Sains Malaysiana 41(8)(2012): 939–947

 

 

Supervised and Unsupervised Artificial Neural Networks for Analysis of

Diatom Abundance in Tropical Putrajaya Lake, Malaysia

(Rangkaian Neural Buatan Diselia dan Tanpa Penyeliaan untuk Analisis Kelimpahan

Diatom di Tasik Tropika Putrajaya, Malaysia)

 

M. Sorayya & S. Aishah

Institute of Biological Sciences (ISB), University of Malaya, 50603 Kuala Lumpur, Malaysia

 

B. Mohd. Sapiyan*

Faculty of Science Computer and Information Technology, University of Malaya,

50603 Kuala Lumpur, Malaysia

 

Received: 29 June 2011 / Accepted: 31 January 2012

 

ABSTRACT

Five years of data from 2001 until 2006 of warm unstratified shallow, oligotrophic to mesothropic tropical Putrajaya Lake, Malaysia were used to study pattern discovery and forecasting of the diatom abundance using supervised and unsupervised artificial neural networks. Recurrent artificial neural network (RANN) was used for the supervised artificial neural network and Kohonen Self Organizing Feature Maps (SOM) was used for unsupervised artificial neural network. RANN was applied for forecasting of diatom abundance. The RANN performance was measured in terms of root mean square error (RMSE) and the value reported was 29.12 cell/mL. Classification and clustering by SOM and sensitivity analysis from the RANN were used to reveal the relationship among water temperature, pH, nitrate nitrogen (NO3-N) concentration, chemical oxygen demand (COD) concentration and diatom abundance. The results indicated that the combination of supervised and unsupervised artificial neural network is important not only for forecasting algae abundance but also in reasoning and understanding ecological relationships. This in return will assist in better management of lake water quality.

 

Keywords:  Diatom; forecasting; recurrent artificial neural network; self organizing maps

 

ABSTRAK

Data selama lima tahun dari 2001 hingga 2006 bagi tasik tropika yang cetek dan panas, berstatus oligotrof ke mesotropi iaitu Tasik Putrajaya, Malaysia telah digunakan untuk mengkaji penemuan corak dan ramalan kuantiti diatom menggunakan rangkaian neural buatan yang diselia dan tidak diselia. Rangkaian neural buatan berulang (RANN) telah digunakan untuk rangkaian neural buatan diselia dan peta atur sendiri Kohonen (SOM) telah digunakan untuk rangkaian neural buatan tanpa pengawasan.RANN telah digunakan untuk ramalan kuantiti diatom. Prestasi RANN diukur daripada ralat min punca kuasa dua (RMSE) dan nilai yang dilaporkan adalah 29.12 sel/mL. Pengelasan dan kelompok oleh SOM dan analisis kepekaan daripadaRANN digunakan untuk mendedahkan hubungan antara suhu air, pH, kepekatan nitrogen nitrat (NO3-N), keperluan oksigen kimia (COD) dan kuantiti diatom. Keputusan menunjukkan bahawa gabungan rangkaian diselia dan tidak diselia neural buatan adalah penting bukan sahaja untuk ramalan pertumbuhan alga tetapi juga dalam analisis dan pemahaman hubungan ekologi. Ini akan membantu dalam pengurusan yang lebih baik bagi kualiti air tasik.

 

Kata kunci: Diatom; peta susun sendiri; ramalan; rangkaian neural buatan berulang

REFERENCES

APHA. 1995. Standard Methods for the Examination of Water and Waste Water. 19th Ed. Washington, D.C: American Public Health Association.

Bowden, G.J., Dandy, G.C. & Maier, H.R. 2006. An evaluation of methods for the selection of inputs for an artificial neural network based river model. Ecological Informatics Recknagel, F. (ed.) 2nd ed. Berlin: Springer-Verlag. pp. 275-292.

Carrillo, P., Reche, I., Sánchez-Castillo, P. & Cruz-Pizarro, L. 1995. Direct and indirect effects of grazing on the Phytoplankton seasonal succession in an oligotrophic lake. Journal of Plankton Research 17: 1363-1379.

