Integrative neural networks model for prediction of sediment rating curve parameters for ungauged basins

Atieh, Maya; Mehltretter, Samantha; Gharabaghi, Bahram; Rudra, R. P.

doi:10.1016/j.jhydrol.2015.11.008

Cited by 47 publications

(23 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An AEDI map may be developed for any region in the world using the methodology presented in this paper for generating a spatial AEDI map of Ontario. and Atieh, Mehltretter et al (2015) were the first to introduce AEDI as an input parameter to an artificial neural network (ANN) model to more accurately predict flow duration curve (FDC) and sediment rating curve (SRC) parameters at ungauged sites. The results of indicated that the parameters defining the log normal distribution for the FDCs (location and scale) were highly sensitive to AEDI.…”

Section: Applications Of Aedi In Hydrologic Modelingmentioning

confidence: 99%

“…Incorporating AEDI in the location and scale ANN models improved prediction performance by 7% and 21%, respectively. Atieh, Mehltretter et al (2015) reported that removing climatic parameters from the SRC prediction model decreased the correlation coefficient by 40% and the Nash-Sutcliffe coefficient by 42%. This paper recommends using AEDI in future hydrological modeling research such as runoff estimation, flood and drought prediction, and water quality studies.…”

Section: Applications Of Aedi In Hydrologic Modelingmentioning

confidence: 99%

“…These methods may be divided into bootstrap (Burn et al 2010), regression (Cheung et al 2008), and nonparametric methods (Tabari et al 2015). Trend and variation analysis of hydrologic parameters including flow and precipitation has commonly been studied by applying statistical analysis methods such as linear regression (Akinremi et al 1999;Asnaashari et al 2015;Atieh, Mehltretter et al 2015). However, the expected accuracy of linear regression analysis is limited because the relationships between hydrologic parameters are generally nonlinear.…”

Section: Introductionmentioning

confidence: 99%

“…Precipitation variability, quantified using entropy, is also an important parameter to include in various hydrologic modeling studies. and Atieh, Mehltretter et al (2015) developed an entropy parameter that captures both the temporal and spatial variability of precipitation in models for predicting flow duration curves and sediment parameters at ungauged sites, and found that including the entropy parameter improved predictions. Using entropy concepts for estimating the variability of hydrologic parameters is still a novel and appealing option that has not been fully investigated.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Investigating the Spatial and Temporal Variability of Precipitation using Entropy Theory

Atieh

Rudra

Gharabaghi

et al. 2017

JWMM

View full text Add to dashboard Cite

This study uses entropy theory to develop a novel application of the apportionment entropy disorder index (AEDI) to capture both spatial and temporal variability in monthly precipitation for various types of hydrologic modeling. In total, 41 Environment Canada stations across Ontario with long term (1955 to 2005) records and a very low percentage of missing data were selected. It was found that the fall and summer seasons are the major contributors to annual precipitation variability. Spatial variability of annual precipitation was observed to be increasing from southern to northern Ontario. The AEDI index map of Ontario, developed in this study, has been successfully integrated into several hydrologic models.

show abstract

Section: Applications Of Aedi In Hydrologic Modelingmentioning

confidence: 99%

Section: Applications Of Aedi In Hydrologic Modelingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Investigating the Spatial and Temporal Variability of Precipitation using Entropy Theory

Atieh

Rudra

Gharabaghi

et al. 2017

JWMM

View full text Add to dashboard Cite

show abstract

“…The following applications in various calculations of ANN in sediment load or transport can be developed by [15] for prediction of suspended sediment using ANN GA conjunction model with Markov chain approach at flood conditions, combining deterministic modelling with ANN for suspended sediment estimates [16]; integrative neural networks model for prediction of sediment rating curve parameters for ungauged basins [17]; a review sediment load change [18]; stream flow discharge and sediment rate relation using ANN [19]; evaluation of transport formulas and ANN models to estimate suspended load transport rate [20]; daily suspended sediment load prediction using ANN and support vector machines [21]; estimate sediment load in ungauged catchments using ANN [22]; suspended sediment modeling using genetic programming and soft computing techniques [23]; estimation of daily suspended sediments using support vector machines [24] and prediction of bed material load transport using neural network [25].…”

Section: Introductionmentioning

confidence: 99%

The application of backpropagation neural network method to estimate the sediment loads

et al. 2017

View full text Add to dashboard Cite

Abstract. Nearly all formulations of conventional sediment load estimation method were developed based on a review of laboratory data or data field. This approach is generally limited by local so it is only suitable for a particular river typology. From previous studies, the amount of sediment load tends to be non-linear with respect to the hydraulic parameters and parameter that accompanies sediment. The dominant parameter is turbulence, whereas turbulence flow velocity vector direction of x, y and z. They were affected by water bodies in 3D morphology of the cross section of the vertical and horizontal. This study is conducted to address the non-linear nature of the hydraulic parameter data and sediment parameter against sediment load data by applying the artificial neural network (ANN) method. The method used is the backpropagation neural network (BPNN) schema. This scheme used for projecting the sediment load from the hydraulic parameter data and sediment parameters that used in the conventional estimation of sediment load. The results showed that the BPNN model performs reasonably well on the conventional calculation, indicated by the stability of correlation coefficient (R) and the mean square error (MSE).

show abstract

Urban stormwater thermal gene expression models for protection of sensitive receiving streams

Sattar

Gharabaghi

Sabouri

et al. 2017

Hydrological Processes

Self Cite

View full text Add to dashboard Cite

Thermal impact of typical high-density residential, industrial, and commercial land uses is a major concern for the health of aquatic life in urban watersheds, especially in smaller, cold, and coolwater streams. This is the first study of its kind that provides simple easy-to-use equations, developed using gene expression programming (GEP) that can guide the assessment and the design of urban stormwater management systems to protect thermally sensitive receiving streams. We developed 3 GEP models using data collected during 3 years (2009-2011) from 4 urban catchments; the first GEP model predicts event mean temperature at the inlet of the pond; the second model predicts the stormwater temperature at the outlet of the pond; and the third model predicts the temperature of the stormwater after flowing through a cooling trench and before discharging to the receiving stream. The new models have high correlation coefficients of 0.90-0.94 and low prediction uncertainty of less than 4% of the median value of the predicted runoff temperatures. Sensitivity analysis shows that climatic factors have the highest influence on the thermal enrichment followed by the catchment characteristics and the key design variables of the stormwater pond and the cooling trench. The general method presented here is easily transferable to other regions of the world (but not necessarily the exact equations developed here); also through sensitivity and parametric analysis, we gained insight on the key factors and their relative importance in modelling thermal enrichment of urban stromwater runoff.

show abstract

Integrative neural networks model for prediction of sediment rating curve parameters for ungauged basins

Cited by 47 publications

References 59 publications

Investigating the Spatial and Temporal Variability of Precipitation using Entropy Theory

Investigating the Spatial and Temporal Variability of Precipitation using Entropy Theory

The application of backpropagation neural network method to estimate the sediment loads

Urban stormwater thermal gene expression models for protection of sensitive receiving streams

Contact Info

Product

Resources

About