Using Machine-Learning Algorithms for Eutrophication Modeling: Case Study of Mar Menor Lagoon (Spain)

[EN] The Mar Menor is a hypersaline coastal lagoon with high environmental value and a characteristic example of a highly anthropized hydro-ecosystem located in the southeast of Spain. An unprecedented eutrophication crisis in 2016 and 2019 with abrupt changes in the quality of its waters caused a great social alarm. Understanding and modeling the level of a eutrophication indicator, such as chlorophyll-a (Chl-a), benefits the management of this complex system. In this study, we investigate the potential machine learning (ML) methods to predict the level of Chl-a. Particularly, Multilayer Neural Networks (MLNNs) and Support Vector Regressions (SVRs) are evaluated using as a target dataset information of up to nine different water quality parameters. The most relevant input combinations were extracted using wrapper feature selection methods which simplified the structure of the model, resulting in a more accurate and efficient procedure. Although the performance in the validation phase showed that SVR models obtained better results than MLNNs, experimental results indicated that both ML algorithms provide satisfactory results in the prediction of Chl-a concentration, reaching up to 0.7 R-CV(2) (cross-validated coefficient of determination) for the best-fit models.This research was partially funded by the Fundacion Seneca del Centro de Coordinacion de la Investigacion de la Region de Murcia under Project 20813/PI/18, and by Spanish Ministry of Science, Innovation and Universities under grants RTI2018-096384-B-I00 and RTC-2017-6389-5.Jimeno-Sáez, P.; Senent-Aparicio, J.; Cecilia-Canales, JM.; Pérez-Sánchez, J. (2020). Using Machine-Learning Algorithms for Eutrophication Modeling: Case Study of Mar Menor Lagoon (Spain). International Journal of Environmental research and Public Health (Online). 17(4):1-14. https://doi.org/10.3390/ijerph17041189114174Pérez-Ruzafa, A., Pérez-Ruzafa, I. M., Newton, A., & Marcos, C. (2019). Coastal Lagoons: Environmental Variability, Ecosystem Complexity, and Goods and Services Uniformity. Coasts and Estuaries, 253-276. doi:10.1016/b978-0-12-814003-1.00015-0Kennish, M. J. (2015). Coastal Lagoons. Encyclopedia of Earth Sciences Series, 140-143. doi:10.1007/978-94-017-8801-4_47García-Ayllón, S. (2019). New Strategies to Improve Co-Management in Enclosed Coastal Seas and Wetlands Subjected to Complex Environments: Socio-Economic Analysis Applied to an International Recovery Success Case Study after an Environmental Crisis. Sustainability, 11(4), 1039. doi:10.3390/su11041039Le Moal, M., Gascuel-Odoux, C., Ménesguen, A., Souchon, Y., Étrillard, C., Levain, A., … Pinay, G. (2019). Eutrophication: A new wine in an old bottle? Science of The Total Environment, 651, 1-11. doi:10.1016/j.scitotenv.2018.09.139Alcolea, A., Contreras, S., Hunink, J. E., García-Aróstegui, J. L., & Jiménez-Martínez, J. (2019). Hydrogeological modelling for the watershed management of the Mar Menor coastal lagoon (Spain). Science of The Total Environment, 663, 901-914. doi:10.1016/j.scitotenv.2019.01.375Nixon, S. W. (1995). Coastal marine eutrophication: A definition, social causes, and future concerns. Ophelia, 41(1), 199-219. doi:10.1080/00785236.1995.10422044Huang, J., Gao, J., & Zhang, Y. (2015). Combination of artificial neural network and clustering techniques for predicting phytoplankton biomass of Lake Poyang, China. Limnology, 16(3), 179-191. doi:10.1007/s10201-015-0454-7Canfield, D. E. (1983). PREDICTION OF CHLOROPHYLL A CONCENTRATIONS IN FLORIDA LAKES: THE IMPORTANCE OF PHOSPHORUS AND NITROGEN. Journal of the American Water Resources Association, 19(2), 255-262. doi:10.1111/j.1752-1688.1983.tb05323.xPhillips, G., Pietiläinen, O.