Journal of Water Resources and Ocean Science

| Peer-Reviewed |

Monthly Predicted Flow Values of the Sanaga River in Cameroon Using Neural Networks Applied to GLDAS, MERRA and GPCP Data

Received: 23 April 2014    Accepted: 23 May 2014    Published: 30 May 2014
Views:       Downloads:

Share This Article

Abstract

The aim of our study is to predict the discharge rate of the river Sanaga using neural network techniques. Our investigations have taken place in the Sanaga watershed area in Cameroon. The measurement station is situated in the locality of Edea-Song-Mbengue (04°04’15”N, 10°27’50”E) where we have obtained monthly values of the river Sanaga discharge rates that have been measured in situ from January 1989 to December 2004. We have trained neural networks (NN), each with data of parameters such as the surface albedo, the total cloud fraction, the evaporation, the outgoing longwave radiation, the air temperature, the specific humidity, the surface runoff and the precipitation height. The precipitation values have been obtained from GPCP (Global Precipitation Climatology Project) and those of the other parameters from the data assimilation systems GLDAS (Global Land Data Assimilation System) and MERRA (Modern Era-Retrospective analysis for Research and Application). As desired outputs of the NN during the learning process, we have used the measured river runoff values. After introducing temporal delays of 01 and 02 months in the learning-process, we could observe the presence of the memory effect of the parameters used on the temporal evolution of the river discharge rate. After analysis of the performance's criteria of the NN with the help of the calculated Root Means Square Errors (RMSE) and determination coefficients between predicted values and in situ observed ones, we have perceived that the NN which takes into account the two-month delay can predict the river discharge rate with a strong correlation.

DOI 10.11648/j.wros.20140302.12
Published in Journal of Water Resources and Ocean Science (Volume 3, Issue 2, April 2014)
Page(s) 22-29
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), 2024. Published by Science Publishing Group

