American Journal of Water Resources
ISSN (Print): 2333-4797 ISSN (Online): 2333-4819 Website: http://www.sciepub.com/journal/ajwr Editor-in-chief: Apply for this position
Open Access
Journal Browser
Go
American Journal of Water Resources. 2021, 9(2), 63-79
DOI: 10.12691/ajwr-9-2-4
Open AccessReview Article

Using Artificial Neural Network to Model Water Discharge and Chemistry in a River Impacted by Acid Mine Drainage

Toluwaleke Ajayi1, , Dina L.Lopez1 and Abiodun E.Ayo-Bali2

1Department of Geological Science, Ohio University, Athens, USA

2Department of Geology and Environmental Science, University of Pittsburgh, USA

Pub. Date: October 11, 2021

Cite this paper:
Toluwaleke Ajayi, Dina L.Lopez and Abiodun E.Ayo-Bali. Using Artificial Neural Network to Model Water Discharge and Chemistry in a River Impacted by Acid Mine Drainage. American Journal of Water Resources. 2021; 9(2):63-79. doi: 10.12691/ajwr-9-2-4

Abstract

In southeast Ohio, Raccoon Creek Watershed (RC) has an extensive mining history resulting in acid mine drainage (AMD) and subsequent environmental problems. Modeling of the discharge and chemistry of AMD impacted Hewett Fork, a tributary of Raccoon Creek, is the focus of this paper. Discharge measurements are collected by the United States Geological Survey (USGS) gage station at the Bolin Mills (BM) station on the main stem of RC. This data for the period 2011-2019 has been analyzed to develop a prediction model for BM discharge and subsequently use the model to predict flow and water chemistry in Hewett Fork (HF). The Neural Network Model using group method of data handling (GMDH) and generalized regression neural network (GRNN) shows a variation of prediction models for BM due to parameters such as decay factor in API and ATI, as well as in the evapotranspiration input variables of the model. However, the study reveals that the GRNN model for BM is the most suitable for BM prediction based on its performance, with an r-value greater than 0.90, and its ease in predicting discharge by specifying a data set to be added to the data set for training and calibrating the network. The result of the water chemistry model using GMDH, with r values greater than 0.80 for each model, shows the input variables have a good capacity to predict chemical concentration/load in the HF stream. This study shows that Artificial Neural Network (ANN) modeling can help to model successfully and predict flow and chemical evolution of rivers in Ohio and other parts of the world.

Keywords:
watershed modeling artificial neural network discharge prediction hydrology

Creative CommonsThis work is licensed under a Creative Commons Attribution 4.0 International License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/

References:

[1]  Pool, J. R., Kruse, N. A., and Vis, M. L., 2013, Assessment of mine drainage remediated streams using diatom assemblages and biofilm enzyme activities: Hydrobiology, p. 1-16.
 
[2]  Herrera, S., Uchiyama, H., Igarashi, T., Asakura, K., Ochi, Y., Iyatomi, N., Asakura, K., and Kawada, S., 2007. Acid mine drainage treatment through a two-step neutralization ferrite-formation process in northern Japan: Physical and chemical characterization of the sludge: Minerals of Engineering, v. 20, p. 1309-1314.
 
[3]  Lopez, D. L., and Stoertz, M. W., 2001, Chemical and physical controls on waters discharged from abandoned underground coal mines: G Geochemistry: Exploration Environment Analysis, v. 1, p. 51-60.
 
[4]  McCament, B., 2007. Watershed Action Plan: Raccoon Creek Headwaters to above Hewett Fork: Ohio Department of Natural Resources, Internal Report.
 
[5]  Bisht, D.C. Raju, M. M. Joshi M. C. 2010. ANN Based River Stage – Discharge Modelling for Godavari River, India. Computer Modelling and New Technologies. 14(3): 48-62.
 
[6]  Sarkar A, R. Kumar, R. D. Singh, G. Thakur, and S. K. Jain, 2004. “Sediment-discharge modeling in a river using artificial neural Advances in Artificial Intelligence networks,” in Proceedings of the International Conference ICON—HERP, IIT Roorkee, India.
 
