Browsing by Author "Ehsan Mirzania"

Now showing 1 - 3 of 3

A comparative survey between cascade correlation neural network (CCNN) and feedforward neural network (FFNN) machine learning models for forecasting suspended sediment concentration
(Nature Research, 2024) Bhupendra Joshi; Vijay Kumar Singh; Dinesh Kumar Vishwakarma; Mohammad Ali Ghorbani; Sungwon Kim; Shivam Gupta; V.K. Chandola; Jitendra Rajput; Il-Moon Chung; Krishna Kumar Yadav; Ehsan Mirzania; Nadhir Al-Ansari; Mohamed A. Mattar
Suspended sediment concentration prediction is critical for the design of reservoirs, dams, rivers ecosystems, various operations of aquatic resource structure, environmental safety, and water management. In this study, two different machine models, namely the cascade correlation neural network (CCNN) and feedforward neural network (FFNN) were applied to predict daily-suspended sediment concentration (SSC) at Simga and Jondhara stations in Sheonath basin, India. Daily-suspended sediment concentration and discharge data from 2010 to 2015 were collected and used to develop the model to predict suspended sediment concentration. The developed models were evaluated using statistical indices like Nash and Sutcliffe efficiency coefficient (NES), root mean square error (RMSE), Willmott’s index of agreement (WI), and Legates–McCabe’s index (LM), supplemented by a scatter plot, density plots, histograms and Taylor diagram for graphical representation. The developed model was evaluated and compared with CCNN and FFNN. Nine input combinations were explored using different lag-times for discharge (Qt-n) and suspended sediment concentration (St-n) as input variables, with the current suspended sediment concentration as the desired output, to develop CCNN and FFNN models. The CCNN4 model with 4 lagged inputs (St-1, St-2, St-3, St-4) outperformed the other developed models with the lowest RMSE = 95.02 mg/l and the highest NES = 0.0.662, WI = 0.890 and LM = 0.668 for the Jondhara Station while the same CCNN4 model secure as the best with the lowest RMSE = 53.71 mg/l and the highest NES = 0.785, WI = 0.936 and LM = 0.788 for the Simga Station. The result shows the CCNN model was better than the FFNN model for predicting daily-suspended sediment at both stations in the Sheonath basin, India. Overall, CCNN showed better forecasting potential for suspended sediment concentration compared to FFNN at both stations, demonstrating their applicability for hydrological forecasting with complex relationships. © The Author(s) 2024.
A Novel Hybrid Algorithms for Groundwater Level Prediction
(Springer Science and Business Media Deutschland GmbH, 2023) Mohsen Saroughi; Ehsan Mirzania; Dinesh Kumar Vishwakarma; Shreya Nivesh; Kanhu Charaan Panda; Farnoosh Aghaee Daneshvar
Estimating groundwater levels (GWL) with accuracy and reliability, in order to maximize the use of water resources, it is crucial to reduce water consumption. To predict GWL in the Shabestar plain in the north-west of Iran, this case study developed a simulation–optimization hybrid model. For predicting GWL, the HBA (honey badger algorithm) optimizes parameters of ANNs (artificial neural networks) and SVRs (support vector regressions). Results were compared to ANN and SVR models. Datasets for periods of April 2001–March 2022 were utilized to develop and assess precision of the models. The average mutual information (AMI) is utilized to find out the combination of inputs for hybrid and standalone predictive models. In consideration of appropriate goodness-of-fit criteria, the predictive accuracy of models has been evaluated: correlation coefficient (R), root mean square error (RMSE), Nash–Sutcliffe model efficiency (NSE), mean absolute error (MAE), and Taylor diagram. Based on testing phase, the HBA-ANN model shows a very good agreement with the measured data (R = 0.999, RMSE(m) = 0.012, NSE = 0.999, MAE(m) = 0.012) followed by HBA-SVR (R = 0.999, RMSE(m) = 0.063, NSE = 0.977, MAE(m) = 0.046), SVR (R = 0.886, RMSE(m) = 0.245, NSE = 0.663, MAE(m) = 0.170) and ANN (R = 0.898, RMSE(m) = 0.272, NSE = 0.584, MAE(m) = 0.212). In conclusion, the HBA-ANN and HBA-SVR models can be used to forecast GWL based on outcomes of this study. Groundwater systems can be well estimated using such advanced AI techniques, saving resources, and labour conventionally employed. © 2023, The Author(s), under exclusive licence to Shiraz University.
An Integrated Statistical-Machine Learning Approach for Runoff Prediction
(MDPI, 2022) Abhinav Kumar Singh; Pankaj Kumar; Rawshan Ali; Nadhir Al-Ansari; Dinesh Kumar Vishwakarma; Kuldeep Singh Kushwaha; Kanhu Charan Panda; Atish Sagar; Ehsan Mirzania; Ahmed Elbeltagi; Alban Kuriqi; Salim Heddam
Nowadays, great attention has been attributed to the study of runoff and its fluctuation over space and time. There is a crucial need for a good soil and water management system to overcome the challenges of water scarcity and other natural adverse events like floods and landslides, among others. Rainfall–runoff (R-R) modeling is an appropriate approach for runoff prediction, making it possible to take preventive measures to avoid damage caused by natural hazards such as floods. In the present study, several data-driven models, namely, multiple linear regression (MLR), multiple adaptive regression splines (MARS), support vector machine (SVM), and random forest (RF), were used for rainfall–runoff prediction of the Gola watershed, located in the south-eastern part of the Uttarakhand. The rainfall–runoff model analysis was conducted using daily rainfall and runoff data for 12 years (2009 to 2020) of the Gola watershed. The first 80% of the complete data was used to train the model, and the remaining 20% was used for the testing period. The performance of the models was evaluated based on the coefficient of determination (R2), root mean square error (RMSE), Nash–Sutcliffe efficiency (NSE), and percent bias (PBAIS) indices. In addition to the numerical comparison, the models were evaluated. Their performances were evaluated based on graphical plotting, i.e., time-series line diagram, scatter plot, violin plot, relative error plot, and Taylor diagram (TD). The comparison results revealed that the four heuristic methods gave higher accuracy than the MLR model. Among the machine learning models, the RF (RMSE (m3/s), R2, NSE, and PBIAS (%) = 6.31, 0.96, 0.94, and −0.20 during the training period, respectively, and 5.53, 0.95, 0.92, and −0.20 during the testing period, respectively) surpassed the MARS, SVM, and the MLR models in forecasting daily runoff for all cases studied. The RF model outperformed in all four models’ training and testing periods. It can be summarized that the RF model is best-in-class and delivers a strong potential for the runoff prediction of the Gola watershed. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.