Abstracts
Résumé
Ce travail décrit une nouvelle approche de la prédiction de l'évolution spatio-temporelle du phosphore minéral dans les eaux de surface, particulièrement dans la baie lagunaire de Tiagba. L'originalité de cette étude réside dans l'utilisation des réseaux de neurones artificiels, précisément du perceptron multicouche, comme outil de modélisation. Deux approches de l'évolution spatio-temporelle de ce nutriment dans cette baie ont été étudiées : sa modélisation statique et sa modélisation dynamique. Ainsi, il a été utilisé deux bases de 3 966 et 4 627 données respectivement pour sa modélisation statique et sa modélisation dynamique. L'algorithme de Levenberg-Marquardt a été utilisé pour la détermination des poids de connexions lors du développement du perceptron multicouche. Il ressort, des résultats obtenus, que les modèles 5-14-1 et 6-14-2 permettent de prédire à 70,30 % et à environ 70 % respectivement les évolutions statique et dynamique du phosphore minéral dans cette baie lagunaire. Ces modèles, jugés satisfaisant peuvent servir de socle pour d'éventuelles études visant à la réhabilitation et la gestion de cet écosystème aquatique dans le cadre de son développement durable.
Mots-clés :
- Phosphore,
- réseau de neurones artificiels,
- baie lagunaire de Tiagba,
- système Ébrié,
- Côte d'Ivoire
Abstract
This work describes a new approach to prediction of spatio-temporal evolution of mineral phosphorus in water bodies, particularly in Tiagba Lagoon Bay. Originality of this study lie on the use of artificial neural networks, principally multilayer perceptron, as modelling tool. Two approaches of spatio-temporal evolution of this nutrient were done: static evolution and dynamic evolutions. Data bases, formed by 3 966 and 4 627 data, served for static and dynamic modelling of this nutrient respectively. Weights of network connection are determined using Levenberg-Marquardt algorithm during execution of Multilayer Perceptron. Results obtained show that models 5-14-1 and 6-14-2 can predict to 70.30% and approximately 70% respectively for static and dynamic evolution of mineral phosphorus in this bay. These models, judged satisfactory, could be used for other studies led to rehabilitation and protection of this aquatic ecosystem for its long development.
Keywords:
- Phosphorus,
- artificial neural networks,
- multilayer perceptron,
- Tiagba Lagoon Bay,
- Ebrié system,
- Côte d'Ivoire
Appendices
Références bibliographiques
- AICHOURI I., A. HANI, N. BOUGHERIRA, L. DJABRI, H. CHAFFAI et S. LALLAHEM (2015). River flow model using artificial neural networks. Energy Procedia, 74, 1007-1014.10.1016/j.egypro.2015.07.832 Google Scholar Search this bibliographic reference on Google Scholar
- ABEL J.M., D. ÖZKUNDACI et D.P. HAMILTON (2010). Nitrogen and phosphorus limitation of phytoplankton growth in New Zealand lakes: Implications for eutrophication control. Ecosyst., 13 (7), 966-977.10.1007/s10021-010-9367-9 Google Scholar Search this bibliographic reference on Google Scholar
- BASHEER I.A. et M. HAJMEER (2000). Artificial neural networks: Fundamentals, computing, design, and application. J. Microbiol. Methods, 43, 3-31.10.1016/S0167-7012(00)00201-3 Google Scholar Search this bibliographic reference on Google Scholar
- BEHRENDT H., P. HUBER, M. KORMMILCH, D. OPITZ, O. SCHMOLL, G. SCHOLZ et R. UEBE (2000). Nutrient emissions into river basins of Germany. Environmental Research of the Federal Ministry of the Environment, Nature Conservation and Nuclear Safety, Institute of Freshwater Ecology and Inland Fisheries, Texte 23/00, Research Report 296 25 515, UBA-FB 99-087/e, Berlin, Allemagne, 13 p.Google Scholar Search this bibliographic reference on Google Scholar
- CABRITA M.T., A. SILVA., P.B. OLIVEIRA, M.M. ANGÉLICO et M. NOGUEIRA (2015). Assessing eutrophication in the Portuguese Continental Exclusive Economic Zone within the European Marine Strategy Framework Directive. Ecol. Indic., 58, 286-299.10.1016/j.ecolind.2015.05.044 Google Scholar Search this bibliographic reference on Google Scholar
- CAO X., Y. WANG, J. HE, X. LUO et Z. ZHENG (2016). Phosphorus mobility among sediments, water and cyanobacteria enhanced by cyanobacteria blooms in eutrophic Lake Dianchi. Environ. Pollut., 219, 580-587.10.1016/j.envpol.2016.06.017 Google Scholar Search this bibliographic reference on Google Scholar
- CHANG N.B., G. MOHIUDDIN, A.J. CRAWFORD, K. BAI et K.R. JIN (2015). Diagnosis of the artificial intelligence-based predictions of flow regime in a constructed wetland for stormwater pollution control. Ecol. Inform., 28, 42-60.10.1016/j.ecoinf.2015.05.001 Google Scholar Search this bibliographic reference on Google Scholar
- COBLE A.A., A.M. MARCARELLI et E.S. KANE (2015). Ammonium and glucose amendments stimulate dissolved organic matter mineralization in a Lake Superior tributary. J. Great Lakes Res., 41 (3), 801-807.10.1016/j.jglr.2015.05.015 Google Scholar Search this bibliographic reference on Google Scholar
- CARMOUZE J.P. et J.P. CAUMETTE (1985). Les effets de la pollution organique sur les biomasses et activités du phytoplancton et des bactéries hétérotrophes dans la lagune Ébrié (Côte d’Ivoire). Rev. Hydrobiol. Trop., 18 (3), 183-211.Google Scholar Search this bibliographic reference on Google Scholar
- DUCHESNE S., B. TOUMBOU et J.P. VILLENEUVE (2016). Validation and comparison of different statistical models for the prediction of water main pipe breaks in a municipal network in Québec, Canada. Rev. Sci. Eau, 29 (1), 1-89.
