Intermittent reservoir daily-inflow prediction using lumped and distributed data multi-linear regression models

Magar, Rajendra; Jothiprakash, V.

doi:10.1007/s12040-011-0127-9

Cited by 31 publications

(12 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional statistical models (i.e., multiple linear regression model) have shown substantially comprehensive and adequate results to the ongoing demand for as close to real-time as possible analysis and prediction [55][56][57][58]. In our study MLR and ANN applications in decomposed time series substantially increase the model accuracy.…”

Section: Performance Of Ann and Mlr On Decomposition Datamentioning

confidence: 78%

“…The prediction accuracy of the water discharge can be improved using ANNs. These have been shown to be highly efficient in predictions of the time series data in a range of environments [55,56,58]. Therefore, a hybrid time series analysis and artificial neural network approach increases the prediction in all the components of the water discharge time series.…”

Section: Performance Of Ann and Mlr On Decomposition Datamentioning

confidence: 99%

See 1 more Smart Citation

Artificial Neural Network and Multiple Linear Regression for Flood Prediction in Mohawk River, New York

Tsakiri

Marsellos

Kapetanakis

2018

Water

View full text Add to dashboard Cite

This research introduces a hybrid model for forecasting river flood events with an example of the Mohawk River in New York. Time series analysis and artificial neural networks are combined for the explanation and forecasting of the daily water discharge using hydrogeological and climatic variables. A low pass filter (Kolmogorov–Zurbenko filter) is applied for the decomposition of the time series into different components (long, seasonal, and short-term components). For the prediction of the water discharge time series, each component has been described by applying the multiple linear regression models (MLR), and the artificial neural network (ANN) model. The MLR retains the advantage of the physical interpretation of the water discharge time series. We prove that time series decomposition is essential before the application of any model. Also, decomposition shows that the Mohawk River is affected by multiple time scale components that contribute to the hydrologic cycle of the included watersheds. Comparison of the models proves that the application of the ANN on the decomposed time series improves the accuracy of forecasting flood events. The hybrid model which consists of time series decomposition and artificial neural network leads to a forecasting up to 96% of the explanation for the water discharge time series.

show abstract

Section: Performance Of Ann and Mlr On Decomposition Datamentioning

confidence: 78%

Section: Performance Of Ann and Mlr On Decomposition Datamentioning

confidence: 99%

Artificial Neural Network and Multiple Linear Regression for Flood Prediction in Mohawk River, New York

Tsakiri

Marsellos

Kapetanakis

2018

Water

View full text Add to dashboard Cite

show abstract

“…Values of exponent "n" were obtained for each of the 4 sub-basins of Okhunwan, Oyanmi, Owan, and Osse as n 1 , n n 2 , n 3 , and n 4, respectively. Mean value (n) was obtained for the entire basin of Benin-Owena River Basin Development Authority (BORBDA) area by averaging the obtained exponent "n" of the 4 sub-basins utilizing lumped modeling technique, which considers a catchment as a single entity for computations and permit watershed parameters and variables to be averaged over this unit [38,39]. Therefore, mean − X value can be obtained from Eq.…”

Section: Catchment-area Ratio Modelmentioning

confidence: 99%

Exponent determination in a poorly gauged basin system in Nigeria based on flow characteristics investigation and regionalization method

Fasipe¹,

Izinyon

2021

SN Appl. Sci.

