Research Article | | Peer-Reviewed

Artificial Neural Network Based Runoff and Sediment Yield Modeling of Maybar Watershed, Awash Basin, Ethiopia

Received: 27 November 2023     Accepted: 19 December 2023     Published: 28 December 2023
Views:       Downloads:
Abstract

Runoff and sediment are important parameters to be understood and predict for managing land and water resource. So, understanding the dynamic process and prediction of the existing process by selecting suitable hydrological model is very essential. This study aims to test and evaluate the application of an artificial neural network (ANN) model for modeling runoff and sediment yield of Maybar watershed, Awash River basin. The ANN model was trained and cross validated using MATLAB, supported by the NN toolbox package. The main input for the ANN model was selected using correlation results from Statistical Packages for Social Science (SPSS). Present rainfall and previous one-day runoff up to four days of runoff were selected as inputs for runoff modeling, and present rainfall, present runoff, and previous one-day runoff were selected as inputs for sediment yield modeling. The proposed model was developed, trained, and cross validated by considering 7 years of data (2010–2016) for model training and 2 years of data for model testing (cross-validation), and their performance was evaluated using performance indicators (R2, RMSE, and NSE). Adding lag of runoff as input results increase the model efficiency during training. Of the five proposed ANN runoff models, model B (2 inputs, 3 hidden neurons, 1 output) performed better than the other proposed runoff models. Similarly, of the three proposed ANN sediment models, model III (3 inputs, 6 hidden neurons, 1 output) performed better than the other proposed sediment models. In general, the ANN model was applicable for predicting runoff and sediment in the Maybar watershed in daily time steps.

Published in International Journal of Intelligent Information Systems (Volume 12, Issue 4)
DOI 10.11648/j.ijiis.20231204.12
Page(s) 63-75
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2023. Published by Science Publishing Group

Keywords

Artificial Neural Networks, Runoff Modeling, Sediment Yield Modeling, Maybar Watershed

