Abstract
An Artificial Neural Network (ANN), a Machine Learning (ML) modeling approach is proposed to predict the ecological state of the North Lagoon of Tunis, a shallow restored Mediterranean coastal ecosystem. A Nonlinear Auto Regressive with exogenous input (NARX) neural network model was fitted to predict Chlorophyll-a (Chl-a) concentrations in the North Lagoon of Tunis as an eutrophication indicator. The modeling is based on approximately three decades of monitoring water quality data (from January 1989 to April 2018) to train, validate and test the NARX model. The most relevant predictor variables used in this model were those having a high permutation importance ranking with Random Forest (RF) model, which simplified the structure of the network, resulting in a more accurate and efficient procedure. Those predictor variables are secchi depth, and dissolved oxygen. Various model scenarios with different NARX architectures were tested for Chl-a prediction. To verify the model performances, the trained models were applied to field monitoring data. Results indicated that the developed NARX model can predict Chl-a concentrations in the North Lagoon of Tunis with high accuracy (R = 0.79; MSE = 0.31). In addition, results showed that the NARX model generally performed better than multivariate linear regression (MVLR). This approach could provide a quick assessment of Chl-a variations for lagoon management and eco-restoration.
Similar content being viewed by others
Data Availability
The data provided by the Al-Buhaira Invest company to the first author are acknowledged.
Code Availability
Neural Net Time Series Toolbox and Regression Learner Toolbox applications were used in the MATLAB® software (version 9.3.0.948333 (R2017b), The Mathworks, MA, USA).
References
Abba SI, Hadi SJ, 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. https://doi.org/10.1016/j.procs.2017.11.212
APHA (1999) Standard methods for the examination of water and wastewater. American Public Health Association, Washington DC
Aqil M, Kita I, Yano A, Nishiyama S (2007) A comparative study of artificial neural networks and neuro-fuzzy in continuous modeling of the daily and hourly behavior of runoff. Journal of Hydrology 337:22–34. https://doi.org/10.1016/j.jhydrol.2007.01.013
Armi Z, Trabelsi E, Turki S, Ben Maïz N, Mahmoudi E (2012) Composition and dynamics of potentially toxic dinoflagellates in a shallow Mediterranean lagoon. Oceanological and Hydrobiological Studies 41(3):25–35
ASCE Task Committee (2000) Artificial neural networks in hydrology I. Preliminary concepts. Journal of Hydrology and Engineering 5:115–123. https://doi.org/10.1061/(asce)1084-0699(2000)5:2(115)
Babovic V, Sannasiraj SA, Soon Chan E (2005) Error correction of a predictive ocean wave model using local model approximation. Journal of Marine Systems 53:1–17. https://doi.org/10.1016/j.jmarsys.2004.05.028
Barnes RSK (1980) Coastal lagoons: The natural history of a neglected habitat. Cambridge University Press, Cambridge
Basset A, Elliott M, West RJ, Wilson JG, Estuarine (2013) Estuarine and lagoon biodiversity and their natural goods and services. Estuarine, Coastal and Shelf Science 132:1–4. https://doi.org/10.1016/j.ecss.2013.05.018
Béjaoui B, Armi Z, Ottaviani., Barelli E, Gargouri-Ellouz E, Chérif R, Turki S, Solidoro C, Aleya L (2016) Random forest model and TRIX used in combination to assess and diagnose the trophic status of Bizerte Lagoon, southern Mediterranean. Ecological Indicators 7:293–301. https://doi.org/10.1016/j.ecolind.2016.07.010
Béjaoui B, Ottaviani E, Barelli E, Ziadi B, Dhib A, Lavoie M, Gianluca C, Turki S, Solidoro C, Aleya L (2018) Machine learning predictions of trophic status indicators and plankton dynamic in coastal lagoons. Ecological Indicators 95:765–774. https://doi.org/10.1016/j.ecolind.2018.08.041
Ben Charrada R (1992) Le lac de Tunis après les aménagements. Paramètres physicochimiques de l’eau et relation avec la croissance des macroalgues. Marine Life 1:29–44
