overtraining in the back propagation occurs because of the complexity of the data introduced to the network.

scholarly journals Superiority of Hybrid Soft Computing Models in Daily Suspended Sediment Estimation in Highly Dynamic Rivers

2021 ◽  
Vol 13 (2) ◽  
pp. 542
Author(s):  
Tarate Suryakant Bajirao ◽  
Pravendra Kumar ◽  
Manish Kumar ◽  
Ahmed Elbeltagi ◽  
Alban Kuriqi
Keyword(s):  
Time Series ◽  
Wavelet Transform ◽  
Suspended Sediment ◽  
River Basin ◽  
Time Series Data ◽  
Series Data ◽  
Discrete Wavelet ◽  
Original Time Series ◽  
Inference System ◽  
Original Time

Estimating sediment flow rate from a drainage area plays an essential role in better watershed planning and management. In this study, the validity of simple and wavelet-coupled Artificial Intelligence (AI) models was analyzed for daily Suspended Sediment (SSC) estimation of highly dynamic Koyna River basin of India. Simple AI models such as the Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) were developed by supplying the original time series data as an input without pre-processing through a Wavelet (W) transform. The hybrid wavelet-coupled W-ANN and W-ANFIS models were developed by supplying the decomposed time series sub-signals using Discrete Wavelet Transform (DWT). In total, three mother wavelets, namely Haar, Daubechies, and Coiflets were employed to decompose original time series data into different multi-frequency sub-signals at an appropriate decomposition level. Quantitative and qualitative performance evaluation criteria were used to select the best model for daily SSC estimation. The reliability of the developed models was also assessed using uncertainty analysis. Finally, it was revealed that the data pre-processing using wavelet transform improves the model’s predictive efficiency and reliability significantly. In this study, it was observed that the performance of the Coiflet wavelet-coupled ANFIS model is superior to other models and can be applied for daily SSC estimation of the highly dynamic rivers. As per sensitivity analysis, previous one-day SSC (St-1) is the most crucial input variable for daily SSC estimation of the Koyna River basin.

scholarly journals Dissolved and particulate nutrient transport dynamics of a small Irish catchment: the River Owenabue

2014 ◽  
Vol 18 (6) ◽  
pp. 2191-2200 ◽  
Author(s):  
S. T. Harrington ◽  
J. R. Harrington
Keyword(s):  
Suspended Sediment ◽  
Water Discharge ◽  
Nutrient Transport ◽  
Sediment Concentration ◽  
Coefficient Of Determination ◽  
Available Phosphorus ◽  
Nitrogen And Phosphorus ◽  
Particulate Nitrogen ◽  
Monitoring Period ◽  
Nitrogen Concentrations

Abstract. The objective of this research was to investigate the relationship between water and sediment discharge on the transport of nutrients: nitrogen and phosphorus. Water discharge, suspended sediment concentration and dissolved and particulate forms of nitrogen and phosphorus were monitored on the 105 km2 River Owenabue catchment in Ireland. Water discharge was found to have an influence on both particulate and dissolved nutrient transport, but more so for particulate nutrients. The particulate portion of N and P in collected samples was found to be 24 and 39%, respectively. Increased particulate nitrogen concentrations were found at the onset of high discharge events, but did not correlate well to discharge. High concentrations of phosphorus were associated with increased discharge rates and the coefficient of determination (r2) between most forms of phosphorus and both discharge and suspended sediment concentrations were observed to be greater than 0.5. The mean TN yield is 4004 kg km−2 yr−1 for the full 29-month monitoring period with a mean PN yield of 982 kg km−2 yr−1, 25% of the TN yield with the contribution to the yield of PN and PP estimated to be 25 and 53% respectively. These yields represent a PN and PP contribution to the suspended sediment load of 5.6 and 0.28% respectively for the monitoring period. While total nitrogen and total phosphorus levels were similar to other European catchments, levels of bio-available phosphorus were elevated indicating a potential risk of eutrophication within the river.

LamaH: Large-sample Data for Hydrology in Central Europe

2021 ◽  
Author(s):  
Christoph Klingler ◽  
Mathew Herrnegger ◽  
Frederik Kratzert ◽  
Karsten Schulz
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Vegetation Indices ◽  
River Network ◽  
Series Data ◽  
High Temporal Resolution ◽  
Stream Length ◽  
Discharge Data ◽  
Large Sample ◽  
Access To Data