References
[1] A. sezin tokar and momcilo markus. 2015. “Precipitation Runoff Modeling Using Artificial Neural Network and Conceptual PRECIPITATION-RUNOFF MODEL.” 0699 (November).
[2] Abirendra Bharti, Ashish Pandey, S. K. Tripathi and Dheeraj Kumar. 2017. “Modelling of Runoff and Sediment Yield Using ANN, LS-SVR, REPTree and M5 Models.” 1489–1507.
[3] Agarwal, Avinash, R K Rai, and Alka Upadhyay. 2014. “Forecasting of Runoff and Sediment Yield Using Artificial Neural Networks.” (May).
[4] Alegre, Porto et al. 2022. “Application of ANNs for the Modeling of Streamflow, Sediment Transport, and Erosion Rate of a High-Altitude River System in Western Himalaya, Uttarakhand.”: 1–15.
[5] Andredaki, M., A. Georgoulas, V. Hrissanthou, and N. Kotsovinos. 2014. “Assessment of Reservoir Sedimentation Effect on Coastal Erosion in the Case of Nestos River, Greece.” International Journal of Sediment Research 29(1): 34–48.
[6] Chakravarti, Ankit, Nitin Joshi, and Himanshu Panjiar. 2015. “Rainfall Runoff Analysis Using Artificial Neural Network.” 8(July).
[7] Dawson, C W, and R L Wilby. 2001. “Hydrological Modelling Using Artificial Neural Networks.” 1: 80–108.
[8] Dawson, Christian W. 1998. “An Artificial Neural Network Approach to Rainfall- Runoff Modelling.” 43(February): 47–66.
[9] Demirel, Mehmet C., Anabela Venancio, and Ercan Kahya. 2009. “Flow Forecast by SWAT Model and ANN in Pracana Basin, Portugal.” Advances in Engineering Software 40(7): 467–73.
[10] Devia, Gayathri K., B. P. Ganasri, and G. S. Dwarakish. 2015. “A Review on Hydrological Models.” Aquatic Procedia 4(Icwrcoe): 1001–7.
[11] FAO. 2016. “AQUASTAT Country Profile – Ethiopia. Food and Agriculture Organization of the United Nations (FAO). Rome, Italy.” FAO, AQUSAT reports: 11–12.
[12] Gebremedhin Tesfayea, Abera Assefab and Desale Kidanec. 2016. “Runoff, Sediment Load and Land Use / Cover Change Relationship: The Case of Maybar Sub-Watershed, South Wollo, Ethiopia.” Intl. J. River Basin Management 0(0): 1–13.
[13] Govindaraju, Rao S. 2000. “A RTIFICIAL N EURAL N ETWORKS IN H YDROLOGY. By the ASCE Task Committee on Application of Artificial Neural Networks in Hydrology 1.” (April).
[14] Habtamu Asrat and Wasihun Gedefaw. 1975. “Maybar Watershed Run off Modeling Habtamu Asrat and Gedefaw Wasihun, Debre Marko s University.”: 148–76.
[15] Haykin, Simon. 2001. “Neural Networks - A Comprehensive Foundation.”
[16] Jimeno-s, Patricia, Javier Senent-aparicio, and David Pulido-velazquez. “A Comparison of SWAT and ANN Models for Daily Runoff Simulation in Different Climatic Zones of Peninsular Spain.
[17] Kişi, Özgür. 2004. “Multi-Layer Perceptrons with Levenberg-Marquardt Training Algorithm for Suspended Sediment Concentration Prediction and Estimation.” Hydrological Sciences Journal 49(6): 1025–40.
[18] Marcoulides, George A. 2005. 100 Journal of the American Statistical Association Discovering Knowledge in Data: An Introduction to Data Mining.
[19] Mohammed, Jemal. 2015. “Stream Flow and Sediment Yield Modeling, The Case Of Gidabo Watershed.”
[20] Nina, Kemal. 2016. “Megech Dam Reservoir Seidement Estimation (Using SWAT Model).” (September).
[21] Nivesh, Shreya, and Pravendra Kumar. 2017. “Modelling River Suspended Sediment Load Using Artificial Neural Network and Multiple Linear Regression: Vamsadhara River Basin, India.” 5(5): 337–44.
[22] Raju, M Mohan et al. 2011. “Development of Artificial Neural-Network-Based Models for the Simulation of Spring Discharge.” 2011.
[23] Shu, C., and T. B. M. J. Ouarda. 2007. “Flood Frequency Analysis at Ungauged Sites Using Artificial Neural Networks in Canonical Correlation Analysis Physiographic Space.” Water Resources Research 43(7).
[24] Singh, Aparajita. 2018. “A Concise Review on Introduction to Hydrological Models.” Global Research and Development Journal for Engineering 3(10): 14–19.
[25] Svozil, Daniel, Vladimír Kvasnička, and Jiří Pospíchal. 1997. “Introduction to Multi-Layer Feed-Forward Neural Networks.” Chemometrics and Intelligent Laboratory Systems 39(1): 43–62.
[26] Tamene, Lulseged, and Paul L. G. Vlek. 2008. “Soil Erosion Studies in Northern Ethiopia.” Land Use and Soil Resources: 73–100.
[27] Tesfa, Yimer. 2015. “Comparative Hydrological Modeling of Maybar Watershed Using Swat-WB and Swat-CN, Awash Basin, Amhara Region.” (May).
[28] Yesuf, Hassen M, Mohammed Assen, Tena Alamirew, and Assefa M Melesse. 2015. “Modeling of Sediment Yield in Maybar Gauged Watershed Using SWAT, Northeast Ethiopia.” 127: 191–205.
[29] Zhu, Yun-mei, X X Lu, and Yue Zhou. 2007. “Suspended Sediment Flux Modeling with Artificial Neural Network: An Example of the Longchuanjiang River in the Upper Yangtze.” 84: 111–25.
Cite This Article
  • APA Style

    Hassen, H. A., Tibebu, Y., Negashe, D., Ayana, M., Abera, F. F. (2023). Artificial Neural Network Based Runoff and Sediment Yield Modeling of Maybar Watershed, Awash Basin, Ethiopia. International Journal of Intelligent Information Systems, 12(4), 63-75. https://doi.org/10.11648/j.ijiis.20231204.12

    Copy | Download

    ACS Style

    Hassen, H. A.; Tibebu, Y.; Negashe, D.; Ayana, M.; Abera, F. F. Artificial Neural Network Based Runoff and Sediment Yield Modeling of Maybar Watershed, Awash Basin, Ethiopia. Int. J. Intell. Inf. Syst. 2023, 12(4), 63-75. doi: 10.11648/j.ijiis.20231204.12

    Copy | Download

    AMA Style

    Hassen HA, Tibebu Y, Negashe D, Ayana M, Abera FF. Artificial Neural Network Based Runoff and Sediment Yield Modeling of Maybar Watershed, Awash Basin, Ethiopia. Int J Intell Inf Syst. 2023;12(4):63-75. doi: 10.11648/j.ijiis.20231204.12