Bowden GJ, Nixon JB, Dandy GC, Maier HR, Holmes M (2006) Forecasting chlorine residuals in a water distribution system using a general regression neural network. Mathematical and Computer Modelling 44:469–484. https://doi.org/10.1016/j.mcm.2006.01.006
Breiman L (2001) Random forests. Machine Learning 45:5–32. https://doi.org/10.1023/A:1010933404324
Charulatha G, Srinivasalu S, Uma Maheswari O et al (2017) Evaluation of ground water quality contaminants using linear regression and artificial neural network models. Arabian Journal of Geosciences 10:128. https://doi.org/10.1007/s12517-017-2867-6
Chen Q, Guan T, Yun L, Li R, Recknagel F (2015) Online forecasting chlorophyll a concentrations by an auto-regressive integrated moving average model: Feasibilities and potentials. Harmful Algae 43:58–65. https://doi.org/10.1016/j.hal.2015.01.002
Cloern JE (2001) Our evolving conceptual model of the coastal eutrophication problem. Marine Ecology Progress Series 210:223–253. https://doi.org/10.3354/meps210223
Cutler DR, Edwards TC, Beard KH, Cutler A, Hess KT, Gibson J, Lawler JJ (2007) Random forests for classification in ecology. Ecology 88:2783–2792. https://doi.org/10.1890/07-0539.1
Daliakopoulos IN, Coulibaly P, Tsanis IK (2005) Groundwater level forecasting using artificial neural networks. Journal of Hydrology 309:229–240. https://doi.org/10.1016/j.jhydrol.2004.12.001
De Casabianca ML, Samson-Kechacha FL, Bone C (1991) Etude spatiotemporelle des sels nutritifs et des principales variables hydrobiologiques dans une lagune méditerranéenne: le lac Mellah (Algérie). Mesogée 51:15–23
de Jonge VN, Elliott M, Orive E (2002) Causes, historical development, effects and future challenges of a common environmental problem: eutrophication. Hydrobiologia (incorporating JAQU) 475/476:1–19. https://doi.org/10.1023/A:1020366418295
Derolez V, Soudant D, Malet N, Chiantella C, Richard M, Abadie E, Aliaume C, Bec B (2020) Two decades of oligotrophication: Evidence for a phytoplankton community shift in the coastal lagoon of Thau (Mediterranean Sea, France). Estuarine, Coastal and Shelf Science 241:106 810. https://doi.org/10.1016/j.ecss.2020.106810
Dhib A, Denis M, Barani A, Turki S, Aleya L (2016) Ultra- and microplankton assemblages as indicators of trophic status in a Mediterranean lagoon. Ecological Indicator 64:59–71
Fogelman S, Zhao H, Blumenstein M, Zhang S (2006) Estimation of oxygen demand levels using UV-Vis spectroscopy and artificial neural networks as an effective tool for real-time, wastewater treatment control. In: Proceedings of the 1st Australian Young Water Professionals Conference, Sydney, Australia
Frolov S, Rayan JP, Chavez FP (2012) Predicting eutrophic-depth-integrated chlorophyll-a from discrete-depth and satellite-observable chlorophyll-a off central California. Journal of Geophysical Research 117:C05042. https://doi.org/10.1029/2011JC007322
García-Ayllón S (2017) Diagnosis of complex coastal ecological systems: Environmental GIS analysis of a highly stressed Mediterranean lagoon through spatiotemporal indicators. Ecological Indicators 83:451–462. https://doi.org/10.1016/j.ecolind.2017.08.015
Harbridge W, Pilkey OH, Whaling P, Swetland P (1976) Sedimentation in the lake of Tunis: a lagoon strongly influenced by man. Environmental Geology 1:215–225. https://doi.org/10.1007/bf02407508
Haykin S (1999) Neural networks: a comprehensive foundation, 2nd edn. Prentice Hall International Editions Series, London
He Z, Wen X, Liu H, Du J (2014) A comparative study of artificial neural network, adaptive neuro fuzzy inference system and support vector machine for forecasting river flow in the semiarid mountain region. Journal of Hydrology 509:379–386. https://doi.org/10.1016/j.jhydrol.2013.11.054
Huang J, Gao J, Zhang Y (2015) Combination of artificial neural network and clustering techniques for predicting phytoplankton biomass of lake Poyang, China. Limnology 16:179–191. https://doi.org/10.1007/s10201-015-0454-7
