Abstract
In the present study, the data-driven (classification trees and support vector machines) and multivariate techniques (principal component analysis and discriminant analysis) were applied to study the habitat preferences of an invasive aquatic fern (Azolla filiculoides) in the Selkeh Wildlife Refuge (a protected area in Anzali wetland, northern Iran). The applied database consisted of measurements from seven different sampling sites in the protected area over the study period 2007–2008. The cover percentage of the exotic fern was modelled based on various wetland characteristics. The predictive performances of the both data-driven methods were assessed based on the percentage of Correctly Classified Instances and Cohen’s kappa statistics. The results of the Paired Student’s t-test (p < 0.01) showed that SVMs outperformed the CTs and thus yielded more reliable prediction than the CTs. All data mining and multivariate techniques showed that both physical-habitat and water quality variables (in particular some nutrients) might affect the habitat requirements of A. filiculoides in the wetland.
Similar content being viewed by others
References
Abbasi FM, Brar DS, Carpena AL, Fukui K, Khush GS (1999) Detection of autosyndetic and allosyndetic pairing among A and E genomes of Oryza through genomic in situ hybridization. Rice Genet Newsl 16:24–25
Ahmad SS, Reshi ZA, Shah MA, Rashid I, Ara R, Andrabi SMA (2016) Heavy metal accumulation in the leaves of Potamogeton natans and Ceratophyllum demersum in a Himalayan RAMSAR site: management implications. Wetl Ecol Manag 24(4):469–475
Akkermans W, Verdonschot PFM, Nijboer RC, Goedhart PW, Braak CJF (2004) Predicting macro-fauna community types from environmental variables by means of support vector machines. In: Lek S, Scardi M, Verdonschot PFM, Descy JP, Park YS (eds) Modelling community structure in freshwater ecosystems. Springer, Berlin, p 518
Ambelu A, Lock K, Goethals PLM (2010) Comparison of modelling techniques to predict macroinvertebrate community composition in rivers of Ethiopia. Ecol Inform 5:147–152
APHA/AWWA/WEF (1998) Standard methods for the examination of water and wastewater, 19th ed. Washington
Barreto R, Charudattan A, Pomella A, Hanada R (2000) Biological control of neotropical aquatic weeds with fungi. Crop Prot 19:697–703
Biswas M, Parveen S, Shimozawa H, Nakagoshi N (2005) Effects of Azolla species on weed emergence in a rice paddy ecosystem. Weed Biol Manag 5:176–183
Bocchi S, Malgioglio A (2010) Azolla–Anabaena as a biofertilizer for rice paddy fields in the Po Valley, a temperate rice area in northern Italy. Int J Agron. doi:10.1155/2010/152158
Boivin J, Ng S (2006) Are more data always better for factor analysis? J Econ 132:169–194
Buckland ST, Borchers DL, Johnston A, Henrys PA, Marques TA (2007) Line transect methods for plant surveys. Biometrics 63:989–998
Cohen J (1960) A coefficient of agreement for nominal scales. Educ Psychol Meas 20:37–46
Dakou E, D’heygere T, Dedecker A, D’heygere T, Goethals PLM, De Pauw N, Lazaridou-Dimitriadou M (2007) Decision tree models for prediction of macroinvertebrate taxa in the river Axios Northern Greece. Aquat Ecol 41:399–411
Davis JC (1986) Statistics and data analysis in geology. Wiley, New York
De’ath G, Fabricius KE (2000) Classification and regression trees: a powerful yet simple technique for ecological data analysis. Ecology 81:3178–3192
Delnavaz B, Ataei A (2009) Alien and exotic Azolla in northern Iran. Afr J Biotechnol 8:187–190
Devin S, Beisel JN (2007) Biological and ecological characteristics of invasive species, a gammarid study. Biol Invasions 9:13–24
Dzeroski S, Demsar D, Grbovic J (2000) Predicting chemical parameters of river water quality from bioindicator data. Appl Intell 13:7–17