10.7202/1035713ar Google Scholar Search this bibliographic reference on Google Scholar
- FONTAINE T.A., T.S. CRUICKSHANK, J.G. ARNOLD et R.H. HOTHCHKISS (2002). Development of a snowfall/snowmelt routine for mountainous terrain for the soil water assessment tool (SWAT). J. Hydrol., 262, 209-223.10.1016/S0022-1694(02)00029-X Google Scholar Search this bibliographic reference on Google Scholar
- FOTIOU T., T.M. TRIANTIS, T. KALOUDIS et A. HISKIA (2015). Evaluation of the photocatalytic activity of TiO2 based catalysts for the degradation and mineralization of cyanobacterial toxins and water off-odor compounds under UV-A, solar and visible light. Chem. Eng. J., 261, 17-26.10.1016/j.cej.2014.03.095 Google Scholar Search this bibliographic reference on Google Scholar
- FREIHOEFER A. et P. McGINLEY (2009). Phosphorus loading model for Lake Eau Claire and Lake Altoona. Center for Watershed Science and Education, University of Wisconsin - Stevens Point, Wisconsin, États-Unis, 99 p.Google Scholar Search this bibliographic reference on Google Scholar
- GUSE B., A. BRONSTERT, M. RODE, B. TETZLAFF et F. WENDLAND (2007). Application of two phosphorus models with different complexities in a mesoscale river catchment. Adv. Geosci., 11, 77-84.10.5194/adgeo-11-77-2007 Google Scholar Search this bibliographic reference on Google Scholar
- GOODY D.C., D.J. LAPWORTH, S.A. BENNETT, T.H.E. HEATON, P.J. WILLIAMS et B.W.J. SURRIDGE (2016). A multi-stable isotope framework to understand eutrophication in aquatic ecosystems. Water Res., 88, 623-633. 10.1016/j.watres.2015.10.046 Google Scholar Search this bibliographic reference on Google Scholar
- HUANG J. et J. GAO (2017). An ensemble simulation approach for artificial neural network: An example from chlorophyll a simulation in Lake Poyang, China. Ecol. Inform., 37, 52-58.10.1016/j.ecoinf.2016.11.012 Google Scholar Search this bibliographic reference on Google Scholar
- HUO S., Z. HE, J. SU, B. XI et C. ZHU (2013). Using artificial neural network models for eutrophication prediction. Procedia Environ. Sci., 18, 310-316.10.1016/j.proenv.2013.04.040 Google Scholar Search this bibliographic reference on Google Scholar
- KASPERSEN B.S., T.B. CHRISTENSEN, A.M. FREDENSLUND, H.B. MøLLER, M.B. BUTTS, N.H. JENSEN et T. KJAER (2016). Linking climate change mitigation and coastal eutrophication management through biogas technology: Evidence from a new Danish bioenergy concept. Sci. Total. Environ., 541, 124-131.10.1016/j.scitotenv.2015.10.015 Google Scholar Search this bibliographic reference on Google Scholar
- LEVENBERG K. (1944). A method for the solution of certain problems in least squares. Quart. Appl. Math., 2, 164-168. 10.1090/qam/10666 Google Scholar Search this bibliographic reference on Google Scholar
- LIU C., S. SHAO, Q. SHEN, C. FAN, L. ZHANG et Q. ZHOU (2016a). Effects of riverine suspended particulate matter on the post-dredging increase in internal phosphorus loading across the sediment-water interface. Environ. Pollut., 211, 165-172.10.1016/j.envpol.2015.12.045 Google Scholar Search this bibliographic reference on Google Scholar