<p>Open large-sample datasets are important for various reasons: i) they enable large-sample analyses, ii) they democratize access to data, iii) they enable large-sample comparative studies and foster reproducibility, and iv) they are a key driver for recent developments of machine-learning based modelling approaches.</p><p>Recently, various large-sample datasets have been released (e.g. different country-specific CAMELS datasets), however, all of them contain only data of individual catchments distributed across entire countries and not connected river networks.</p><p>Here, we present LamaH, a new dataset covering all of Austria and the foreign upstream areas of the Danube, spanning a total of 170.000 km² in 9 different countries with discharge observations for 882 gauges. The dataset also includes 15 different meteorological time series, derived from ERA5-Land, for two different basin delineations: First, corresponding to the entire upstream area of a particular gauge, and second, corresponding only to the area between a particular gauge and its upstream gauges. The time series data for both, meteorological and discharge data, is included in hourly and daily resolution and covers a period of over 35 years (with some exceptions in discharge data for a couple of gauges).</p><p>Sticking closely to the CAMELS datasets, LamaH also contains more than 60 catchment attributes, derived for both types of basin delineations. The attributes include climatic, hydrological and vegetation indices, land cover information, as well as soil, geological and topographical properties. Additionally, the runoff gauges are classified by over 20 different attributes, including information about human impact and indicators for data quality and completeness. Lastly, LamaH also contains attributes for the river network itself, like gauge topology, stream length and the slope between two sequential gauges.</p><p>Given the scope of LamaH, we hope that this dataset will serve as a solid database for further investigations in various tasks of hydrology. The extent of data combined with the interconnected river network and the high temporal resolution of the time series might reveal deeper insights into water transfer and storage with appropriate methods of modelling.</p>

scholarly journals ANALISIS FAKTOR PENENTU INDEKS HARGA SAHAM GABUNGAN DI INDONESIA

2019 ◽  
Vol 1 (4) ◽  
pp. 37
Author(s):  
Yulizar Fikri ◽  
Ali Anis
Keyword(s):  
Economic Growth ◽  
Foreign Exchange ◽  
Stock Price ◽  
Price Index ◽  
Time Series Data ◽  
Secondary Data ◽  
Coefficient Of Determination ◽  
Series Data ◽  
Foreign Exchange Reserves ◽  
Stock Price Index

This study aims to determine the analysis of the determinants of the composite stock price index in Indonesia. The independent variables in this study are inflation as X1, foreign exchange reserves as X2, exchange rates as X3, and economic growth as X4, and the dependent variable of the composite stock price index as Y. The data used are secondary data in the formof time series data from 2010Q1 until 2019Q2, with data collection techniques, namely documentation from Bank Indonesia publications, the Central Statistics Agency, investing. comsite and library research. The research methods used are: (1) Multiple Linear Regression, (2) Classical Assumption Test (3) coefficient of determination. The results of this study indicate that:(1) inflation does not significantly influence the composite stock price index. (2) foreign exchange reserves have a significant positive effect on the composite stock price index. (3) the rupiah exchange rate has an influence on the composite stock price index and (4) economic growth hasno significant effect on the composite stock price index.

scholarly journals MENINGKATKAN KINERJA KEUANGAN RETURN ON EQUITY (ROE) MELALUI RASIO STRUKTUR MODAL DEBT TO ASSET RATIO (DAR) DAN DEBT TO EQUITY RATIO (DER) PADA PT BANK MANDIRI TBK YANG TERDAFTAR DI BURSA EFEK INDONESIA

2021 ◽  
Vol 12 (1) ◽  
pp. 52-65
Author(s):  
Armalinda Armalinda
Keyword(s):  
Financial Performance ◽  
Quantitative Research ◽  
Time Series Data ◽  
Stock Exchange ◽  
Statistical Tests ◽  
Financial Statements ◽  
Coefficient Of Determination ◽  
Series Data ◽  
Return On Equity ◽  
Equity Ratio

This study aims to determine how much influence the Debt to Assets Ratio (DAR) and Debt to Equity Ratio (DER) have on the Return on Equity (ROE) of PT Bank Mandiri Tbk which are listed on the Indonesia Stock Exchange. The research design used in this research is associative/quantitative research. The population in this study is the annual financial statements of PT. Bank Mandiri Tbk for the period 2012-2019, while the sample was taken using time series data, namely the annual financial statements of PT. Bank Mandiri Tbk for the period 2012-2019 which consists of balance statements, income statements, and cash flow from funding activities from 2012 to 2019. The result of the coefficient of determination (R Square) is 0.813. This figure means that 0.813 or 81.3% of the diversity of data from financial performance data can be explained by the two independent variables, namely the Debt to Asset Ratio and the Debt to Equity Ratio. While the rest (1-0.813 = 0.817) or 18.7% is explained by other factors outside the study. The results of statistical tests show that the Asset Ratio and Debt to Equity Ratio together (simultaneously) have an effect on financial performance (Return on Equity).

scholarly journals PENGARUH EKUIVALEN RATE BAGI HASIL, TINGKAT SUKU BUNGA DEPOSITO BPR DAN JUMLAH KANTOR BPRS TERHADAP JUMLAH NASABAH DEPOSITO iB MUDHARABAH PADA BPRS DI INDONESIA PERIODE 2016-2018

