Performance assessment of artificial neural networks and support vector regression models for stream flow predictions

Ateeq-ur-Rauf,; Ghumman, Abdul Razzaq; Ahmad, Sajjad; Hashmi, Hashim Nisar

doi:10.1007/s10661-018-7012-9

Cited by 40 publications

(5 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SVR with RBF kernel had better performance than the three SVR models (linear, polynomial, and sigmoid kernel) in both the training and testing phase; this is compatible with scientific results of ZAHRAIE et al [2011], LIMA et al [2013], GHUMMAN et al [2018] and TIAN et al [2018].…”

Section: Discussionsupporting

confidence: 88%

Journal of Water and Land Development

Bekri,

El Hmaidi,

Ousmana

et al. 2021

View full text Add to dashboard Cite

The purpose of this study is to develop mathematical models based on artificial intelligence: Models based on the support vectors regression (SVR) for drought forecast in the Ansegmir watershed (Upper Moulouya, Morocco). This study focuses on the prediction of the temporal aspect of the two drought indices (standardized precipitation index -SPI and standardized precipitation-evapotranspiration index -SPEI) using six hydro-climatic variables relating to the period 1979-2013. The model SVR3-SPI: RBF, ε = 0.004, C = 20 and γ = 1.7 for the index SPI, and the model SVR3-SPEI: RBF ε = 0.004, C = 40 and γ = 0.167 for the SPEI index are significantly better in comparison to other models SVR1, SVR2 and SVR4. The SVR model for the SPI index gave a correlation coefficient of R = 0.92, MSE = 0.17 and MAE = 0.329 for the learning phase and R = 0.90, MSE = 0.18 and MAE = 0.313 for the testing phase. As for the SPEI index, the overlay is slightly poorer only in the case of the SPI index between the observed values and the predicted ones by the SVR model. It shows a very small gap between the observed and predicted values. The correlation coefficients R = 0.88 for the learning, R = 0.86 for testing remain higher and corresponding to a quadratic error average MSE = 0.21 and MAE = 0.351 for the learning and MSE = 0.21 and MAE = 0.350 for the testing phase. The prediction of drought by SVR model remain useful and would be extremely important for drought risk management.

show abstract

Section: Discussionsupporting

confidence: 88%

Journal of Water and Land Development

Bekri,

El Hmaidi,

Ousmana

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The models, which included General Head Boundary (GHB), River, and Stream boundary conditions, showed calibration results with normalized Root Mean Square (RMS) errors ranging from 7.3% to 13.02%, and high correlation coefficients between 94% and 97%. The similarity of the normalized RMS values between the calibration and validation phases confirmed the validity of the models under all tested boundary conditions [8,9]. In recent years, the application of soft computing methods to simulate and estimate various environmental phenomena has gained considerable attention (Liu et al, 2008;Dastorani et al, 2010;Heddam et al, 2012;Ghumman et al, 2018).…”

Section: Introductionsupporting

confidence: 58%

“…The similarity of the normalized RMS values between the calibration and validation phases confirmed the validity of the models under all tested boundary conditions [8,9]. In recent years, the application of soft computing methods to simulate and estimate various environmental phenomena has gained considerable attention (Liu et al, 2008;Dastorani et al, 2010;Heddam et al, 2012;Ghumman et al, 2018). A notable study by Ebrahimi and Rajaee (2017) involved data collected from two wells in the Qom plain to simulate groundwater levels.…”

