Advertisement

Journal of Applied Phycology

, Volume 29, Issue 4, pp 2145–2153 | Cite as

Modeling the species richness and abundance of lotic macroalgae based on habitat characteristics by artificial neural networks: a potentially useful tool for stream biomonitoring programs

  • José Celso Rocha
  • Cleto K. Peres
  • José Leonel L. Buzzo
  • Vinícius de Souza
  • Eric A. Krause
  • Pitágoras C. Bispo
  • Fernando Frei
  • Lucas S. M. Costa
  • Ciro C. Z. BrancoEmail author
Article

Abstract

One of the major challenges in stream ecology is the development of computational models that can predict aspects of the community structure of organisms from these ecosystems when they are subject to natural or artificial environmental fluctuations. To contribute towards this aim, we conducted a study whose main goal was to evaluate the efficiency and accuracy of different architectures of multilayer artificial neural networks (ANNs) in predicting the species richness and abundance of macroalgae based on environmental variables of tropical streams. We used data from 82 streams located in southern Brazil, where species richness, macroalgal abundance, and environmental parameters were measured. A set of 20 environmental parameters measured directly in the stream was used as explanatory variables. The performance of the ANN architectures was assessed using two different pieces of software (random combinatorial and exhaustive) and the coefficient of determination (R 2) and mean-squared error (MSE). For both species richness and macroalgal abundance, the best ANN architectures were obtained using random combination software and the performance parameters showed a combination of high R 2 and very low MSE. Our results suggest that computational models that are constructed based on ANN frameworks can be efficient and accurate in predicting the species richness and abundance of stream macroalgae from environmental data. Therefore, considering that models based on linear relationships have often failed, we recommend the application of ANNs as a tool to estimate species richness and abundance of lotic macroalgae from environmental data, in the management, conservation, and biomonitoring programs of tropical stream ecosystems.

Keywords

Stream macroalgae Species richness and abundance Environmental distribution Artificial neural networks Predictive models Stream biomonitoring programs 

Notes

Acknowledgments

This work was supported by funding received by Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP - Grants 2010/17864-0 and 2014/22952-6 to CCZB) and Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq - Grants 306567/2014-8 to CCZB and 305275/2014-3 to PCB). We also thank ICMBio/MMA and the conservation units for granting permission to collect specimens and for providing logistical support during the field works.

Supplementary material

10811_2017_1107_MOESM1_ESM.docx (20 kb)
ESM 1 (DOCX 20 kb)