2019 ◽  
Vol 3 (2) ◽  
pp. 124-139
Author(s):  
Juliana Putri ◽  
Salman Alfarisi
Keyword(s):  
Interest Rates ◽  
Time Series Data ◽  
Predictive Analytics ◽  
Linear Regression Analysis ◽  
Profit Sharing ◽  
Variable Number ◽  
Coefficient Of Determination ◽  
Series Data ◽  
Equivalent Rate ◽  
Rate Of Profit

This study aims to determine the effect of the equivalent rate of profit sharing, interest rates on BPR deposits and the number of BPRS Offices on the number of mudharabah iB deposit customers at BPRS in Indonesia. The research method used is quantitative descriptive research using secondary data in the form of financial reports published by OJK in Sharia Banking Statistics (SPS) and Indonesian Banking Statistics (SPI) with time series data in the period of 2016-2018. The sample in this study all BPRS in Indonesia is 168 BPRS. Analysis of research using multiple linear regression analysis using application or supporting software namely PASW (Predictive Analytics SoftWare) Statistics 18, the results of research, it can be concluded that: 1) Equivalent rate of profit sharing (X1) has a significant negative effect of iB mudharabah deposit customers, 2) Variable interest rates on BPR deposits (X2) do not affect the number of mudharabah iB deposit customers. 3) The variable number of BPRS offices (X3) has a significant positive effect on the number of mudharabah iB deposit customers. 4) The coefficient of determination obtained is 0.586 or 58.6%. which means that 58.6% causes variable variable number of iB mudharabah (Y) deposit customers can be influenced by the equivalent rate of profit sharing, the level of BPR deposit rates and the number of BPRS offices, while the remaining 41.4% is influenced by other factors not included in the study.

A New Imputation Method for Treating Missing Precipitation Records

2014 ◽  
Vol 635-637 ◽  
pp. 1488-1495
Author(s):  
Yu Liu ◽  
Feng Rui Chen
Keyword(s):  
Time Series Data ◽  
Absolute Error ◽  
Imputation Method ◽  
Temporal Information ◽  
Series Data ◽  
Precipitation Trend ◽  
Monthly Total Precipitation ◽  
The Mean ◽  
Spatio Temporal ◽  
Precipitation Records

This study aims to present a new imputation method for missing precipitation records by fusing its spatio-temporal information. On the basis of extending simple kriging model, a nonstationary kriging method which assumes that the mean or trend is known and varies in whole study area was proposed. It obtains precipitation trend of each station at a given time by analyzing its time series data, and then performs geostatistical analysis on the residual between the trend and measured values. Finally, these spatio-temporal information is integrated into a unified imputation model. This method was illustrated using monthly total precipitation data from 671 meteorological stations of China in April, spanning the period of 2001-2010. Four different methods, including moving average, mean ratio, expectation maximization and ordinary kriging were introduced to compare with. The results show that: Among these methods, the mean absolute error, mean relative error and root mean square error of the proposed method are the smallest, so it produces the best imputation result. That is because: (1) It fully takes into account the spatio-temporal information of precipitation. (2) It assumes that the mean varies in whole study area, which is more in line with the actual situation for rainfall.

scholarly journals Field methods of a near-bed suspended sediment experiment in the Yangtze River, China

2020 ◽  
Vol 13 (21) ◽  
Author(s):  
Caiwen Shu ◽  
Guangming Tan ◽  
Yiwei Lv ◽  
Quanxi Xu
Keyword(s):  
Suspended Sediment ◽  
Suspended Sediment Concentration ◽  
Dynamic Equilibrium ◽  
Water Discharge ◽  
Sediment Concentration ◽  
Common Method ◽  
Sediment Discharge ◽  
Improved Method ◽  
The Common ◽  
The Impact

AbstractUsing experimental data of near-bed suspended sediment concentrations at five typical hydrometric stations of the Three Gorges Reservoir at the early reserving stage, the differences were investigated between the common method and improved method during flood seasons and non-flood seasons. The impact of taking measurements below 0.2 times the water depth on the results was discussed. The results show that the average discharges and velocities at each station calculated by the common method were slightly larger than those calculated by the improved method. Regarding the suspended sediment concentration at each station, the errors in the reservoir and downstream channels in dynamic equilibrium state were small, and the largest errors occurred where the river bed was strongly scoured in the downstream reach below the large dam. There was no significant relationship between water discharge and flow velocity, and the missed measurement phenomenon also occurred. The sediment discharge error was affected by the suspended sediment concentration, implying that errors usually occurred in channels with serious erosion during flood seasons. The correction coefficients (R2) of sediment discharge at each station were given during the experiment, which showed that the sediment discharges at the hydrometric stations where a large amount of sediment transport occurred near the river bottom, needed to be modified. Furthermore, the test methods proposed in this study were applied to calculate the sediment discharges of three rivers, and the results indicate that this method can narrow the gap between bathymetric comparisons and sediment load measurements.

Sign in / Sign up

Export Citation Format

Share Document