[7]  Fernando D. A. K and A. W. Jayawardena, 1998. “Runoff forecasting using RBF networks with OLS algorithm,” Journal of Hydrologic Engineering, ASCE, vol. 3, no. 3, pp. 203-209.
 
[8]  Raghuwanshi, R. Singh, and L. S. Reddy 2006, “Runo ff and sediment yield modeling using artificial neural networks: Upper Siwane River, India,” Journal of Hydrologic Engineering, ASCE, vol. 11, no. 1, pp. 71-79, 2006.
 
[9]  Schaap, M. G., Leij, F. J., Van Genuchenten, M.T., 1998. Neural Network Analysis for Hierarchical Prediction of Soil Hydraulics Properties. Soil Science Society of America Journal 62, 845-855.
 
[10]  Maier, H.R., and Dandy, G.C., 2000, Neural networks for the prediction and forecasting of water resources variables: a review of modelling issues and applications. Environmental Modelling and Software 15, 101-124.
 
[11]  Liong, S.Y., Lim, W.H., Paudyal, G.N., 2000. River stage forecasting in Bangladesh: neural network approach. Journal of Computing in Civil Engineering 14, 1-8.
 
[12]  Cigizoglu, H. K. 2003. Incorporation of ARMA models into flow forecasting by artificial neural networks. Environmetrics 14(4).
 
[13]  Golob, R., Stokelj, T., Grgic, D., 1998. Neural-network-based water inflow forecasting. Control Engineering Practice 6, 593-600.
 
[14]  Rajurkar, M. P., Kothyari, U. C. & Chaube, U. C. 2002. Artificial neural networks for daily rainfall–runoff modelling. Hydrol. Sci. J. 47(6), 865-877.
 
[15]  Kang, K. W., Kim, J. H., Park, C. Y., and Ham, K. J. 1993. ‘‘Evaluation of hydrological forecasting system based on neural network model.’’ Proc., 25th Congress of Int. Assoc. for Hydr. Res., International Association for Hydraulic Research, Delft, The Netherlands 257-264.
 
[16]  Karunanithi, N., Grenney, W. J., Whitley, D., and Bovee, K. 1994. “Neural networks for river flow prediction.” J. Comp. in Civ. Engrg., ASCE, 8(2), 201-220.
 
[17]  Haykin, S. 1994. Neural networks: a comprehensive foundation. MacMillan, New York.
 
[18]  Aiyelokun Oluwatobi, Ogunsanwo Gbenga, Adelere Joy and Agbede Oluwole, 2018. Modeling And Simulation of River Discharge Using Artificial Neural Networks. Ife Journal of Science vol. 20, no. 2 (2018).
 
[19]  Raju. M. Mohan, R. K. Srivastava, Dinesh C. S. Bisht, H. C. Sharma, and Anil Kumar 2011: Development of Artificial Neural-Network-Based Models for the Simulation of Spring Discharge. Hindawi Publishing Corporation Advances in Artificial Intelligence Volume 2011, Article ID 686258, 11 pages.
 
[20]  Alaa M. Al-Abadi 2014. Modeling of stage–discharge relationship for Gharraf River, southern Iraq using backpropagation artificial neural networks, M5 decision trees, and Takagi–Sugeno inference system technique: a comparative study. Appl Water Sci 6:407-420.
 
[21]  Gopalsamy, K., 2004, Stability of artificial neural networks with impulses. Applied Mathematics and Computation, v. 154, p. 783-813.
 
[22]  Khan M.Y.A , F. Hasan, S. Panwar & G.J. Chakrapani. (2016). Neural network model for discharge and water-level prediction for Ramganga River catchment of Ganga Basin, India, Hydrological Sciences Journal, 61:11, 2084-2095.
 
[23]  Nayef Al-Mutairi and Al-Rukaibi F 2012: Neural Network Models for Traffic Noise Quality Prediction: A Comparative Study Journal of Civil & Environmental Engineering 2: 1.
 
[24]  Word System Group, Inc., Mass., USA 2008: NeuroShell 2 Help (wardsystems.com).
 