References

  1. Allan JD, Castillo MM (2007) Stream ecology: structure and function of running water. Springer, DordrechtCrossRefGoogle Scholar
  2. Almeida SFP, Feio MJ (2012) DIATMOD: diatom predictive model for quality assessment of Portuguese running waters. Hydrobiologia 695:185–197CrossRefGoogle Scholar
  3. Bailey RC, Norris RH, Reynolds TB (2004) Bioassessment of freshwater ecosystems - using the reference condition approach. Springer, New YorkCrossRefGoogle Scholar
  4. Barinova S, Liu N, Ding J, An Y, Qin X, Wu C (2016) Ecological assessment of water quality of the Songhua River upper reaches by algal communities. Acta Ecol Sinica 36:126–132CrossRefGoogle Scholar
  5. Beale MH, Hagan MT, Demuth HB (2015) Neural network toolbox: MATLAB user’s guide. The MathWorks Inc, NatickGoogle Scholar
  6. Birk S, Bonne W, Borja A, Brucet S, Courrat A, Poikane S, Solimini A, van de Bund W, Zampoukas N, Hering D (2012) Three hundred ways to assess Europe’s surface waters: an almost complete overview of biological methods to implement the water framework directive. Ecol Indic 18:31–41CrossRefGoogle Scholar
  7. Blois JL, Willians JW, Fitzpatrick MC, Jackson ST, Ferrier S (2013) Space can substitute for time in predicting climate-change effects on biodiversity. Proc Natl Acad Sci U S A 110:9374–9379CrossRefPubMedPubMedCentralGoogle Scholar
  8. Branco CCZ, Necchi Júnior O (1996) Distribution of stream macroalgae in the eastern Atlantic rainforest of São Paulo state, southeastern Brazil. Algol Stud 333:139–150Google Scholar
  9. Branco LHZ, Pereira JL (2002) Evaluation of seasonal dynamics and bioindication potential of macroalgal communities in a polluted tropical stream. Arch Hydrobiol 155:147–161CrossRefGoogle Scholar
  10. Branco CCZ, Krupek RA, Peres CK (2009) Distribution of stream macroalgal communities from the mid-western region of Paraná state, southern Brazil: importance of local-scale variation. Braz Arch Biol Techn 52:379–386CrossRefGoogle Scholar
  11. Branco CCZ, Necchi Júnior O, Peres CK (2010) Effects of artificial substratum types and exposure time on macroalgal colonization in a tropical stream. Fund Appl Limnol 178:17–27CrossRefGoogle Scholar
  12. Branco CCZ, Bispo PC, Peres CK, Tonetto AF, Branco LHZ (2014) The roles of environmental conditions and spatial factors in controlling stream macroalgal communities. Hydrobiologia 732:123–132CrossRefGoogle Scholar
  13. Brey T (2012) A multi-parameter artificial neural network model to estimate macrobenthic invertebrate productivity and production. Limnol Oceanogr-Meth 10:581–589CrossRefGoogle Scholar
  14. Brosse S, Guegan JF, Tourenq JN, Lek S (1999) The use of artificial neural networks to assess fish abundance and spatial occupancy in the littoral zone of a mesotrophic lake. Ecol Model 120:299–311CrossRefGoogle Scholar
  15. Bucklin DN, Basille M, Benscoter AM, Brandt LA, Mazzotti FJ, Romañach SS, Speroterra C, Watling JI (2015) Comparing species distribution models constructed with different subset of environmental predictors. Divers Distrib 21:23–35CrossRefGoogle Scholar
  16. Cantonati M, Rott E, Spitale D, Angeli N, Komárek J (2012) Are benthic algae related to spring types? Freshw Sci 31:481–498CrossRefGoogle Scholar
  17. Catford JA, Naiman RJ, Chambers LE, Roberts J, Douglas M, Davies P (2013) Predicting novel riparian ecosystems in a changing climate. Ecosystems 16:382–400CrossRefGoogle Scholar
  18. Cohen J (1960) A coefficient of agreement for nominal scales. Educ Psycol Meas 20:37–46CrossRefGoogle Scholar
  19. Dell’Uomo A (1991) Use of benthic macroalgae for monitoring rivers in Italy. In: Whitton BA, Rott E, Friedrich G (eds) Use of algae for monitoring rivers. Universität Innsbruck, Innsbruck, pp 129–137Google Scholar
  20. DeNicola DM, Hogland KD, Roemer SC (1992) Influence of canopy cover on spectral irradiance and periphyton assemblages in a prairie stream. J N Am Benthol Soc 11:391–404CrossRefGoogle Scholar
  21. Dudley TL (1992) Beneficial effects of herbivores on stream macroalgae via epiphyte removal. Oikos 65:121–127CrossRefGoogle Scholar
  22. Feio MJ, Dolédec S (2012) Integration of invertebrate traits into predictive models for indirect assessment of stream functional integrity: a case study in Portugal. Ecol Indic 15:236–247CrossRefGoogle Scholar
  23. Ferreira WR, Ligeiro R, Macedo DR, Hughes RM, Kaufmann PR, Oliveira LG, Callisto M (2014) Importance of environmental factors for the richness and distribution of benthic macroinvertebrates in tropical headwater streams. Freshw Sci 33:860–871CrossRefGoogle Scholar
  24. Fielding HG, Bell JF (1997) A review of methods for the assessment of prediction errors in conservation presence/absence models. Environ Conserv 24:38–49CrossRefGoogle Scholar