View full text Add to dashboard Cite

In this study, a method for estimating the exponent “n” values of the catchment-area equations of four sub-basins within the poorly gauged Benin-Owena River Basin Development Authority (BORBDA) in Nigeria is presented to enable the estimation of flows at ungauged sites within the basin and the determination of small hydropower (SHP) potential at different locations in each sub-basin and the entire basin. Optimal prediction of streamflow characteristics in poorly gauged basin requires developing a methodology for extrapolation of data from gauged to ungauged sites within the basin. Four sub-catchments of BORBDA, a poorly gauged basin in Nigeria, were investigated using Remote Sensing (RS), Geographic Information System (GIS), statistical techniques, and Natural Resources Conservation Service-Curve Number (NRCS-CN) hydrological model. Discharge values at gauged sites (Qg) were obtained from recorded discharge values collected for 12 months at an established gauging station in each sub-basin. RS and GIS techniques were used to develop classification maps and obtain crucial data like curve number (CN), elevation, Hydrologic Soil Group (HSG), rainfall intensity, slope, area of gauged and ungauged required for evaluating spatial discharge (ungauged) utilizing NRCS-CN model. From the established model for each sub-basin, exponent “n” in the relationship between discharge and catchment area was obtained to be 0.23, 0.41, 0.71, and 0.74. Using the lumped modeling approach, which considers a watershed as a single unit for computation, where watershed parameters and variables were to be averaged produced “n” = 0.52 for BORBDA area, which is within the range of 0.5–0.85 suggested by previous researchers. Obtained BORBDA exponent “n” was validated for use in the entire basin through soil homogeneity test by generating BORBDA soil map which confirms the four sub-basins investigated share similar HSG A, B, and D with BORBDA. The exponent “n” value is useful for predicting flows in ungauged parts of the basin. The exponent “n” value obtained for the basin is helpful in the assessment of discharge and determination of SHP potential at different locations within the poorly gauged BORBDA basin, and the dissemination of the research findings will find practical use and guide to practicing hydrologists in Nigeria and locations around the world with similar challenges of poorly gauged basins particularly Africa and other developing countries.

show abstract

“…It is very difficult to measure all the model parameters precisely, they are always data based. About 28 hydrologic models, were evaluated by ASCE Task Committee, for adopting them in absence of data for un-gauged basins [16]. The hydrologic modeling took off from traditional empirical models to conceptual lumped models and to the present day distributed models.…”

Section: Conventional Hydrological Modelsmentioning

confidence: 99%

Prediction of Sediment Deposition in Reservoir Using Analytical Method

Patil¹

2016

AJCE

View full text Add to dashboard Cite

Sediment particles, a product of erosion in the catchment are transported along the river with flowing water. The construction of Weir, barrage or a dam causes obstruction to the flow resulting in reduction of velocity. The reduced velocity causes sedimentation resulting in reduction of storage capacity which affects the overall life of the reservoir. The sediment deposition in the reservoir is a continuous and complex process which affects the useful life of a reservoir. The quantification of sediment deposition in a reservoir is necessary for effective reservoir and river basin management. The present study has been carried out to assess sediment deposition in Koyna Reservoir which is located in the Western Maharashtra, India. In India most of the rainfall is caused due to the southwest monsoon during the period from June to September, massive convective thunderstorms dominate the weather. In the present study analytical methods are used for estimation of sediment deposited in the Koyna reservoir. For the prediction annual inflow data is used. The storage capacity of Koyna reservoir is calculated considering the loss of storage due to sediment deposition for a period from 1961 to 2375. The results obtained indicated a loss of reservoir capacity by the year 2004, as 267.25 Mm 3 (9.55%). The physical measurement indicated that the Koyna reservoir had lost 293.09 Mm 3 (10.48%) of its capacity by the year 2004. The results obtained by analytical method have 8.82% error compared with the actual measurements.

show abstract

Intermittent reservoir daily-inflow prediction using lumped and distributed data multi-linear regression models

Cited by 31 publications

References 32 publications

Artificial Neural Network and Multiple Linear Regression for Flood Prediction in Mohawk River, New York

Artificial Neural Network and Multiple Linear Regression for Flood Prediction in Mohawk River, New York

Exponent determination in a poorly gauged basin system in Nigeria based on flow characteristics investigation and regionalization method

Prediction of Sediment Deposition in Reservoir Using Analytical Method

Contact Info

Product

Resources

About