IOC SCOR, IAPSO (2010) The international thermodynamic equation of seawater – 2010: Calculation and use of thermodynamic properties. Intergovernmental Oceanographic Commission, Manuals and Guides No. 56, UNESCO (English), 196 pp
Jimeno-Sáez P, Senent-Aparicio J, Pérez-Sánchez J, Pulido-Velazquez DA (2018) Comparison of SWAT and ANN Models for daily runoff simulation in different climatic zones of Peninsular Spain. Water 10:192
Jimeno-Sáez P, Senent-Aparicio JM, Cecilia J, 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 17:1189. https://doi.org/10.3390/ijerph17041189
Kalaji HM, Sytar O, Brestic M, Samborska IA, Cetner MD, Carpentier C (2016) Risk assessment of urban lake water quality based on in situ cyanobacterial and total chlorophyll-a monitoring. Polish Journal of Environmental Studies 25(2):655–661. https://doi.org/10.15244/pjoes/60895
Keller S, Maier PM, Riese FM, Norra S, Holbach A, Börsig N, Wilhelms A, Moldaenke C, Zaake A, 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 15:1881
Kohavi R, John GH (1997) Wrappers for feature subset selection. Artificial Intelligence 97(1–2):273–324
Kuo JT, Hsieh MH, Lung WS, She N (2007) Using artificial neural network for reservoir eutrophication prediction. Ecological Modelling 200:171–177
Lee JHW, Huang Y, Dickmen M, Jayawardena AW (2003) Neural network modelling of coastal algal blooms. Ecological Modelling 159:179–201. https://doi.org/10.1016/S0304-3800(02)00281-8
Li X, Sha J, Wang ZL (2017) Chlorophyll-A Prediction of lakes with different water quality patterns in China based on hybrid neural networks. Water 9:524
Lin T, Horne BG, Tino P, Giles CL (1996) Learning long-term dependencies in NARX recurrent neural networks. IEEE Transactions on Neural Networks 7(6):1329–1338. https://doi.org/10.1109/72.548162
Lorenzen CJ (1967) Determination of chlorophyll and pheopigments by spectrophotometric equations. Limnology and Oceanography 12:34–346
Lu F, Chen Z, Liu W, Shao H (2016) Modeling chlorophyll-a concentrations using an artificial neural network for precisely eco-restoring lake basin. Ecological Engineering 95:422–429. https://doi.org/10.1016/j.ecoleng.2016.06.072
Maier HR, Jain A, Dandy GC, Sudheer K (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 and Software 25:891–909. https://doi.org/10.1016/j.envsoft.2010.02.003
Mc Quaid N, Zamyadi A, Prevost M, Bird DF, Dorner S (2011) Use of in vivo phycocyanin fluorescence to monitor potential microcystin-producing cyanobacterial biovolume in a drinking water source. Journal of Environmental Monitoring 13:455–463. https://doi.org/10.1039/c0em00163e
Mdaini Z, El Gafsi M, Tremblay J, Pharand P, Gagné JP (2019) Spatio-temporal variability of biomarker responses and lipid composition of Marphysasanguinea, Montagu (1813) in the anthropic impacted lagoon of Tunis. Marine Pollution Bulletin 144:275–286. https://doi.org/10.1016/j.marpolbul.2019.04.065
Menendez M, Martınez M, Comın FA (2001) A comparative study of the effect of pH and inorganic carbon resources on the photosynthesis of three floating macroalgae species of a Mediterranean coastal lagoon. Journal of Experimental Marine Biology and Ecology 256:123–136
Mitchell MW (2011) Bias of the random forest Out-of-Bag (OOB) error for certain input parameters. Open Journal of Statistics 1:205–211. https://doi.org/10.4236/ojs.2011.13024
Mjalli FS, Al-Asheh S, Alfadala HE (2006) Use of artificial neural network black-box modeling for the prediction of wastewater treatment plants performance. Journal of Environmental Management 83:329–338. https://doi.org/10.1016/j.jenvman.2006.03.004
Mooney H, Larigauderie A, Cesario M, Elmquist T, Hoegh-Guldberg O, Lavorel S, Mace GM, Palmer M, Scholes R, Yahara T (2009) Biodiversity, climate change, and ecosystem services. Current Opinion in Environment Sustainability 1:46–54. https://doi.org/10.1016/J.COSUST.2009.07.006
Motoda H, Liu H (2002) Feature selection, extraction and construction. Towards the foundation of data mining workshop. In: Proceedings of the Sixth Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD’02), Taipei, Taiwan; pp 67–72