Elshorbagy A, El-Baroudy I (2009) Investigating the capabilities of evolutionary data-driven techniques using the challenging estimation of soil moisture content. J Hydroinf 11:237–251
Everaert G, Boets P, Lock K, Džeroski S, Goethals PLM (2011) Using classification trees to analyze the ecological impact of invasive species in polder lakes in Flanders, Belgium. Ecol Model 222:2202–2212
Fernández-Zamudio R, García-Murilloa P, Cirujano S (2010) Germination characteristics and sporeling success of A. filiculoides Lam., an aquatic invasive fern, in a Mediterranean temporary wetland. Aquat Bot 93:89–92
Fielding AH, Bell JF (1997) A review of methods for the assessment of prediction errors in conservation presence/absence models. Environ Conserv 24:38–49
Fukunaga K (1990) Introduction to statistical pattern recognition. Academic Press, New York
Giustolisi O, Savic DA (2009) Advances in data-driven analyses and modelling using EPR-MOGA. J Hydroinf 11:225–236
Goethals PLM (2005) Data driven development of predictive ecological models for benthic macroinvertebrates in rivers. PhD thesis. University of Ghent, p 377
Goethals PLM, De Pauw N (2001) Development of a concept for integrated river assessment in Flanders, Belgium. J Limnol 60(1):7–16
Goethals PLM, Dedecker AP, Gabriels W, Lek S, De Pauw N (2007) Applications of artificial neural networks predicting macroinvertebrates in freshwaters. Aquat Ecol 41:491–508
Gooyong L, Sangeun L, Heekyung P (2014) Improving applicability of neuro-genetic algorithm to predict short-term water level: a case study. J Hydroinf. doi:10.2166/hydro.2013.011
Haghi Vayghan A, Zarkami R, Sadeghi R, Fazli H (2015) Modelling habitat preferences of Caspian kutum, Rutilus frisii kutum (Kamensky, 1901) (Actinopterygii, Cypriniformes) in the Caspian Sea. Hydrobiologia. doi:10.1007/s10750-015-2446-3
Hammer Ø (2013) Paleontological statistics (PAST). Natural History Museum, University of Oslo, Oslo, p 221
Harper DAT (1999) Numerical palaeobiology. Wiley, New York
Hill MP (2003) The impact and control of alien aquatic vegetation in South African aquatic ecosystems. Afr J Aquat Sci 28:19–24
Hoang TH, Lock K, Mouton A, Goethals PLM (2010) Application of classification trees and support vector machines to model the presence of macroinvertebrates in rivers in Vietnam. Ecol Inform 5:140–146
Janes R (1998) Growth and survival of A. filiculoides in Britain. 1. Vegetative reproduction. New Phytol 138:367–376
Japan International Cooperation Agency (JICA) (2005) The study on integrated management of the Anzali Wetland in the Islamic Republic of Iran-final report, vol 2. p 222
Kannaiyan S, Somporn C (1989) Effect of high temperature on growth, nitrogen fixation, and chlorophyll content of five species of Azolla-Anabaena symbiosis. Biol Fertil Soils 7:168–172
Karatayev AY, Burlakova LE, Padilla DK, Mastitsky SE, Olenin S (2009) Invaders are not a random selection of species. Biol Invasions 11:2009–2019
Keerthi SS, Shevade SK, Bhattacharyya C, Murthy KRK (2001) Improvements to Platt’s SMO algorithm for SVM classifier design. Neural Comput 13:637–649
Landis JR, Koch GG (1977) The measurement of observer agreement for categorical data. Biometrics 33:159–174
Liu X, Min C, Xia-shi L, Chungchu L (2008) Research on some functions of Azolla in CELSS system. Acta Astronaut 63:1061–1066
Lumpkin TA, Plucknett DL (1982) Azolla as a green manure, use and management in crop production. Westview tropical agriculture, vol 5. Westview Press, Boulder
Mansoori J (1995) Islamic Republic of Iran. In: Scott DA (ed) A directory of wetlands in the Middle East. IUCN, Slimbridge
Olenin S, Minchin D, Daunys D (2007) Assessment of biopollution in aquatic ecosystems. Mar Pollut Bull 55:379–394
Parsons M, Thoms MC, Horris RH (2004) Development of a standard approach to river habitat assessment in Australia. Environ Monit Assess 98:109–130