    Copy | Download

  • @article{10.11648/j.ijiis.20231204.12,
      author = {Hussen Ali Hassen and Yonatan Tibebu and Dagemawi Negashe and Mehret Ayana and Fikru Fentaw Abera},
      title = {Artificial Neural Network Based Runoff and Sediment Yield Modeling of Maybar Watershed, Awash Basin, Ethiopia},
      journal = {International Journal of Intelligent Information Systems},
      volume = {12},
      number = {4},
      pages = {63-75},
      doi = {10.11648/j.ijiis.20231204.12},
      url = {https://doi.org/10.11648/j.ijiis.20231204.12},
      eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijiis.20231204.12},
      abstract = {Runoff and sediment are important parameters to be understood and predict for managing land and water resource. So, understanding the dynamic process and prediction of the existing process by selecting suitable hydrological model is very essential. This study aims to test and evaluate the application of an artificial neural network (ANN) model for modeling runoff and sediment yield of Maybar watershed, Awash River basin. The ANN model was trained and cross validated using MATLAB, supported by the NN toolbox package. The main input for the ANN model was selected using correlation results from Statistical Packages for Social Science (SPSS). Present rainfall and previous one-day runoff up to four days of runoff were selected as inputs for runoff modeling, and present rainfall, present runoff, and previous one-day runoff were selected as inputs for sediment yield modeling. The proposed model was developed, trained, and cross validated by considering 7 years of data (2010–2016) for model training and 2 years of data for model testing (cross-validation), and their performance was evaluated using performance indicators (R2, RMSE, and NSE). Adding lag of runoff as input results increase the model efficiency during training. Of the five proposed ANN runoff models, model B (2 inputs, 3 hidden neurons, 1 output) performed better than the other proposed runoff models. Similarly, of the three proposed ANN sediment models, model III (3 inputs, 6 hidden neurons, 1 output) performed better than the other proposed sediment models. In general, the ANN model was applicable for predicting runoff and sediment in the Maybar watershed in daily time steps.
    },
     year = {2023}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Artificial Neural Network Based Runoff and Sediment Yield Modeling of Maybar Watershed, Awash Basin, Ethiopia
    AU  - Hussen Ali Hassen
    AU  - Yonatan Tibebu
    AU  - Dagemawi Negashe
    AU  - Mehret Ayana
    AU  - Fikru Fentaw Abera
    Y1  - 2023/12/28
    PY  - 2023
    N1  - https://doi.org/10.11648/j.ijiis.20231204.12
    DO  - 10.11648/j.ijiis.20231204.12
    T2  - International Journal of Intelligent Information Systems
    JF  - International Journal of Intelligent Information Systems
    JO  - International Journal of Intelligent Information Systems
    SP  - 63
    EP  - 75
    PB  - Science Publishing Group
    SN  - 2328-7683
    UR  - https://doi.org/10.11648/j.ijiis.20231204.12
    AB  - Runoff and sediment are important parameters to be understood and predict for managing land and water resource. So, understanding the dynamic process and prediction of the existing process by selecting suitable hydrological model is very essential. This study aims to test and evaluate the application of an artificial neural network (ANN) model for modeling runoff and sediment yield of Maybar watershed, Awash River basin. The ANN model was trained and cross validated using MATLAB, supported by the NN toolbox package. The main input for the ANN model was selected using correlation results from Statistical Packages for Social Science (SPSS). Present rainfall and previous one-day runoff up to four days of runoff were selected as inputs for runoff modeling, and present rainfall, present runoff, and previous one-day runoff were selected as inputs for sediment yield modeling. The proposed model was developed, trained, and cross validated by considering 7 years of data (2010–2016) for model training and 2 years of data for model testing (cross-validation), and their performance was evaluated using performance indicators (R2, RMSE, and NSE). Adding lag of runoff as input results increase the model efficiency during training. Of the five proposed ANN runoff models, model B (2 inputs, 3 hidden neurons, 1 output) performed better than the other proposed runoff models. Similarly, of the three proposed ANN sediment models, model III (3 inputs, 6 hidden neurons, 1 output) performed better than the other proposed sediment models. In general, the ANN model was applicable for predicting runoff and sediment in the Maybar watershed in daily time steps.
    
    VL  - 12
    IS  - 4
    ER  - 

    Copy | Download

Author Information
  • Department of Hydraulic and Water Resources Engineering, Kombolcha Institute of Technology, Wollo University, Kombolcha, Ethiopia

  • Department of Hydraulic and Water Resources Engineering, Woldiya University, Woldiya, Ethiopia

  • Department of Hydraulic and Water Resources Engineering, Kombolcha Institute of Technology, Wollo University, Kombolcha, Ethiopia

  • Department of Hydraulic and Water Resources Engineering, Kombolcha Institute of Technology, Wollo University, Kombolcha, Ethiopia

  • Department of Hydraulic and Water Resources Engineering, Kombolcha Institute of Technology, Wollo University, Kombolcha, Ethiopia

  • Sections