Chon, T.S., Park, Y.S., Moon, K.H. & Cha, E.Y. 1996. Patternizing communities by using an artificial neural network. Ecological Modelling90: 67-78.

Colasanti, R.L. 1991. Discussions of the possible use of neural network algorithms in ecologicalmodelling. Binary 3: 13-15.

Cybenko, G. 1989. Approximations by superpositions of sigmoidal functions. Mathematics of Control Signals and Systems 2: 303-314.

Darley, W.M. 1982. Alga Biology: A Physiological Approach. Oxford London: Blackwell Scientific Publication.

Edwards, M. & Morse, D.R. 1995. The potential for computer-aided identification in biodiversity research. Trends in Ecology and Evoluation10: 153-158.

Elfithri, R., Toriman, M.E., Mokhtar, M.B. & Juahir, H. 2011. Perspectives and initiatives on integrated river basin management in Malaysia: A review. The Social Sciences 6(2): 169-176.

Foody, G.M. 1999. Application of the self-organizing feature map neural network in community data analysis. Ecological Modelling120: 97-107.

Gasim, M.B., Toriman, M.E., Rahim, S.A., Islam, M.S., Chek, T.C. & Juahir, H. 2006. Hydrology and water quality assessment of tasik chini’s feeder rivers, Pahang Malaysia Geografia 3: 1-16.

Gray, N.F. 2010. Water Technology, An Introduction For Environmental Scientists and Engineers (3rd ed.). Oxford: Elseiver: 747.

Gurbuz, H., Kivrak, E., Soyupak, S. & Yerli, S.V. 2003. Predicting dominant phytoplankton quantities in reservoir by using neural networks. Hydrobiologia 504: 133-141.

Jeong, K.S., Joo, G.J., Kim, H.W., Ha, K. & Recknagel, F. 2001. Prediction and elucidation of phytoplankton dynamics in the Nakdong River (Korea) by means of a recurrent artificialneural network. Ecological Modelling146: 115-129.

Kingston, J.C. 1982. Association and distribution of common diatoms in surface samples from Northern Minnesota peatlands. Nova Hedwigia 73: 333-346.

Kohonen, T. 1989. Self-Organization and Associative Memory (3rd ed.) Berlin: Springer-Verlag.

Kutty, A.A., Ismail, A. & Fong, C.S. 2001. A preliminary Study of Phytoplankton at Lake Chini Pahang, Pakistan Journal of Biological Sciences 4(3): 309-313.

Leclercq L. 1988. Utilization de trios indices, chimique, diatomique et biocénotique, pour l’évaluation de la qualité de l’eau de la Joncquiere, riviére calcaire polluée par le village de Doische (Belgique, Prov. Namur). Mém. Soc. Roy. Bot. Belg. 10: 26-34.

Lek, S., Delacoste, M., Baran, P., Dimopoulos, I., Lauga, J. & Aulagnier, S. 1996. Application of neural networks to modelling nonlinear relationships in ecology. Ecological Modelling90: 39-52.

Matlab 2006. The Math Works Inc. Matlab (Version 6.5.1).

Maier, H.R., Dandy, G.C. & Burch, M.D. 1998. Use of artificial neural networks for modeling cyanobacteria Anabaena spp. in the River Murray, South Australia. Ecological Modelling105: 257-272.

Maindonald, J.H. & Braun, W.J. 2007. Data Analysis and Graphics Using R . An Example-Based Approach. 2nd ed. Cambridge: Cambridge University Press.

Maznah, W. 2010. Perspectives on the use of algae as biological indicators for monitoring and protecting aquatic environments, with special reference to Malaysian freshwater ecosystems. Tropical Life Sciences Research 21(2): 51-67.

Maznah, W. & Mansor, M. 1999. Benthic diatoms in the Pinang River (Malaysia) and its tributaries with emphasis on species diversity and water quality. International Journal on Algae 1(4): 103-118.