[25]  Khaled Assaleh, Tamer Shanableh, Yasmin Abu Kheil 2012. Group Method of Data Handling for Modeling Magnetorheological Dampers. Intelligent Control and Automation, 4, 70-79.
 
[26]  Shaikh Abdul Hannan, R. R. Manza, R. J. Ramteke, 2010. Generalized Regression Neural Network and Radial Basis Function for Heart Disease Diagnosis International Journal of Computer Applications (0975-8887) Volume 7– No.13.
 
[27]  Theodosiou, M. 2011. Disaggregation & aggregation of time series components: A hybrid forecasting approach using generalized regression neural networks and the theta method. Neurocomputing, 74(6), 896-905.
 
[28]  Wu, L., Long, T-y, Liu, X., et al., 2012. Impacts of climate and land-use changes on the migration of non-point source nitrogen and phosphorus during rainfall-runoff in the Jialing River Watershed, China. J. Hydrol. 475, 26-41.
 
[29]  Post, D. A., A. J. Jakeman, I. G. Littlewood, P. G. Whitehead, and M. D. A. Jayasuriya, 1996. Modeling land-cover-induced variations in hydrologic response: Picaninny Creek, Victoria. Ecol. Modell., 86, 177-182.
 
[30]  Hovenga, P.A., Wang, D., Medeiros, S.C., et al., 2016. The response of runoff and sediment loading in the Apalachicola River, Florida to climate and land use land cover change. Earth’s Future 4, 124-142.
 
[31]  Jackson A. Geography as notes; Rivers; discharge and hydrographs; 2013. Available: https://geographyas.info/rivers/discharge-andhydrographs/Discharge&Hydrographs.
 
[32]  Pfister, L., Kwadijk, J., Musy, A., et al., 2004. Climate change, land use change and runoff prediction in the Rhine-Meuse basins. River Res. Appl. 20, 229-241.
 
[33]  Liu Z, Yao Z, Huang H, Wu S, Liu G 2014. Land use and climate changes and their impacts on runoff in the Yarlung Zangbo river basin, China. Land Degradation and Development.; 25(3).
 
[34]  Hänggi P, Weingartner R. Inner-annual variability of runoff and climate within the upper Rhine River basin, 1808-2007. In: Hydrological Sciences Journal. 2011; 56(1): 34-50.
 
[35]  Dewalle, David R. Swistock, Bryan R. 1995: Final Report: Regional streamflow sensitivity to climate change in an urbanizing environment. EPA Grant, Pennsylvania State University.
 
[36]  Beschta, R.L. 1990. Peak-flow estimation using an antecedent precipitation index (API) model in tropical environments. Pages 128-137 in R.R. Ziemer, C.L. O’loughlin, and L.S. Hamilton, editors. Research needs and applications to reduce sedimentation and erosion in tropical steeplands. International Association of Hydrologic Sciences. Publication 192. Washington, D.C.
 
[37]  Reid, L.M. and J. Lewis. 2007. Rates and implications of rainfall interception in acoastal redwood forest. Pages 107-117 in R.B. Standiford, G.A. Giusti, Y.Valachovic, W.J. Zielinski, and M.J. Furniss, editors. Proceedings of the redwoodregion forest science symposium: What does the future hold? United States Department of Agriculture, Forest Service, Pacific Southwest Research Station,General Technical Report 194. Albany, California.
 
[38]  Cammalleri, C., Agnesse, C., Ciraolo, G., Minacapilli, M., Provenzano, G., Rallo, G., 2010. Actual evapotranspiration assessment by means of a coupled energy/hydrologic balance model: validation over an olive grove by means of scintillometry and measurements of soil water conents. J. Hydrol. 392 (1-2), 70-82.
 
[39]  Chen, Y.M., Xue, Y.J ., Hu, Y.M., 2018. How multiple factors control evapotranspiration in North America evergreen needleleaf forests. Sci. Total Environ. 622, 1217-1224.
 
[40]  Vinukollu, R.K., Wood, E.F., Ferguson, C.R., Fisher, J.B., 2011. Global estimates of evapotranspiration for climate studies using multi-sensor remote sensing data: evaluation of three process- based approaches. Rem.Sens. Environ. 115(3), 801-823.
 