-P., Carvalho, L., Solimini, A., Lyche Solheim, A., & Cardoso, A. C. (2008). Chlorophyll–nutrient relationships of different lake types using a large European dataset. Aquatic Ecology, 42(2), 213-226. doi:10.1007/s10452-008-9180-0EL PAÍS https://elpais.com/elpais/2019/10/22/inenglish/1571743580_215496.htmlGarcía-Ayllón, S. (2017). Integrated management in coastal lagoons of highly complexity environments: Resilience comparative analysis for three case-studies. Ocean & Coastal Management, 143, 16-25. doi:10.1016/j.ocecoaman.2016.10.007Garcia-Ayllon, S. (2018). The Integrated Territorial Investment (ITI) of the Mar Menor as a model for the future in the comprehensive management of enclosed coastal seas. Ocean & Coastal Management, 166, 82-97. doi:10.1016/j.ocecoaman.2018.05.004Pérez-Ruzafa, A., Campillo, S., Fernández-Palacios, J. M., García-Lacunza, A., García-Oliva, M., Ibañez, H., … Marcos, C. (2019). Long-Term Dynamic in Nutrients, Chlorophyll a, and Water Quality Parameters in a Coastal Lagoon During a Process of Eutrophication for Decades, a Sudden Break and a Relatively Rapid Recovery. Frontiers in Marine Science, 6. doi:10.3389/fmars.2019.00026Iglesias, C., Martínez Torres, J., García Nieto, P. J., Alonso Fernández, J. R., Díaz Muñiz, C., Piñeiro, J. I., & Taboada, J. (2013). Turbidity Prediction in a River Basin by Using Artificial Neural Networks: A Case Study in Northern Spain. Water Resources Management, 28(2), 319-331. doi:10.1007/s11269-013-0487-9Najah, A., El-Shafie, A., Karim, O. A., & El-Shafie, A. H. (2012). Application of artificial neural networks for water quality prediction. Neural Computing and Applications, 22(S1), 187-201. doi:10.1007/s00521-012-0940-3Li, X., Cheng, Z., Yu, Q., Bai, Y., & Li, C. (2017). Water-Quality Prediction Using Multimodal Support Vector Regression: Case Study of Jialing River, China. Journal of Environmental Engineering, 143(10), 04017070. doi:10.1061/(asce)ee.1943-7870.0001272Su, J., Wang, X., Zhao, S., Chen, B., Li, C., & Yang, Z. (2015). A Structurally Simplified Hybrid Model of Genetic Algorithm and Support Vector Machine for Prediction of Chlorophyll a in Reservoirs. Water, 7(12), 1610-1627. doi:10.3390/w7041610Abba, S. I., Hadi, S. J., & Abdullahi, J. (2017). River water modelling prediction using multi-linear regression, artificial neural network, and adaptive neuro-fuzzy inference system techniques. Procedia Computer Science, 120, 75-82. doi:10.1016/j.procs.2017.11.212Juntunen, P., Liukkonen, M., Pelo, M., Lehtola, M. J., & Hiltunen, Y. (2012). Modelling of Water Quality: An Application to a Water Treatment Process. Applied Computational Intelligence and Soft Computing, 2012, 1-9. doi:10.1155/2012/846321Li, X., Sha, J., & Wang, Z. (2016). A comparative study of multiple linear regression, artificial neural network and support vector machine for the prediction of dissolved oxygen. Hydrology Research, 48(5), 1214-1225. doi:10.2166/nh.2016.149Charulatha, G., Srinivasalu, S., Uma Maheswari, O., Venugopal, T., & Giridharan, L. (2017). Evaluation of ground water quality contaminants using linear regression and artificial neural network models. Arabian Journal of Geosciences, 10(6). doi:10.1007/s12517-017-2867-6Keller, S., Maier, P., Riese, F., Norra, S., Holbach, A., Börsig, N., … Hinz, S. (2018). Hyperspectral Data and Machine Learning for Estimating CDOM, Chlorophyll a, Diatoms, Green Algae and Turbidity. International Journal of Environmental Research and Public Health, 15(9), 1881. doi:10.3390/ijerph15091881Li, X., Sha, J., & Wang, Z.