Keywords

River Runoff, GLDAS, GPCP, MERRA, Neural Network, Sanaga Watershed area

References
[1] Chen, Y., C. “Flood discharge rate measurement of a mountain river - Nanshih River in Taiwan”. Hydrol. Earth Syst. Sci., 2013, 17, 1951–1962.
[2] Negrel, P., Kosuth, P. and Bercher, N. “Esti-mating river discharge from earth observation measurements of river surface hydraulic variables”. Hydrol. Earth Syst. Sci., 2011, 15, 2049–2058.
[3] EOS. “Space-Based Measurement of River Runoff Transactions”, American Geophysical, Union. Eos, Vol. 86, No. 19, 10 May 2005.
[4] Emad, H. Habib and Ehab A. Meselhe. “Stage-discharge for Low-Gradient Tidal Streams Using Data-driven Models”. Journal of Hydraulic Engineering, ASCE/May 2006.
[5] Lillian, Oygarden. “Erosion and surface runoff in small agricultural catchments”. IAHS Publ. 1996, no. 236, Global and Regional Perspectives Centre for Soil and Environmental Research
[6] Watanabe, Fumio, Kobayashi, Yukimitsu, Suzuki, Shinji, Hotta, Tomoki and Ta-kahashi, Satoru. “Estimating the Volume of Surface Runoff from in Situ Measured Soil Sorptivity”. Journal of Arid Land Studies, 2012, 22 (1), 95-98.
[7] Pekarova, P., Pavol, Miklanek and Jan Pekar. “Spatial and temporal runoff oscillation analysis of the main rivers of the world during the 19th – 20th centuries”. Journal of Hydrology, 2003, 274, 62-79.
[8] Bjerkliea David, M., Del-wyn, M., Laurence, C. Smith, Lawrence Dingman. “Estimating discharge rate in rivers using re-motely sensed hydraulic information”. Journal of Hydrology, 2005, 309, 191–209.
[9] Tarpanelli, Angelica, Barbetta, Silvia, Brocca, Luca and Moramarco, Tommaso. “Discharge Estimation by Using Altimetry Data and Simplified Flood Routing Modeling”. Remote Sens., 2013, 5, 4145-4162; doi:10.3390/rs50941 45
[10] Deming J., Chaohua D. and Weison L. “Neural networks approach to high vertical resolution atmospheric temperature profile retrieval from space borne high spectral resolution infrared sounder measurements”. Proc. SPIE 6064, Im-age Processing: Algorithms and Systems, Neural Networks, and Machine Learning, 2006, 60641L; doi:10.1117/12.649743.
[11] Moreau, E., Mallet, C., Thiria, S., Mabbou, B., Badran, F. and Klapisz, C. “Atmospheric Liquid Water Retrieval Using a Gated Experts Neural Network”. Journal of Atmospheric and Oceanic Technology, 2002, 19, 457-467.
[12] Lek, S., Dimopoulos, I., Ghachtoul, Y., El. « Rainfall-runoff modelling using artificial network”. Revue des sciences de l’eau, rev. Sci. Eau, 1996, 3, 319-331.
[13] Tesch, R. and Randeu, W., L. “A neural network model for short term river flow prediction”. Nat. Hazards Earth Syst. Sci., 2006, 6, 629-635.
[14] Laurence, C., Smith and Tamlin, M., Pavelsky. “Estimation of river discharge rate, propagation speed, and hydraulic geometry from space: Lena River, Siberia”. Water Ressources Research, 2006, Vol. 44, doi:10.1029/2007 WR006133.
[15] Shrivastava, G., Karmakar, S., Guhathakurta, P. and Manoj Kumar Kowar, M.K.). “Application of Artificial Neural Networks in Weather Forecasting: A Comprehensive Literature Review”. International Journal of Computer Applications, 2012, 51, (18), 0975-8887.
[16] Del Frate, F. and Giovanni S. “Neural Networks for the retrieval of water vapour and liquid water from radiometric data”. Radio Science, 1998, 33, (5), 1373-1386.
[17] Widrow, B., Lehr, M.A. “30 years of adaptive neural networks: Perceptron, Madaline, and Backpropagation”. Proceedings of the IEEE, 1990, (9), 78.
[18] Kou-Lin Shu, Xiaogang Gao, Sorooshi Sorooshia and Hoshin V. Gupta. “Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks”. Journal of applied meteorology, 1996, 36, 1176-1189.
[19] Huffman, G. J., Bolvin, D. T. “Version 1.2 GPCP One-Degree Daily Precipitation Data Set Documentation. Mesoscale”, Atmospheric Processes Laboratory, NASA Goddard Space Flight Center, 2013.
[20] Rodell, M., Houser, P.R., Jambor, U., Gottschalck, J., Mitchell, K., Meng, C.J., Arsenault, K., Cosgrove, B., Radakovich, J., Bosilovich, M., Entin, J.K., Walker, J.P., Lohmann, D. and Toll, D. “The Global Land Data Assimilation System”. Bulletin of American Meteorological Society, 2004, 381-394, doi: 10.1175/BAMS-85-3-381.
[21] Hongliang, F., Hrubiak, P. L., Hiroko, K., Rodell, M., Teng, W. L. and Vollmer, B.E. “Global Land Data Assimilation System (GLDAS) products from NASA, Hydrology Data and Information Services Center (HDISC)”. ASPRS Annual Conference, Portland Oregon, April 28 - May 2, 2008.
[22] Rui, H., Teng W. L., Vollmer B.E., Mocko, D.M., Beaudoing, H.K. and Rodell, M. “NASA Giovanni Portals for NLDAS/GLDAS Online Visualization, Analysis and Intercomparison”. American Geophysical Union, Fall Meeting, 2011.
[23] Hagan, M., Demuth, H., and Beate, M. “Neural Network design. Boston”: Pws publication, 1996.
[24] Demuth, H., Beate, M., and Hogan, M. “Neural Network toolbox user’s guide”. The Mathworks. Inc., Natrick, USA, 2009.
Author Information
  • Laboratoire d’Ingénierie des Systèmes Industriels et de l'Environnement (LISIE), Institut Universitaire de Technologie Fotso Victor, Université de Dschang, P.O Box 134 Bandjoun, Cameroun; Higher Institute of the Sahel, University of Maroua, P.O. Box 46 Maroua, Cameroon; Laboratory of Mechanics and Modeling of Physical Systems (L2MSP) - University of Dschang, Cameroon

  • Laboratoire d’Ingénierie des Systèmes Industriels et de l'Environnement (LISIE), Institut Universitaire de Technologie Fotso Victor, Université de Dschang, P.O Box 134 Bandjoun, Cameroun

  • Geographic Information Science Center of Excellence, South Dakota State University, Brookling, SD 57007, USA

  • Laboratoire d’Ingénierie des Systèmes Industriels et de l'Environnement (LISIE), Institut Universitaire de Technologie Fotso Victor, Université de Dschang, P.O Box 134 Bandjoun, Cameroun; Laboratory for Environmental Modeling and Atmospheric Physics (LAMEPA) Department of Physics University of Yaounde 1 P.O Box 812 Yaounde, Cameroon

  • Laboratory of Automatic and Applied Informatics (LAIA), IUT-FV, University of Dschang

  • Laboratory of Automatic and Applied Informatics (LAIA), IUT-FV, University of Dschang

Cite This Article
  • APA Style

    SIDDI Tengeleng, NZEUKOU Armand, KAPTUE Armel, TCHAKOUTIO SANDJON Alain, SIMO Théophile, et al. (2014). Monthly Predicted Flow Values of the Sanaga River in Cameroon Using Neural Networks Applied to GLDAS, MERRA and GPCP Data. Journal of Water Resources and Ocean Science, 3(2), 22-29. https://doi.org/10.11648/j.wros.20140302.12

    Copy | Download

    ACS Style

    SIDDI Tengeleng; NZEUKOU Armand; KAPTUE Armel; TCHAKOUTIO SANDJON Alain; SIMO Théophile, et al. Monthly Predicted Flow Values of the Sanaga River in Cameroon Using Neural Networks Applied to GLDAS, MERRA and GPCP Data. J. Water Resour. Ocean Sci. 2014, 3(2), 22-29. doi: 10.11648/j.wros.20140302.12