[41]  Kruse, N.A., De Rose, L., Korenowsky, R., Bowman, J.R.., Lopez, D., Johnson, K., and Rankin, E., 2013. The role of remediation, natural alkalinity sources and physical stream parameters in stream recovery: Environmental Management, v. 128, p. 1000-1013.
 
[42]  Voinovich School of Leadership and Public Affairs. 2015a. Raccoon Creek Partnership. Ohio University. Athens, Ohio. Retrieved from http://watersheddata.com/.
 
[43]  Hansen M., 1995. The Teays River. Geofacts No. 10 Ohio Department of Natural Resources- Division of Geological Survey, Columbus, Ohio. 2 p.
 
[44]  De Rose, L.M., 2011. Physical and Chemical Controls on Natural and Anthropogenic Remediation of Two Streams Impacted by Acid Mine Drainage in the Raccoon Creek Watershed, Ohio. [Master’s Thesis]: Ohio University, 178 p.
 
[45]  Kruse, N.A., Bowman, J.R., Mackey, A.L., McCament, B., Johnson, K.S., 2012. The lasting impacts of offline periods in lime dosed streams: A case study in Raccoon Creek, Ohio: Mine Water Environment, v.31, p. 266-272.
 
[46]  Sturgeon, M.T. and Associates, 1958. The geological and mineral resources of Athens County, Ohio: Ohio Geological Survey, Bulletin 57: Columbus, Ohio.
 
[47]  Slucher, R., Swinford, M., Larsen, E., Schumacher, A., Shrake, L., Rice, L., Caudill, R., and Rea, G., 2006. Bedrock Geologic Map of Ohio BG-1 Version 6. Ohio Department of Natural Resources Division of Geological Survey, Columbus, Ohio.
 
[48]  Wilson, K.S., 1988. Chemical Quality, Benthic Organisms, and Sedimentation in Stream Draining Coal-mined Lands in Raccoon Creek Basin [Master’s Thesis]: Ohio University, 80 p.
 
[49]  Aurelian, F., Georgescu, D., Pordea, I., Iuhas T., 2004. Encapsulation technologies and systems for radioactive waste dumps: Advances in Mineral Resources Management and Environmental Geotechnology, v.1, p. 419-424.
 
[50]  Bicknell, B.R., Imhoff, J.C., Kittle Jr., J.L., Jobes, T.H., and Donigan Jr., A.S., 2005, HSPF Version 12.2 User’s Manual: AQUA TERRA Consultants, 683 p.
 
[51]  Blaney, H. F., and Criddle, W. D.: 1950. Determining Water Requirements in Irrigated Area from Climatological Irrigation Data, US Department of Agriculture, Soil Conservation Service, Tech.Pap. No. 96, 48 pp.
 
[52]  Singh, V. P.: 1989. Hydrologic Systems, Vol. II, Watershed Modelling, Prentice-Hall, Inc.
 
[53]  Hargreaves, G. H.: 1975. ‘Moisture Availability and Crop Production’, TRANSACTION of the ASAE. 18, 980-984.
 
[54]  McKay Daniel 2017, Modelling of the Raccoon Creek Watershed, Ohio. [Master’s Thesis]: Ohio University.
 
[55]  Hill, P. I., Graszkiewicz, Z., Taylor, M. and Nathan, R. J. 2014. Loss models for catchment simulation. State 4 Analysis of rural catchments. May 2014. ARR Revision project 6
 
[56]  Lindsay, R. K., Kohler, M. A. and Paulhus, J. L. H. 1975. Hydrology for Engineers (2nd ed.). McGraw-Hill.
 
[57]  Xu, C.-Y. and Singh, V. P. 2002.‘Evaluation and Generalization of Radiation-based Methods for calculating Evaporation’, Hydrolog. Processes. 15, 305-319.
 
[58]  United States Department of Agriculture Natural Resources Conservation Service (USDA), 1957: Determining consumptive use and irrigation water requirement. Technical Bulletin No. 1275.