A comparative survey between cascade correlation neural network (CCNN) and feedforward neural network (FFNN) machine learning models for forecasting suspended sediment concentration

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

doi:10.1038/s41598-024-61339-1

A comparative survey between cascade correlation neural network (CCNN) and feedforward neural network (FFNN) machine learning models for forecasting suspended sediment concentration

Sci Rep. 2024 May 9;14(1):10638. doi: 10.1038/s41598-024-61339-1.

Authors

Affiliations

¹ Department of Agricultural Engineering, Institute of Agricultural Sciences, Banaras Hindu University, Varanasi, Uttar Pradesh, 221005, India.
² Department of Soil and Water Conservation Engineering, Acharya Narendra Deva University of Agriculture & Technology, Kumarganj, Ayodhya, Uttar Pradesh, 224229, India.
³ Department of Irrigation and Drainage Engineering, Govind Ballabh Pant University of Agriculture and Technology, Pantnagar, Uttarakhand, 263145, India. dinesh.vishwakarma4820@gmail.com.
⁴ Department of Water Engineering, Faculty of Agriculture, University of Tabriz, Tabriz, 5166616471, Iran.
⁵ Department of Railroad Construction and Safety Engineering, Dongyang University, 36040, Yeongju, South Korea.
⁶ Department of Irrigation and Drainage Engineering, Acharya Narendra Deva University of Agriculture & Technology, Kumarganj, Ayodhya, Uttar Pradesh, 224229, India.
⁷ Division of Agricultural Engineering, ICAR-Indian Agricultural Research Institute, New Delhi, 110012, India.
⁸ Department of Water Resources and River Research, Korea Institute of Civil Engineering and Building Technology, Goyang-si, 10223, Republic of Korea.
⁹ Faculty of Science and Technology, Madhyanchal Professional University, Ratibad, Bhopal, 462044, India.
¹⁰ Environmental and Atmospheric Sciences Research Group, Scientific Research Center, Al-Ayen University, Thi-Qar, Nasiriyah, 64001, Iraq.
¹¹ Department of Civil, Environmental, and Natural Resources Engineering, Lulea University of Technology, 97187, Luleå, Sweden. nadhir.alansari@ltu.se.
¹² Department of Agricultural Engineering, College of Food and Agriculture Sciences, King Saud University, P.O. Box 2460, Riyadh, 11451, Saudi Arabia. mmattar@ksu.edu.sa.

Abstract

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 (N_ES), 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 (Q_t-n) and suspended sediment concentration (S_t-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 (S_t-1, S_t-2, S_t-3, S_t-4) outperformed the other developed models with the lowest RMSE = 95.02 mg/l and the highest N_ES = 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 N_ES = 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.

Keywords: Cascade correlation neural network; Feedforward neural network; Machine learning; Seonath basin; Suspended sediment concentration.