    Copy | Download

    AMA Style

    SIDDI Tengeleng, NZEUKOU Armand, KAPTUE Armel, TCHAKOUTIO SANDJON Alain, SIMO Théophile, et al. Monthly Predicted Flow Values of the Sanaga River in Cameroon Using Neural Networks Applied to GLDAS, MERRA and GPCP Data. J Water Resour Ocean Sci. 2014;3(2):22-29. doi: 10.11648/j.wros.20140302.12

    Copy | Download

  • @article{10.11648/j.wros.20140302.12,
      author = {SIDDI Tengeleng and NZEUKOU Armand and KAPTUE Armel and TCHAKOUTIO SANDJON Alain and SIMO Théophile and Djiongo Cedrigue},
      title = {Monthly Predicted Flow Values of the Sanaga River in Cameroon Using Neural Networks Applied to GLDAS, MERRA and GPCP Data},
      journal = {Journal of Water Resources and Ocean Science},
      volume = {3},
      number = {2},
      pages = {22-29},
      doi = {10.11648/j.wros.20140302.12},
      url = {https://doi.org/10.11648/j.wros.20140302.12},
      eprint = {https://download.sciencepg.com/pdf/10.11648.j.wros.20140302.12},
      abstract = {The aim of our study is to predict the discharge rate of the river Sanaga using neural network techniques. Our investigations have taken place in the Sanaga watershed area in Cameroon. The measurement station is situated in the locality of Edea-Song-Mbengue (04°04’15”N, 10°27’50”E) where we have obtained monthly values of the river Sanaga discharge rates that have been measured in situ from January 1989 to December 2004. We have trained neural networks (NN), each with data of parameters such as the surface albedo, the total cloud fraction, the evaporation, the outgoing longwave radiation, the air temperature, the specific humidity, the surface runoff and the precipitation height. The precipitation values have been obtained from GPCP (Global Precipitation Climatology Project) and those of the other parameters from the data assimilation systems GLDAS (Global Land Data Assimilation System) and MERRA (Modern Era-Retrospective analysis for Research and Application). As desired outputs of the NN during the learning process, we have used the measured river runoff values. After introducing temporal delays of 01 and 02 months in the learning-process, we could observe the presence of the memory effect of the parameters used on the temporal evolution of the river discharge rate. After analysis of the performance's criteria of the NN with the help of the calculated Root Means Square Errors (RMSE) and determination coefficients between predicted values and in situ observed ones, we have perceived that the NN which takes into account the two-month delay can  predict the river discharge rate with a strong correlation.},
     year = {2014}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Monthly Predicted Flow Values of the Sanaga River in Cameroon Using Neural Networks Applied to GLDAS, MERRA and GPCP Data
    AU  - SIDDI Tengeleng
    AU  - NZEUKOU Armand
    AU  - KAPTUE Armel
    AU  - TCHAKOUTIO SANDJON Alain
    AU  - SIMO Théophile
    AU  - Djiongo Cedrigue
    Y1  - 2014/05/30
    PY  - 2014
    N1  - https://doi.org/10.11648/j.wros.20140302.12
    DO  - 10.11648/j.wros.20140302.12
    T2  - Journal of Water Resources and Ocean Science
    JF  - Journal of Water Resources and Ocean Science
    JO  - Journal of Water Resources and Ocean Science
    SP  - 22
    EP  - 29
    PB  - Science Publishing Group
    SN  - 2328-7993
    UR  - https://doi.org/10.11648/j.wros.20140302.12
    AB  - The aim of our study is to predict the discharge rate of the river Sanaga using neural network techniques. Our investigations have taken place in the Sanaga watershed area in Cameroon. The measurement station is situated in the locality of Edea-Song-Mbengue (04°04’15”N, 10°27’50”E) where we have obtained monthly values of the river Sanaga discharge rates that have been measured in situ from January 1989 to December 2004. We have trained neural networks (NN), each with data of parameters such as the surface albedo, the total cloud fraction, the evaporation, the outgoing longwave radiation, the air temperature, the specific humidity, the surface runoff and the precipitation height. The precipitation values have been obtained from GPCP (Global Precipitation Climatology Project) and those of the other parameters from the data assimilation systems GLDAS (Global Land Data Assimilation System) and MERRA (Modern Era-Retrospective analysis for Research and Application). As desired outputs of the NN during the learning process, we have used the measured river runoff values. After introducing temporal delays of 01 and 02 months in the learning-process, we could observe the presence of the memory effect of the parameters used on the temporal evolution of the river discharge rate. After analysis of the performance's criteria of the NN with the help of the calculated Root Means Square Errors (RMSE) and determination coefficients between predicted values and in situ observed ones, we have perceived that the NN which takes into account the two-month delay can  predict the river discharge rate with a strong correlation.
    VL  - 3
    IS  - 2
    ER  - 

    Copy | Download

  • Sections