-L. (2017). Chlorophyll-A Prediction of Lakes with Different Water Quality Patterns in China Based on Hybrid Neural Networks. Water, 9(7), 524. doi:10.3390/w9070524Yi, H.-S., Park, S., An, K.-G., & Kwak, K.-C. (2018). Algal Bloom Prediction Using Extreme Learning Machine Models at Artificial Weirs in the Nakdong River, Korea. International Journal of Environmental Research and Public Health, 15(10), 2078. doi:10.3390/ijerph15102078Nazeer, M., Bilal, M., Alsahli, M., Shahzad, M., & Waqas, A. (2017). Evaluation of Empirical and Machine Learning Algorithms for Estimation of Coastal Water Quality Parameters. ISPRS International Journal of Geo-Information, 6(11), 360. doi:10.3390/ijgi6110360Erena, Domínguez, Aguado, Soria, & García-Galiano. (2019). Monitoring Coastal Lagoon Water Quality Through Remote Sensing: The Mar Menor as a Case Study. Water, 11(7), 1468. doi:10.3390/w11071468García-Oliva, M., Marcos, C., Umgiesser, G., McKiver, W., Ghezzo, M., De Pascalis, F., & Pérez-Ruzafa, A. (2019). Modelling the impact of dredging inlets on the salinity and temperature regimes in coastal lagoons. Ocean & Coastal Management, 180, 104913. doi:10.1016/j.ocecoaman.2019.104913López-Ballesteros, A., Senent-Aparicio, J., Srinivasan, R., & Pérez-Sánchez, J. (2019). Assessing the Impact of Best Management Practices in a Highly Anthropogenic and Ungauged Watershed Using the SWAT Model: A Case Study in the El Beal Watershed (Southeast Spain). Agronomy, 9(10), 576. doi:10.3390/agronomy9100576Senent-Aparicio, J., Pérez-Sánchez, J., García-Aróstegui, J., Bielsa-Artero, A., & Domingo-Pinillos, J. (2015). Evaluating Groundwater Management Sustainability under Limited Data Availability in Semiarid Zones. Water, 7(12), 4305-4322. doi:10.3390/w7084305Navarro, M. C., Pérez-Sirvent, C., Martínez-Sánchez, M. J., Vidal, J., Tovar, P. J., & Bech, J. (2008). Abandoned mine sites as a source of contamination by heavy metals: A case study in a semi-arid zone. Journal of Geochemical Exploration, 96(2-3), 183-193. doi:10.1016/j.gexplo.2007.04.011Conesa, H. M., & Jiménez-Cárceles, F. J. (2007). The Mar Menor lagoon (SE Spain): A singular natural ecosystem threatened by human activities. Marine Pollution Bulletin, 54(7), 839-849. doi:10.1016/j.marpolbul.2007.05.007Domingo-Pinillos, J., Senent-Aparicio, J., García-Aróstegui, J., & Baudron, P. (2018). Long Term Hydrodynamic Effects in a Semi-Arid Mediterranean Multilayer Aquifer: Campo de Cartagena in South-Eastern Spain. Water, 10(10), 1320. doi:10.3390/w10101320Stefanova, A., Hesse, C., & Krysanova, V. (2015). Combined Impacts of Medium Term Socio-Economic Changes and Climate Change on Water Resources in a Managed Mediterranean Catchment. Water, 7(12), 1538-1567. doi:10.3390/w7041538Velasco, J., Lloret, J., Millan, A., Marin, A., Barahona, J., Abellan, P., & Sanchez-Fernandez, D. (2006). Nutrient And Particulate Inputs Into The Mar Menor Lagoon (Se Spain) From An Intensive Agricultural Watershed. Water, Air, and Soil Pollution, 176(1-4), 37-56. doi:10.1007/s11270-006-2859-8García-Oliva, M., Pérez-Ruzafa, Á., Umgiesser, G., McKiver, W., Ghezzo, M., De