- LIU C., J. ZHONG, J. WANG, L. ZHANG et C. FAN (2016b). Fifteen-year study of environmental dredging effect on variation of nitrogen and phosphorus exchange across the sediment-water interface of an urban lake. Environ. Pollut., 219, 639-648.10.1016/j.envpol.2016.06.040 Google Scholar Search this bibliographic reference on Google Scholar
- MA Z., X. SONG, R. WAN, L. GAO et D. JIANG (2014). Artificial neural network modeling of the water quality in intensive Litopenaeus vannamei shrimp tanks. Aquaculture, 433, 307-312.10.1016/j.aquaculture.2014.06.029 Google Scholar Search this bibliographic reference on Google Scholar
- MANDAL S., S.S. MAHAPATRA et R.K. PATEL (2015). Enhanced removal of Cr (VI) by cerium oxide polyaniline composite: Optimization and modeling approach using response surface methodology and artificial neural networks. J. Environ. Chem. Eng., 3 (2), 870-885. 10.1016/j.jece.2015.03.028 Google Scholar Search this bibliographic reference on Google Scholar
- MANSSOURI T., H. SAHBI, I. MANSSOURI et B. BOUDAD (2015). Utilisation d’un modèle hybride basé sur la RLMS et les RNA-PMC pour la prédiction des paramètres indicateurs de la qualité des eaux souterraines, cas de la nappe de Souss-Massa-Maroc. Eur. Sci. J., 11, 35-46.Google Scholar Search this bibliographic reference on Google Scholar
- MARQUARDT D. (1963). An algorithm for least-squares estimation of nonlinear parameters. J. Soc. Indust. Appl. Math., 11, 431-441.10.1137/0111030 Google Scholar Search this bibliographic reference on Google Scholar
- MELLANDER P.E., P. JORDAN, M. SHORE, N.T. McDONALD, D.P. WALL, G. SHORTLE et K. DALY (2016). Identifying contrasting influences and surface water signals for specific groundwater phosphorus vulnerability. Sci. Total. Environ., 541, 292-302.10.1016/j.scitotenv.2015.09.082 Google Scholar Search this bibliographic reference on Google Scholar
- MULLER A.C. et D.L. MULLER (2015). Forecasting future estuarine hypoxia using a wavelet based neural network model. Ocean Modell., 96 (2), 314-323.10.1016/j.ocemod.2015.11.003 Google Scholar Search this bibliographic reference on Google Scholar
- NOUMI M. (2004). Painlevé equations through symetry. Translations of Mathematical Monographs. Vol. 223, American Mathematical Society (AMS), États-Unis, 156 p.10.1090/mmono/223 Google Scholar Search this bibliographic reference on Google Scholar
- PINEDO S., R. ARÉVALO et E. BALLESTEROS (2015). Seasonal dynamic of upper sublittoral assemblages on Mediterranean rocky shores along a eutrophication gradient. Estuar. Coast. Shelf Sci., 161, 93-101.10.1016/j.ecss.2015.05.004 Google Scholar Search this bibliographic reference on Google Scholar
- PIZARRO J., P.M. VERGARA, S. CERDA et D. BRIONES (2016). Cooling and eutrophication of southern Chilean lakes. Sci. Total. Environ., 541, 683-691.10.1016/j.scitotenv.2015.09.105 Google Scholar Search this bibliographic reference on Google Scholar
- ROBSON J.B. (2014). State of the art in modelling of phosphorus aquatic systems: Review, criticisms and commentary. Environ. Model. Softw., 61, 339-359.10.1016/j.envsoft.2014.01.012 Google Scholar Search this bibliographic reference on Google Scholar
- ROLLAND D.C., J. HAURY, P. MARMONIER et Y. LAGADEUC (2015). Effect of macrophytes on flow conditions and deposition of suspended particles in small streams: An experimental study using artificial vegetation. Rev. Sci. Eau, 28 (3), 231-245.