Platt J (1998) Fast training of support vector machines using sequential minimal optimization. In: Schoelkopf B, Burges C, Smola A (eds) Advances in Kernel methods—support vector learning. MIT Press, Cambridge
Quinlan JR (1993) C4.5, program for machine learning. Morgan Kaufmann Publishers, San Francisco, p 302
Ricciardi A, MacIsaac HJ (2000) Recent mass invasion of the North American Great Lakes by Ponto-Caspian species. Trends Ecol Evol 15:62–65
Robert JA (2003) Neural network rainfall-runoff forecasting based on continuous resampling. J Hydroinf 5:51–61
Sadeghi R, Zarkami R, Sabetraftar K, Van Damme P (2012) Application of classification trees to model the distribution pattern of a new exotic species Azolla filiculoides (Lam.) in Selkeh Wildlife Refuge, Anzali wetland, Iran. Ecol Model 243:8–17
Savic DA, Giustolisi O, Laucelli D (2009) Asset deterioration analysis using multi-utility data and multi-objective data. J Hydroinf 11:211–224
Serag MS, El-Hakeem A, Badway M, Mousa MA (2000) On the ecology of A. filiculoides Lam. in Damietta District, Egypt. Limnologica 30:73–81
Sumners WH, Archibold OW (2007) Exotic plant species in the southern boreal forest of Saskatchewan. For Ecol Manag 251:156–163
Sweet AR, Hills LV (1971) A study of A. pinnata R. brown. Am Fern J 71:1–14
Taghi-Ganji M, Khosravi M, Rakhshaee R (2005) Biosorption of Pb (2I), Cd (2I), Cu (2I) and Zn (II) from the wastewater by treated A. filiculoides with H2O2/MgCl2. Int J Environ Sci Technol 1:265–271
Van Der Heide T, Roijackers RMM, Peeters ETHM, Van Nes EH (2006) Experiments with duckweed–moth systems suggest that global warming may reduce rather than promote herbivory. Freshw Biol 51:110–116
Van Hove C, Lejeune A (2002) The Azolla–Anabaena symbiosis. Biol Environ 102:23–26
Vander Zanden MJ, Olden JD (2008) A management framework for preventing the secondary spread of aquatic invasive species. Can J Fish Aquat Sci 65:1512–1522
Vapnik V (1995) The nature of statistical learning theory. Springer, New York, p 187
Vitousek PM, D’Antonio CM, Loope LL, Westbrooks R (1996) Biological invasions as global environmental change. Am Sci 84:468–478
Watanabe I, Espinase CR (1976) Potential of nitrogen fixing Azolla–Anabaena complex as fertilizer in paddy soil. IRRI Saturday seminar
Witten IH, Frank E, Hall MA (2011) Data mining, practical machine learning tools and techniques, 3rd edn. Morgan Kaufmann, San Francisco, p 629
Zarkami R (2011) Application of classification trees-J48 to model the presence of roach (Rutilus rutilus) in rivers. CJES 9:189–198
Zarkami R, Goethals PLM, De Pauw N (2010) Use of classification tree methods to study the habitat requirements of tench Tinca tinca. L., 1758. CJES 8:55–63
Zarkami R, Sadeghi R, Goethals PLM (2012) Use of fish distribution modelling for river management. Ecol Model 230:44–49
Zarkami R, Sadeghi R, Goethals PLM (2014) Modelling occurrence of roach ‘‘Rutilus rutilus’’ in streams. Aquat Ecol 48:161–177
Zhengfu R, Fernando A (2007) Use of an artificial neural network to capture the domain knowledge of a conventional hydraulic simulation model. J Hydroinf 9(1):15–24
Zimmerman WJ (1985) Biomass and pigment production in three isolates of Azolla: II. Response to light and temperature stress. Ann Bot Lond 56:701–709
Acknowledgements
We would like to thank Guilan Environmental Protection Bureau and Selkeh Wildlife Refuge centre for giving opportunity to take samples in the field.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Sadeghi, R., Zarkami, R. & Van Damme, P. Analyzing the occurrence of an invasive aquatic fern in wetland using data-driven and multivariate techniques. Wetlands Ecol Manage 25, 485–500 (2017). https://doi.org/10.1007/s11273-017-9530-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11273-017-9530-6