Pascalis, F., & Marcos, C. (2018). Assessing the Hydrodynamic Response of the Mar Menor Lagoon to Dredging Inlets Interventions through Numerical Modelling. Water, 10(7), 959. doi:10.3390/w10070959Wei, B., Sugiura, N., & Maekawa, T. (2001). Use of artificial neural network in the prediction of algal blooms. Water Research, 35(8), 2022-2028. doi:10.1016/s0043-1354(00)00464-4(2000). Artificial Neural Networks in Hydrology. I: Preliminary Concepts. Journal of Hydrologic Engineering, 5(2), 115-123. doi:10.1061/(asce)1084-0699(2000)5:2(115)Jimeno-Sáez, P., Senent-Aparicio, J., Pérez-Sánchez, J., & Pulido-Velazquez, D. (2018). A Comparison of SWAT and ANN Models for Daily Runoff Simulation in Different Climatic Zones of Peninsular Spain. Water, 10(2), 192. doi:10.3390/w10020192Nguyen, V. D., Tan, R. R., Brondial, Y., & Fuchino, T. (2007). Prediction of vapor–liquid equilibrium data for ternary systems using artificial neural networks. Fluid Phase Equilibria, 254(1-2), 188-197. doi:10.1016/j.fluid.2007.03.014Bekkari, N., & Zeddouri, A. (2019). Using artificial neural network for predicting and controlling the effluent chemical oxygen demand in wastewater treatment plant. Management of Environmental Quality: An International Journal, 30(3), 593-608. doi:10.1108/meq-04-2018-0084Zhang, Y., Gao, X., Smith, K., Inial, G., Liu, S., Conil, L. B., & Pan, B. (2019). Integrating water quality and operation into prediction of water production in drinking water treatment plants by genetic algorithm enhanced artificial neural network. Water Research, 164, 114888. doi:10.1016/j.watres.2019.114888Naghibi, S. A., Ahmadi, K., & Daneshi, A. (2017). Application of Support Vector Machine, Random Forest, and Genetic Algorithm Optimized Random Forest Models in Groundwater Potential Mapping. Water Resources Management, 31(9), 2761-2775. doi:10.1007/s11269-017-1660-3Kuhn, M. (2008). Building Predictive Models inRUsing thecaretPackage. Journal of Statistical Software, 28(5). doi:10.18637/jss.v028.i05Caret: Classification and Regression Training, R Package Version 6.0-84 https://CRAN.R-project.org/package=caretMaier, H. R., Jain, A., Dandy, G. C., & Sudheer, K. P. (2010). Methods used for the development of neural networks for the prediction of water resource variables in river systems: Current status and future directions. Environmental Modelling & Software, 25(8), 891-909. doi:10.1016/j.envsoft.2010.02.003Kumar, S., & Bucher, P. (2016). Predicting transcription factor site occupancy using DNA sequence intrinsic and cell-type specific chromatin features. BMC Bioinformatics, 17(S1). doi:10.1186/s12859-015-0846-zMjalli, F. S., Al-Asheh, S., & Alfadala, H. E. (2007). Use of artificial neural network black-box modeling for the prediction of wastewater treatment plants performance. Journal of Environmental Management, 83(3), 329-338. doi:10.1016/j.jenvman.2006.03.004Palani, S., Liong, S.-Y., & Tkalich, P. (2008). An ANN application for water quality forecasting. Marine Pollution Bulletin, 56(9), 1586-1597. doi:10.1016/j.marpolbul.2008.05.021Kuo, J.-T., Hsieh, M.-H., Lung, W.-S., & She, N. (2007). Using artificial neural network for reservoir eutrophication prediction. Ecological Modelling, 200(1-2), 171-177. doi:10.1016/j.ecolmodel.2006.06.018Jimeno-Sáez, P., Senent-Aparicio, J., Pérez-Sánchez, J., Pulido-Velazquez, D., & Cecilia, J. (2017). Estimation of Instantaneous Peak Flow Using Machine-Learning Models and Empirical Formula in Peninsular Spain. Water, 9(5), 347. doi:10.3390/w905034