Mulia IE, Tay H, Roopsekhar K, Tkalich P (2013) Hybrid ANN–GA model for predicting turbidity and chlorophyll a concentrations. Journal of Hydro-Environmental Research 7:279–299. https://doi.org/10.1016/j.jher.2013.04.003
Nayak PC, Sudheer KP, Rangan DM, Ramasastri KS (2005) Short-term flood forecasting with a neuro fuzzy model. Water Resources Research 41:2517–2530. https://doi.org/10.1029/2004WR003562
Nazeer M, Wong MS, Nichol JE (2017) A new approach for the estimation of phytoplankton cell counts associated with algal blooms. Science of the Total Environment 590–591:125–183. https://doi.org/10.1016/j.scitotenv.2017.02.182
Newton A, Icely J, Cristina S et al (2014) An overview of ecological status, vulnerability and future perspectives of European large shallow, semi-enclosed coastal systems, lagoons and transitional waters. Estuarine, Coastal and Shelf Science 140:95–122. https://doi.org/10.1016/J.ECSS.2013.05.023
Newton A, Brito AC, Icely JD et al (2018) Assessing, quantifying and valuing the ecosystem services of coastal lagoons. Journal for Nature Conservation 44:50–56. https://doi.org/10.1016/j.jnc.2018.02.009
Nguyen VD, Tan RR, Brondial Y, Fuchino T (2007) Prediction of vapor-liquid equilibrium data for ternary systems using artificial neural networks. Fluid Phase Equilibria 254:188–197
Palani S, Liong SY, Tkalich P (2008) An ANN application for water quality forecasting. Marine Pollution Bulletin 56:1586–1597
Park Y, Cho KH, Park J, Cha SM, Kim JH (2015) Development of early-warning protocol for predicting chlorophyll-a concentration using machine learning models in freshwater and estuarine reservoirs, Korea. Science of the Total Environment 502:31–41. https://doi.org/10.1016/j.scitotenv.2014.09.005
Parsons TR, Maita Y, Lalli CM (1984) A manual of chemical and biological methods for seawater analysis. Pergamon Press, Oxford Oxfordshire
Phillips G, Pietiläinen O, Carvalho L et al (2008) Chlorophyll–nutrient relationships of different lake types using a large European dataset. Aquatic Ecology 42:213–226. https://doi.org/10.1007/s10452-008-9180-0
Rajaee T, Ebrahim H, Nourani F (2019) A review of the artificial intelligence methods in groundwater level modeling. Journal of Hydrology 572:336–351. https://doi.org/10.1016/j.jhydrol.2018.12.037
Rezgui A, Maiz N, Moussa M (2008) Fonctionnement hydrodynamique et écologique du Lac Nord de Tunis par modélisation numérique. Revue des Sciences de l’Eau 21:349–361. https://doi.org/10.7202/018781ar
Robledano F, Esteve MA, Martínez-Fernández J, Farinós P (2011) Determinants of wintering waterbird changes in a Mediterranean coastal lagoon affected by eutrophication. Ecological Indicators 11:395–406. https://doi.org/10.1016/j.ecolind.2010.06.010
Samarasinghe S (2007) Neural networks for applied sciences and engineering. Auerbach Publications, New York
Schramm W (1999) Factors influencing seaweed responses to eutrophication: some results from EU-project EUMAC. Journal of Applied Phycology 11:69–78
Shili A (1995) Contribution à l’étude de Ruppia dans le Lac Nord de Tunis. Mémoire de Diplôme des Etudes Approfondies en biologie marine et océanographie, Faculté des Sciences de Tunis, p 1-128
Souchu P, Bec B, Smith VH, Laugier T, Fiandrino A, Benau L, Orsoni V, Collos Y, Vaquer A (2010) Patterns in nutrient limitation and chlorophyll-a along an anthropogenic eutrophication gradient in French Mediterranean coastal lagoons. Canadian Journal of Fisheries and Aquatic Sciences 67:743–753. https://doi.org/10.1139/F10-018
Strickland JDH, Parsons TR (1972) A Practical Handbook of Seawater Analysis. Fisheries Research Board of Canada, Ottawa, Bulletin 167. 1968
Su 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(4):1610–1627. https://doi.org/10.3390/w7041610
Tian W, Liao Z, Zhang J (2017) An optimization of artificial neural network model for predicting chlorophyll dynamics. Ecological Modelling 364:42–52. https://doi.org/10.1016/j.ecolmodel.2017.09.013