10.7202/1034012ar Google Scholar Search this bibliographic reference on Google Scholar
- SANTHI C., J.G. ARNOLD, J.R. WILLIAMS, W.A. DUGAS, R. SRINIVASAN et L.M. HAUCK (2001). Validation of the SWAT model on a large river basin with point and nonpoint sources. J. Am. Water Resour. Assoc., 37 (5), 1169-1188.10.1111/j.1752-1688.2001.tb03630.x Google Scholar Search this bibliographic reference on Google Scholar
- SHOULIANG H., H. ZHUOSHI, S. JING, X. BEIDOU et Z. CHAOWEI (2013). Using artificial neural network models for eutrophication prediction. Procedia Environ. Sci., 18, 310-316.10.1016/j.proenv.2013.04.040 Google Scholar Search this bibliographic reference on Google Scholar
- SONG Y., Y. DENG et C. JUNG (2016). Mitigation and degradation of natural organic matters (NOMs) during ferrate(VI) application for drinking water treatment. Chemosphere, 146, 145-153.10.1016/j.chemosphere.2015.12.001 Google Scholar Search this bibliographic reference on Google Scholar
- SUNOHARA M.D., N. GOTTSCHALL, E. CRAIOVAN, G. WILKES, E. TOPP, S.K. FREY et D.R. LAPEN (2016). Controlling tile drainage during the growing season in Eastern Canada to reduce nitrogen, phosphorus, and bacteria loading to surface water. Agric. Water Manag., 178, 159-170.10.1016/j.agwat.2016.08.030 Google Scholar Search this bibliographic reference on Google Scholar
- SUTELA T., T. VEHANEN et M. RASK (2016). A littoral fish index that responds to eutrophication in boreal lakes. Fisheries Res., 173 (1), 88-92.10.1016/j.fishres.2015.06.006 Google Scholar Search this bibliographic reference on Google Scholar
- TETZLAFF B. (2006). Die Phosphatbelastung großer Flusseinzugsgebiete aus diffusen und punktuellen Quellen. Schriften des Forschungszentrums Juelich, Reihe Umwelt/Environment, Juliers, Allemagne, Vol. 65, 287 p.Google Scholar Search this bibliographic reference on Google Scholar
- ULRICH A.E., D.F. MALLEY et P.D. WATTS (2016). Lake Winnipeg basin: Advocacy, challenges and progress for sustainable phosphorus and eutrophication control. Sci. Total. Environ., 542 (B), 1030-1039.Google Scholar Search this bibliographic reference on Google Scholar
- WANG L. et T. LIANG (2016). Distribution patterns and dynamics of phosphorus forms in the overlying water and sediment of Dongting Lake. J. Great Lakes Res., 42 (3), 565-570.10.1016/j.jglr.2016.03.013 Google Scholar Search this bibliographic reference on Google Scholar
- WANG Y.P., R.M. LAW et B. PARK (2010). A global model of carbon, nitrogen and phosphorus cycles for the terrestrial biosphere. Biogeosciences, 7, 2261-2282.10.5194/bg-7-2261-2010 Google Scholar Search this bibliographic reference on Google Scholar
- XU Y., C. MA, Q. LIU, B. XI, G. QIAN, D. ZHANG et S. HUO (2015). Method to predict key factors affecting lake eutrophication - A new approach based on Support Vector Regression model. Int. Biodeterior. Biodegradation, 102, 308-315. 10.1016/j.ibiod.2015.02.013 Google Scholar Search this bibliographic reference on Google Scholar
- YAO M.K. (2011). Évaluation et modélisation de l’eutrophisation dans une baie lagunaire tropicale apparentée lacustre : cas de la baie lagunaire de Tiagba (Côte d’Ivoire). Thèse de doctorat, Univ. Félix Houphouët-Boigny, Côte d’Ivoire, 242 p.Google Scholar Search this bibliographic reference on Google Scholar
- YAO M.K., K.L. AKPETOU, Y.S. BROU, D.C AKMEL, A. TROKOUREY et K.B. YAO (2016a). Eutrophication modeling by new approach in tropical lagoon bay: Case of Tiagba Lagoon Bay (Ebrie Systeme, Côte d’Ivoire). Aust. J. Basic Appl. Sci., 10 (13), 37-44.Google Scholar Search this bibliographic reference on Google Scholar
- YAO Y., P. WANG, C. WANG, J. HOU, L. MIAO, Y. YUAN, T. WANG et C. LI (2016b). Assessment of mobilization of labile phosphorus and iron across sediment-water interface in a shallow lake (Hongze) based on in situ high-resolution measurement. Environ. Pollut., 219, 873-882.10.1016/j.envpol.2016.08.054 Google Scholar Search this bibliographic reference on Google Scholar
- ZUO J., J. SONG, H. YUAN, X. LI, N. LI et L. DUAN (2016). Particulate nitrogen and phosphorus in the East China Sea and its adjacent Kuroshio waters and evaluation of budgets for the East China Sea Shelf. Cont. Shelf Res., 131, 1-11.10.1016/j.csr.2016.11.003 Google Scholar Search this bibliographic reference on Google Scholar
- ZHANG G.P. (2003). Time series forecasting using a hybrid ARIMA and neural networkmodel. Neurocomputing, 50, 159-175.10.1016/S0925-2312(01)00702-0 Google Scholar Search this bibliographic reference on Google Scholar
