Modeling river discharge time series using support vector machine and artificial neural networks

Ghorbani, Mohammad Ali; Khatibi, Rahman; Goel, Arun; FazeliFard, M. H.; Azani, Atefeh

doi:10.1007/s12665-016-5435-6

Cited by 56 publications

(24 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Finally, 10 sensitivity parameters were selected: runoff curve number (CN 2 ), evaporation compensation coefficient of the soil (ESCO), available water of the soil (SOL_AWC), basis flow coefficient (ALPHA_BF), groundwater re-evaporation coefficient (GW_REVAP), surface runoff coefficient (SURLAG), linear index of the silt re-carried (SPCON), effective hydraulic conductivity of main river channel (CH_K 2 ), residual decomposition factor (RSDCO), and the power index of the silt re-carried (SPEXP). On the basis of model sensitivity analysis, the SCE-UA algorithm proposed by DUAN [30][31][32] was applied to adjust the above sensitivity parameters and determine the numerical value of each parameter by satisfying the two-control standard for E ns and R 2 , which are greater than 0.85, respectively ( Table 6).…”

Section: Calibrating and Validating The Parametersmentioning

confidence: 99%

An Improved SWAT for Predicting Manganese Pollution Load at the Soil-Water Interface in a Manganese Mine Area

Zhang¹,

Ren²,

Hursthouse³

et al. 2018

Pol. J. Environ. Stud.

View full text Add to dashboard Cite

Predicting pollution load at the soil-water interface is key to controlling runoff pollution in disturbed mining sites [1]. With the large-scale exploitation and smelting of ore, the solid resource and its waste (ore, waste ore, tailing sand, waste residue, etc.) result in the formation of heavy metal pollution flow in the soil-water interface under the effect of rainfall runoff [2-4]. In the long term, it could cause an increasingly prominent problem of heavy metal complex pollution in the manganese mine and the surrounding area [5]. This is particularly true for mining sites in the Hunan region of China, where largescale exploitation of metal manganese has generated large areas of degraded land. The soil and water assessment tool (SWAT) model developed by the U.S. Department of Agriculture in 1994 is a continuous distributed watershed environment model based on GIS software [6-7]. It has been widely applied to evaluate agricultural non-point source pollution [8-9]. The SWAT model includes two main parts: land surface process and water surface/confluence process. The former considers 8 modules of hydrology, meteorology, silt, soil temperature, crop growth, nutrient, pesticide, and agricultural management for system contribution; the later completes hydrological circulation and material migration of the basin through

show abstract

Section: Calibrating and Validating The Parametersmentioning

confidence: 99%

An Improved SWAT for Predicting Manganese Pollution Load at the Soil-Water Interface in a Manganese Mine Area

Zhang¹,

Ren²,

Hursthouse³

et al. 2018

Pol. J. Environ. Stud.

View full text Add to dashboard Cite

show abstract

“…ANN and MT performed equally well for estimation of discharge however, MT appear to be more transparent than ANN. Ghorbani et al (2016) compared the performance of SVM, ANN, MLR and simple rating curve (RC) reporting SVM to be best among them for estimating the discharge. Maghrebi and Ahmadi (2017) proposed an innovative approach for modelling discharge rating curve using isovel contours with the corresponding hydro-geometric parameters of the cross sections and dimensional analysis to interrelate the discharges at two different stages.…”

Section: Materials and Methodologymentioning

confidence: 99%

Review of Application of Data Driven Techniques in Discharge Rating Curve

Zakwan¹,

Muzzammil²,

Alam³

2017

Aquademia: Water, Environment and Technology

View full text Add to dashboard Cite

Establishing a reliable rating curve is an integral part of water resource engineering. The present paper is a review of data driven techniques used for modelling the stage discharge relationship over the last two decades. Over the year's several data driven techniques such as ANN, SVM, MT, fuzzy logic and GA have been applied by researchers in quest of arriving at a reliable technique to model the stage discharge relationship. Although, during this period several techniques have been used to establish the stage discharge relationship but the application of modern optimization tools such as ACO, PSO or PS has remained limited in this field. Therefore, application of modern optimization techniques and their comparison with existing literature would be appreciated in near future.

show abstract

“…The conventional support vector machine (SVM) is one of the machine learning methods [25]. The principle of machine learning is to minimize structural risk and achieve data classification or regression by applying kernel function and high-dimensional data simplification schemes (as presented in Equation (1)).…”

Section: Conventional Lssvm Modelmentioning

confidence: 99%

An Improved LSSVM Model for Intelligent Prediction of the Daily Water Level

Guo

Zhu

et al. 2018

Energies

View full text Add to dashboard Cite

Daily water level forecasting is of significant importance for the comprehensive utilization of water resources. An improved least squares support vector machine (LSSVM) model was introduced by including an extra bias error control term in the objective function. The tuning parameters were determined by the cross-validation scheme. Both conventional and improved LSSVM models were applied in the short term forecasting of the water level in the middle reaches of the Yangtze River, China. Evaluations were made with both models through metrics such as RMSE (Root Mean Squared Error), MAPE (Mean Absolute Percent Error) and index of agreement (d). More accurate forecasts were obtained although the improvement is regarded as moderate. Results indicate the capability and flexibility of LSSVM-type models in resolving time sequence problems. The improved LSSVM model is expected to provide useful water level information for the managements of hydroelectric resources in Rivers. Energies 2019, 12, 112 2 of 11 artificial neural network (ANN) methods. Palani et al. [8] applied an ANN model for water quality estimation. Nourani et al. [9] established an ANN model for groundwater level prediction. Ivan and Gilja [10] showed good performance of ANNs for hydraulic parameter prediction. However, the model accuracy differs with neuron structures and parameter calibrations might be time-consuming.The support vector machine (SVM) has been used to address short-term forecasting problems since the 90s of the 20th century, on the basis of which LSSVM (least squares support vector machine) is put forward to overcome drawbacks (e.g., computation cost [11], uncertainties in structural parameter determination [12]) of SVM. LSSVM models solve a linear matrix equation with fewer constraint conditions and have been utilized in a variety of applications, e.g., forecasting of groundwater level fluctuations [13], river stage [14], and watershed runoff [15]. In the case of monthly flow forecasting, Noori et al. [16] discussed the influence of parameter selections on the model performance. Hybrid models have also been proved to be effective ways, such as SVM-Wavelet transform [17].Although the LSSVM models provide favorable solutions in hydrological forecasting problems, issues such as the kernel function and unbalanced features need to be carefully explored. Cheng et al. [18] improved LSSVM by integrating an adaptive time function. Thereby, the dynamic nature of the time series is considered by assigning an appropriate weight in the cash flow prediction for construction projects. To cope with low efficiency, Cong et al. [19] incorporated the fruit fly optimization algorithm (FOA) for appropriate parameter values of LSSVM. Comparison between LS-SVM-FOA and other models indicated the superiority of the improved model. Ghorbani et al.[20] modelled river discharge time series using SVM and ANN. The authors conclude that SVM and ANN have an edge over the results by the conventional RC (Rating Curve) and MLR (Multiple Linear Regression) models. This is mor...

show abstract

Modeling river discharge time series using support vector machine and artificial neural networks

Cited by 56 publications

References 33 publications

An Improved SWAT for Predicting Manganese Pollution Load at the Soil-Water Interface in a Manganese Mine Area

An Improved SWAT for Predicting Manganese Pollution Load at the Soil-Water Interface in a Manganese Mine Area

Review of Application of Data Driven Techniques in Discharge Rating Curve

An Improved LSSVM Model for Intelligent Prediction of the Daily Water Level

Contact Info

Product

Resources

About