Simulation of the recharge process for groundwater using Artificial Neural Networks as an Approximation Method in the Las Sierras Aquifer, Nicaragua
DOI:
https://doi.org/10.5377/rtu.v12i33.15896Keywords:
Hydrogeology, Artificial Neural Networks (ANN), Machine Learning (ML)Abstract
The knowledge of hydrogeologial system functionality, is a vital importance for its management and sustainable development. One of the variables and main input it feeds this system is Recharge (R) product of precipitation (P). The purpose of this study is desing a No Lineal Regresor Model using Artificial Neural Networks (ANN). For the above, with INETER data collected, it was estimate R using input variables for instance: precipitation (P), soil textures and other known environmental variables in Managua Aquifer. With the information collected, data exploration or 'Data mining' was carried out through descriptive statistics, which allows presenting, interpreting and analyzing the data in a comprehensive way. Using the Python programming language (Rossum, 1991) and the JupyterLab work environment, the ANN elements were developed through the Scikit-Learn library or better known as Sklearn (Cournapeau, 2010). After the iterations and settings of hyperparameters, a better fit will be improved using the cost function, which determines the error between the estimated value and the observed value, in order to optimize the parameters of ANN. At the end, the final configurations of ANN are indicated for each soil texture.
Downloads
References
ASCE. (2000). Artificial neural networks in hydrology. J. Hydrol. Eng.
Corea, F. V. (2014). Predicción espacio temporal de la irradiancia solar global a corto plazo en España mediante geoestadistica y redes neuranales artificiales. España.
Cortez, P., Rocha, M., Allegro, F., & Neves, J. (2002). Real-time forecasting by bio-inspired models. In. Proceeding of the Artifical Intelligence and Applications. Málaga, Spain.
Cournapeau, D. (07 de 2010). Scikit - Learn. https://scikit-learn.org/stable/
D. Hunter, J. (2003). Matplotlib. Matplotlib: https://matplotlib.org/
FAO. (2013). https://coin.fao.org/. https://coin.fao.org/: https://coin.fao.org/coin-static/cms/media/5/12820625348650/fao_nic_recursoshidricos_cepal.pdf
Galelli, S., G. B., H., H. R. Maier, A., G. C., D., & M. S., G. (62, 33–51). An evaluation framework for input variable selection algorithms for environmental data-driven models. Environ. Modell. Software, 2014.
Glorot, X., Bordes, A., & Bengio, Y. (01 de 01 de 2010). Deep Sparse Rectifier Neural Networks. Journal of Machine Learning Research.
Hornik, K., M., S., & H., W. (1989). Multilayer feedforward networks are universal approximators. Neural Networks, 2(5), 359–366.
INAA/JICA. (1993). Estudio sobre el Proyecto de Abastecimiento de Agua en Managua. Managua.
INETER. (2004). Mapa de las Provincias Geológicas de Nicaragua. INETER, Managua.
INETER. (2020). Estudio de Potencial de Recarga Hidrica y Deficit de agua Subterránea. Managua: Nicaragua.
INETER. (2020). Informe de Modelo Numerico del Acuifero de las Sierras. Managua: Nicaragua.
INETER. (2021). Atlas Nacional de suelo: Mapa de Textura de suelo. Managa: Nicaragua.
INETER. (13 de 06 de 2022). Atlas Climáticos. Período 1971 - 2010. Instituto Nicaraguense de Estudios Territoriales, Managua. Retrieved 2022, from https://www.ineter.gob.ni/
Kenda K, P., & Klemen, K. (2019). Groundwater Modeling with Machine Learning Techniques. Inst Proc.
Köppen, W. P. (1918). Klassifikation der Klimate nach Temperatur. Hamburg.
Losilla, M., Rodriguez, H., Stimson, J., & Bethune, D. (2001). Los Acuifero Volcánicos y el Desarrollo sostenible en America Central. San José: Editorial Universidad de Costa Rica.
Maier, H., & G. C., D. (2000). Neural networks for the prediction and forecasting of water resources variables: A review of modelling issues and applications. Environ. Modell. Software, 15(1), 101–124.
McKinney, W. (2008). Pandas. https://pandas.pydata.org/
Oliphant, T. (2005). NumPy. NumPy: https://numpy.org/
Pedregosa, F., Varoquaux, G., & Gramfort , A. (2010). Scikit-learn: Machine Learning in Python. JMLR 12, 2011, 2825-2830. Scikit-learn: Machine Learning in Python: https://scikit-learn.org/stable/
Pham, Q., Kumar, M., Di Nunno, F., & Elbeltagi, A. (2022). Groundwater level prediction using machine learning algorithms in a. Springer.
Quilty, J., J. Adamowski, B., & M., R. (2016). Bootstrap rank-ordered conditional mutual information (broCMI): A nonlinear. Water Resour. Res, 52, 2299–2326.
Reed, R., & Marks, R. (1999). Neural smithing supervised learning in feedforward neural networks. Mit Press.
Rossum, G. v. (1991). https://www.python.org/
S. Sahoo, T.A, R., J., E., & I., F. (2017). Machine Learning Algorithms for Modeling Groundwater Level changes in agricultural regions of the US. AGUPUBLICATIONS, 53,3878-3895.
Schosinsky, G., & Losilla, M. (2006). Cálculo de la recarga potencial de acuíferos mediante un balance hídrico de suelos. Revista Geológica de América Central, 34-35, 13-30. .
Shortridge J.E, G. (2019). Machine Leaning methos for empirical streamflow simulation.
Tao, H., Hameed, M., Marhoon, H., Zounemat-Kermani, M., Heddam, S., Kim, S., . . . Saadi, Z. (2022). Groundwater Level Prediction using Machine Learning Models:A Comprehensive Review. ELSEVIER.
Thornthwaite, C. W. (1948). An Approach Toward a Rational Classification of Climate. American Geographical Society.
Wasserman, P. (1989). Neural computing: theory and practice. New York: Van Nostrand Reinhold.
Werbos, P. (1994). The Roots of Backpropagation From Ordered Derivatives to Neural Networks and Political Forecasting. New York, USA: Wiley Intercescience Publication.
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 National Autonomous University of Nicaragua, Managua
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
The authors who publish in this journal agree to the following terms.
- The author or authors of the articles, essays or research grant the National Autonomous University of Nicaragua, Managua (UNAN-Managua) the editing rights (copyright) of the submitted work, therefore the University has the exclusive right to publish the article for the entire copyright period.
- These copyrights/authors authorize Torreón Universitario Magazine and the University to edit and disseminate/publish the article in said Magazine, including printed and electronic reproduction, storage, retrieval and any other type of publication, and sources of secondary information as services. of summaries and databases, they also empower it to protect the article against unauthorized use for dissemination by printed or electronic media (PDF, HTML, EPUB, XML or others).
License for use of content
The magazine uses the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International License.
Under this statement:
This journal is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. It can be copied, distributed and transmitted publicly as long as the author and source are cited (Revista Torreón Universitario), it should not be modified or used for any commercial purpose. The full license can be found at http://creativecommons.org/licenses/by-nc-nd/4.0/.