Trabelsi-Bahri EL, Armi Z, Trabelsi-Annabi N, Shili A, Ben Maiz N (2013) Water quality variables as indicators in the restoration impact assessment of the north lagoon of Tunis, South Mediterranean. Journal of Sea Research 79:12–19. https://doi.org/10.1016/j.seares.2013.01.003
Van Berk H, Oostinga H (1992) North Lake of Tunis and its shores: restoration and development. Terra et Aqua 49:23–32
Viaroli P, Bartoli M, Giordani G, Naldi M (2008) Community shifts, alternative stable states, biogeochemical controls and feedbacks in eutrophic coastal lagoons: a brief overview. Aquat Conserv Mar Freshw Ecosyst 18:105–117. https://doi.org/10.1002/aqc
Wallace J, Champagne P, Hall G (2016) Time series relationships between chlorophyll-a, dissolved oxygen, and pH in three facultative wastewater stabilization ponds. Environmental Science: Water Research & Technology 2:1032–1040. https://doi.org/10.1039/C6EW00202A
Watzin MC, Miller EB, Shambaugh AD, Kreider MA (2006) Application of the WHO alert level framework to cyanobacterial monitoring of Lake Champlain, Vermont. Environmental Toxicology 21:278–288. https://doi.org/10.1002/tox.20181
Wei B, Sugiura N, Maekawa T (2001) Use of artificial neural network in the prediction of algal blooms. Water Research 35:2022–2028
Were K, Bui DT, Dick ØB, Singh BR (2015) A comparative assessment of support vector regression, artificial neural networks, and random forests for predicting and mapping soil organic carbon stocks across an Afromontane landscape. Ecological Indicators 52:394–403. https://doi.org/10.1016/j.ecolind.2014.12.028
Xu G, Schwarz P, Yang H (2019) Determining China’s CO2 emissions peak with a dynamic nonlinear artificial neural network approach and scenario analysis. Energy Policy 128:752–762. https://doi.org/10.1016/j.enpol.2019.01.058
Zaldívar JM, Cardoso AC, Viaroli P, Wit RD, Ibañez C, Reizopoulou S, Razinkovas A, Basset A, Holmer M, Murray N (2008) Eutrophication in transitional waters: an overview. Transitional Waters Monographs 1:1–78. https://doi.org/10.1285/i18252273v2n1p1
Zang C, Huang S, Wu M et al (2010) Comparison of relationships between ph, dissolved oxygen and chlorophyll a for aquaculture and non-aquaculture waters. Water, Air, and Soil Pollution 219:157–174. https://doi.org/10.1007/s11270-010-0695-3
Zhang WZ, Wang H, Chai F, Qiu G (2016) Physical drivers of chlorophyll variability in the open South China Sea. Journal of Geophysical Research Oceans 121:7123–7140. https://doi.org/10.1002/2016JC011983
Acknowledgements
We thank Al-Buhaira Invest company for providing the first author with the data.
Funding
No funding has been provided. However, the field work and laboratory analyses were a part of an institutional activity (Al-Buhaira Invest company).
Author information
Authors and Affiliations
Contributions
NBH wrote the paper, collected data, conceived, designed and performed the analysis. CG helped in the correction of the paper and contributed in the designing of the analysis. HC helped in conceiving and the designing of the analysis and was a major contributor in writing the manuscript. NBM provided a big sequence of the monthly field investigation data. VG contributed in implementing and working with the software. AS helped in the supervision of this work and was a major contributor in writing the manuscript. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflicts of Interest/ Competing Interests
No conflict of interest associated with this publication.
Consent to Participate
Not applicable.
Consent for Publication
Not applicable.
Ethical Approval
Not applicable.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This article belongs to the Topical Collection: Wetlands in the Developing World.
Rights and permissions
About this article
Cite this article
Hadid, N.B., Goyet, C., Chaar, H. et al. Machine Learning Modeling Techniques for Forecasting the Trophic Level in a Restored South Mediterranean Lagoon Using Chlorophyll-a. Wetlands 41, 111 (2021). https://doi.org/10.1007/s13157-021-01479-6
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s13157-021-01479-6