Najah, A., Elshafie, A., Karim, O.A. & Jaffar, O. 2009. Prediction of Johor river water quality parameters using artificial neural networks. European Journal of Scientific Research 28(3): 422-435.

Nather Khan, I.S.A. 1985. Studies on the water quality and periphyton community in Linggi River Basin, Malaysia. PhD Diss., University of Malaya (unpublished)

Nather Khan, I.S.A. 1990. Assessment of water pollution using diatom community structure and species distribution: A case study in a tropical river basin. Internationae Revue der gesamten Hydrobiologie and Hydrographie75(3): 317-338.

Nather Khan, I.S.A. 1991. Effect of urban and industrial wastes on species diversity of the diatom community in a tropical river, Malaysia. Hydrobiologia 224: 175-184.

Patrick, R. 1994. What are the requirements for an effective biomonitor? In: Biological Monitoring of Aquatic Systems. Loeb, Stanford L and Anne Spacie, eds. pp. 23-29.

Pineda, F. 1987. Generalization of backpropagation to recurrent neural networks. Physical Review Letters 19(59): 2229-2232.

Principe, J.C., Euliano, N.R. & Lefebvre, W.C. 1999. Neural and Adaptive Systems: Fundamentals Through Simulations. N.Y: John Wiley & Sons.

Putrajaya Corporation. 1998. Putrajaya Lake Management Guide. Putrajaya Corporation, Selangor Darul Ehsan.

Recknagel, F., Welk, A., Kim, B. & Takamura, N. 2006. Artificial Neural Network Approach to Unravel and Forecast Algal Population Dynamics of Two Lakes Different in Morphometry and Eutrophication. In: Recknagel, F. Ecological Informatics (2nd ed.) NY: Springer-Verlag.

Recknagel, F., Kim, B. & Welk, A. 2005. Unravelling and prediction of ecosystem behaviours of Lake Soyang (South Korea) in response to changing seasons and management by means of artificial neural networks. Verh. Internat. Verein. Limnol29(3): 1497-1502.

Recknagel, F. 2001. Applications of machine learning to ecological modelling. Ecological Modelling146: 303-310.

Reynolds, C.S. 1984. The Ecology of Freshwater Phytoplankton. Cambridge: Cambridge University Press.

Round, F.E. 1984. The Ecology of Algae. Cambridge : Cambridge University Press. pp 653.

Salleh, A. 1996. Panduan Mengenali Alga Air Tawar. Kuala Lumpur: Dewan Bahasa dan Pustaka.

Sawyer, C.N., McCarty, P.L. & Parkin, G.F. 1994. Chemistry for Fnvironmental Engineering. New York: McGraw-Hill.

Schultz, R., Wieland & Lutze, G. 2000. Neural networks in argroecological modelling—stylish application or helpful tool?. Computers and Electronics in Agriculture 29: 73-97.

Sommer, U. 1989. Nutrient status and nutrient competition of phytoplankton in a shallow, hypertrophic lake. Limnology and Oceanography 34(7): 1162-1173.

Talib, A., Abu Hasan, Y. & Abdul Rahman, N.N. 2009. Predicting biochemical oxygen demand as indicator of river pollution using artificial neural networks. 18th World IMACS / MODSIM Congress, Cairns, Australia 13-17 July 2009

Thomann, R.V. & Mueller, J.A. 1987. Principles of Surface Water Quality Modeling and Control New York: Harrper and Row.

Vanni, M.J. & Temte, J. 1990. Seasonal patterns of grazing and nutrient limitation of phytoplankton in a eutrophic lake. Limnology and Oceanography 35: 697-709.

WHO. 1987. WHO, UNEP/WHO/UNESCO/WMO Project on Global Environmental Monitoring. GEM Water Operational Guide.

Werner, D. 1977. The Biology of Diatoms. Bot. Monogr., V. 13. Berkeley and New York: University of California Press,

Zhang, G.P., Patuwo, B.E. & Hu, M.Y. 1998. Forecasting with artificial neural networks: The state of the art. International Journal of Forecasting 14: 35-62.

 

 

*Corresponding author; email: pian@um.edu.my