Urmia lake water level fluctuation hydro informatics modeling using support vector machine and conjunction of wavelet and neural network

Noury, Mojtaba; Sedghi, Hossein; Babazedeh, Hosein; Fahmi, Hedayat

doi:10.1134/s0097807814030129

Cited by 20 publications

(15 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, WLF forecasting via ANNs based on data transformed with wavelets was determined to be more effective than using raw data in ANNs. This confirms the conclusions presented by Noury et al (2014). Knowledge about WLF may be used in the construction of small hydropower plants, which are a source of renewable energy.…”

Section: Discussionsupporting

confidence: 89%

Forecasting surface water-level fluctuations of a small glacial lake in Poland using a wavelet-based artificial intelligence method

2018

View full text Add to dashboard Cite

Lake waters are a significant source of drinking water and contribute to the local economy (e.g. enabling irrigation, offering opportunities for tourism, waterways for transport, and meeting utility water demands); therefore, the ability to accurately forecast lake water levels is important. However, given the significant lack of research with respect to forecasting water levels in small lakes (i.e. 0.05 km 2 \ area \ 10 km 2 ), the present study sought to address this knowledge gap by testing a pair of hypotheses: (1) it is possible to forecast water levels in small surface lakes using artificial neural networks (ANN), and (2) better water-level forecasts will be obtained when the wavelet transform (WT) is used as an input data preprocessing tool. Based on an analysis of a case study in Lake Biskupinskie (1.16 km 2 ) in Poland and based on a range of model performance statistics (e.g. mean absolute error, root mean square error, mean squared error, coefficient of determination, mean absolute percentage error), both hypotheses were confirmed for monthly forecasting of lake water levels. ANNs provided good forecasting results, and WT pre-processing of input data led to even better forecasts. Additionally, it was found that meteorological variables did not have a significant impact in forecasting water-level fluctuations. In light of the results and the limited scope of the present study, proposed future research directions and problems to be resolved are discussed.

show abstract

Section: Discussionsupporting

confidence: 89%

Forecasting surface water-level fluctuations of a small glacial lake in Poland using a wavelet-based artificial intelligence method

2018

View full text Add to dashboard Cite

show abstract

“…It got the most beneficial values of MAPE, RMSE and R2 criteria, while the value of MBE did not diverge far from that of the MLR models. Similar values of individual forecasting criteria have been obtained by other researchers, despite the different characteristics of the lakes investigated (Kisi et al 2012;Noury et al 2014;Young 2015;Yarar et al 2009;Vaziri 1997). This confirms the possibility of an efficient application of ANN to forecasting water level of lakes located in temperate climates (with cold winters) and having a relatively low area (under 100 km 2 ).…”

Section: Resultssupporting

confidence: 84%

Forecasting Surface Water Level Fluctuations of Lake Serwy (Northeastern Poland) by Artificial Neural Networks and Multiple Linear Regression

Piasecki

Jurasz

Skowron

2017

Journal of Environmental Engineering and Landscape Management

View full text Add to dashboard Cite

The aim of this study is to assess the possibility of forecasting water level fluctuations in a relatively small (<100 km2), post-glacial lake located in a temperate climate zone by means of artificial neural networks and multiple linear regression. The area of study was Lake Serwy, located in northeastern Poland. Two artificial neural network (ANN) multilayer perceptron (MLP) and multiple linear regression (MLR) models were built. The following explanatory variables were considered: maximal and minimal temperature (Tmax, Tmin) wind speed (WS), vertical circulation (VC) and water level from previous periods (WL). Additionally, a binary variable describing the period of the year (winter, summer) has been considered in one of the two MLP and MLR models. The forecasting models have been assessed based on selected criteria: mean absolute percentage error (MAPE), root mean squared error (RMSE), coefficient of determination (R2) and mean biased error. Considering their values and absolute deviations from observed values it was concluded that the ANN model using an additional binary variable (MLP_B+) has the best forecasting performance. Absolute deviations from observed values were the determining factor which made this model the most efficient. In the case of the MLP_B+ model, those values were about 10% lower than in other models. The conducted analyses indicated good performance of ANN networks as a forecasting tool for relatively small lakes located in temperate climate zones. It is acknowledged that they enable water level forecasting with greater precision and lower absolute deviations than the use of multiple linear regression models.

show abstract

“…Evaporation and other variables of the water balance equation, the water exchange with soils, and seepage of water at the lake bottom can also influence the water balance of a lake and hence cause WLF [42] . Recent advances in hydroinformatics actually allowed for an extremely accurate modelling of water levels [16] . However, this accuracy was only achieved in lakes, whose water level is solely governed by natural hydrological processes [16] .…”

Section: Discussionmentioning

confidence: 99%

“…Recent advances in hydroinformatics actually allowed for an extremely accurate modelling of water levels [16] . However, this accuracy was only achieved in lakes, whose water level is solely governed by natural hydrological processes [16] . Hydrological processes are likely to play only a minor role in reservoirs, at least in determining the amplitude of WLF.…”

Section: Discussionmentioning

confidence: 99%

“…In a purely natural context of pristine lakes, modelling WLF is possible with ever increasing accuracy. For example, using elaborate hydroinformatics, Noury et al [16] modelled the hydrologic drivers of WLF in Umuria lake, Iran, with great precision. In reservoirs, however, it is energy production that mainly drives WLF and not hydrological processes [12] .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Hydro-Economic Model for Water Level Fluctuations: Combining Limnology with Economics for Sustainable Development of Hydropower

et al. 2014

View full text Add to dashboard Cite

Water level fluctuations in lakes lead to shoreline displacement. The seasonality of flooding or beaching of the littoral area affects nutrient cycling, redox gradients in sediments, and life cycles of aquatic organisms. Despite the ecological importance of water level fluctuations, we still lack a method that assesses water levels in the context of hydropower operations. Water levels in reservoirs are influenced by the operator of a hydropower plant, who discharges water through the turbines or stores water in the reservoir, in a fashion that maximizes profit. This rationale governs the seasonal operation scheme and hence determines the water levels within the boundaries of the reservoir's water balance. For progress towards a sustainable development of hydropower, the benefits of this form of electricity generation have to be weighed against the possible detrimental effects of the anthropogenic water level fluctuations. We developed a hydro-economic model that combines an economic optimization function with hydrological estimators of the water balance of a reservoir. Applying this model allowed us to accurately predict water level fluctuations in a reservoir. The hydro-economic model also allowed for scenario calculation of how water levels change with climate change scenarios and with a change in operating scheme of the reservoir (increase in turbine capacity). Further model development will enable the consideration of a variety of additional parameters, such as water withdrawal for irrigation, drinking water supply, or altered energy policies. This advances our ability to sustainably manage water resources that must meet both economic and environmental demands.

show abstract

Urmia lake water level fluctuation hydro informatics modeling using support vector machine and conjunction of wavelet and neural network

Cited by 20 publications

References 13 publications

Forecasting surface water-level fluctuations of a small glacial lake in Poland using a wavelet-based artificial intelligence method

Forecasting surface water-level fluctuations of a small glacial lake in Poland using a wavelet-based artificial intelligence method

Forecasting Surface Water Level Fluctuations of Lake Serwy (Northeastern Poland) by Artificial Neural Networks and Multiple Linear Regression

A Hydro-Economic Model for Water Level Fluctuations: Combining Limnology with Economics for Sustainable Development of Hydropower

Contact Info

Product

Resources

About