Section: Introductionmentioning

confidence: 60%

Analysis of Groundwater with Simulation Model MODFLOW: A Critical Review

et al. 2024

IJFMR

View full text Add to dashboard Cite

Groundwater modeling is an essential tool in hydrology for the management and protection of groundwater resources. MODFLOW, developed by the U.S. Geological Survey (USGS), is the most widely used groundwater flow simulation model. This paper reviews the development, applications, capabilities, and future perspectives of MODFLOW. We analyze various MODFLOW versions, its integration with other software, and its applicability in diverse hydrogeological contexts. Visual MODFLOW is a Graphical User Interface for the USGS MODFLOW and is commercially available. It is favored by Hydrogeologist for its user-friendly design. The software primarily facilitates the modeling of groundwater flow and contaminant transport under various conditions. This article aims to review the breadth of its applications in groundwater modeling over the past 22 years. Visual MODFLOW has been applied in diverse areas including agriculture, airfields, constructed wetlands, climate change, drought studies, environmental impact assessments, landfills, mining operations, river and floodplain monitoring, saltwater intrusion, soil profile surveys, and watershed analyses, among others. This review will elucidate the software’s scope and effectiveness in groundwater modeling and research to date. Groundwater modeling is crucial for predicting changes in groundwater systems and environmental conditions. This study focuses on simulating the groundwater level of the Pawana Watershed, India using three different models: MODFLOW, Extreme Learning Machine (ELM), and Wavelet-Extreme Learning Machine (WA-ELM). Initially, the simulation is conducted using MODFLOW, achieving reasonable accuracy with a correlation coefficient (R²) of 0.917 and a scatter index (SI) of 0.0004.

show abstract

“…Artificial intelligence (AI)-based approaches, i.e., machine learning (ML) methods, belong to the latter group. Widely used ML approaches include artificial neural networks (ANNs) and least-squares support vector machines (LSSVMs) (Ghumman et al, 2018;Kisi et al, 2019;Meng et al, 2019;Adnan et al, 2020;Ali and Shahbaz, 2020). Such models have been proven to be efficient tools to model qualitative and quantitative hydrological variables and deal with nonlinear features in streamflow.…”

Section: Introductionmentioning

confidence: 99%

AI-based techniques for multi-step streamflow forecasts: application for multi-objective reservoir operation optimization and performance assessment

Guo

et al. 2021

Hydrol. Earth Syst. Sci.

View full text Add to dashboard Cite

Abstract. Streamflow forecasts are traditionally effective in mitigating water scarcity and flood defense. This study developed an artificial intelligence (AI)-based management methodology that integrated multi-step streamflow forecasts and multi-objective reservoir operation optimization for water resource allocation. Following the methodology, we aimed to assess forecast quality and forecast-informed reservoir operation performance together due to the influence of inflow forecast uncertainty. Varying combinations of climate and hydrological variables were input into three AI-based models, namely a long short-term memory (LSTM), a gated recurrent unit (GRU), and a least-squares support vector machine (LSSVM), to forecast short-term streamflow. Based on three deterministic forecasts, the stochastic inflow scenarios were further developed using Bayesian model averaging (BMA) for quantifying uncertainty. The forecasting scheme was further coupled with a multi-reservoir optimization model, and the multi-objective programming was solved using the parameterized multi-objective robust decision-making (MORDM) approach. The AI-based management framework was applied and demonstrated over a multi-reservoir system (25 reservoirs) in the Zhoushan Islands, China. Three main conclusions were drawn from this study: (1) GRU and LSTM performed equally well on streamflow forecasts, and GRU might be the preferred method over LSTM, given that it had simpler structures and less modeling time; (2) higher forecast performance could lead to improved reservoir operation, while uncertain forecasts were more valuable than deterministic forecasts, regarding two performance metrics, i.e., water supply reliability and operating costs; (3) the relationship between the forecast horizon and reservoir operation was complex and depended on the operating configurations (forecast quality and uncertainty) and performance measures. This study reinforces the potential of an AI-based stochastic streamflow forecasting scheme to seek robust strategies under uncertainty.

show abstract

Performance assessment of artificial neural networks and support vector regression models for stream flow predictions

Cited by 40 publications

References 44 publications

Journal of Water and Land Development

Journal of Water and Land Development

Analysis of Groundwater with Simulation Model MODFLOW: A Critical Review

AI-based techniques for multi-step streamflow forecasts: application for multi-objective reservoir operation optimization and performance assessment

Contact Info

Product

Resources

About