  25. Gebler D, Kayzer D, Szoszkiewicz K, Budka A (2014) Artificial neural network modeling indices based on physical-chemical characteristics of water. Hydrobiologia 737:215–224CrossRefGoogle Scholar
  26. Gevrey M, Dimopolous I, Lek S (2003) Review and comparison of methods to study the contribution of variables in artificial neural network models. Ecol Model 160:249–264CrossRefGoogle Scholar
  27. Goethals PLM, Dedecker AP, Gabriels W, Lek S, Pauw N (2007) Applications of artificial neural networks predicting macroinvertebrates in freshwaters. Aquat Ecol 41:491–508CrossRefGoogle Scholar
  28. Gordon ND, McMahon TA, Finlayson BL (1992) Stream hydrology: an introduction for ecologists. Wiley, ChichesterGoogle Scholar
  29. Graham NAJ, Jennings S, MacNeil MA, Mouillot D, Wilsno SK (2015) Predicting climate-driven regime shifts versus rebound potential in coral reefs. Nature 518:94–97CrossRefPubMedGoogle Scholar
  30. Hart DD (1992) Community organization in streams: the importance of species interactions, physical factors, and chance. Oecologia 91:220–228CrossRefPubMedGoogle Scholar
  31. Haykin S (2008) Neural networks and learning machines. Prentice Hall, New YorkGoogle Scholar
  32. Hrivnák R, Kochjarová J, Ot’ahel’ová H, Pal’ove-Balang P, Slezák M, Slezák P (2014) Environmental drivers of macrophyte species richness in artificial and natural aquatic water bodies – comparative approach from two central European regions. Ann Limnol 50:269–278CrossRefGoogle Scholar
  33. Hu BF, Xie SL (2006) Effect of seasonality on distribution of macroalgae in a stream system (Xin’an spring) in Shanxi Province, North China. J Integr Plant Biol 48:889–896CrossRefGoogle Scholar
  34. Klose K, Cooper SD, Bennett DM (2015) Effects of wildfire on stream algal abundance, community structure, and nutrient limitation. Freshw Sci 34:1494–1509CrossRefGoogle Scholar
  35. Kovács ZL (2002) Redes neurais artificiais: Fundamentos e Aplicações. Livraria da Física, São PauloGoogle Scholar
  36. Kung SY (1993) Digital neural networks. Prentice Hall, Englewood CliffsGoogle Scholar
  37. Lake PS (2000) Distubance, patchiness, and diversity in streams. J N Am Benthol Soc 19:573–592CrossRefGoogle Scholar
  38. Lek S, Guégan JF (1999) Artificial neural networks as a tool in ecological modeling, an introduction. Ecol Model 120:65–73CrossRefGoogle Scholar
  39. Lek S, Guégan JF (2000) Artificial neuronal networks: application to ecology and evolution. Springer, BerlinCrossRefGoogle Scholar
  40. Lek S, Delacoste M, Baran P, Dimopoulos I, Lauga J, Aulagnier S (1996) Application of neural networks to modeling nonlinear relationships in ecology. Ecol Model 90:39–52CrossRefGoogle Scholar
  41. Lippmann RP (1987) An introduction to computing with neural nets. IEEE a.S.S.P. Magazine 2:4–22Google Scholar
  42. Lopez-Exposito P, Suarez AB, Negro C (2016) Estimation of Chlamydomonas reinhardtii biomass concentration from chord length distribution data. J Appl Phycol 28:2315–2322CrossRefPubMedGoogle Scholar
  43. Manel S, Dias JM, Buckton ST, Ormerod SJ (1999) Alternative methods for predicting species distribution: an illustration with Himalayan river birds. J Appl Ecol 36:734–747CrossRefGoogle Scholar
  44. Necchi Júnior O, Branco CCZ, Branco LHZ (2000) Distribution of stream macroalgae in São Paulo state, southeastern Brazil. Algol Stud 97:43–57Google Scholar
  45. Necchi Júnior O, Branco LHZ, Branco CCZ (2003) Ecological distribution of stream macroalgal communities from a drainage basin in the Serra da Canastra National Park, Minas Gerais, southeastern Brazil. Braz J Biol 63:1–12CrossRefGoogle Scholar
  46. Oberholster PJ, De Klek AR, De Klek L, Chamier J, Botha A-M (2016) Algal assemblage responses to acid mine drainage and steel plant wastewater effluent up and downstream of pre and post wetland rehabilitation. Ecol Indic 62:106–116Google Scholar
  47. Olaya-Marín EJ, Martínez-Capel F, Soares Costa RM, Alcaraz-Hernandez JD (2012) Modeling native fish richness to evaluate the effects of hydromorphological changes and river restoration (Júcar River basin, Spain). Sci Total Environ 440:95–105CrossRefPubMedGoogle Scholar
  48. Olaya-Marín EJ, Martínez-Capel F, Vezza P (2013) A comparison of artificial neural networks and random forests to predict native fish species richness in Mediterranean rivers. Knowl Manag Aquat Ecosys 409:1–19Google Scholar
  49. Oppel S, Meirinhyo A, Ramírez I, Gardner B, O’Connell AF, Miller PI, Louzao M (2012) Comparison of five modeling techniques to predict the spatial distribution and abundance of seabirds. Biol Conserv 156:94–104CrossRefGoogle Scholar
  50. Ormerod SJ (2014) Rebalancing the philosophy of river conservation. Aquat Conserv Mar Freshwat Ecosys 24:147–152CrossRefGoogle Scholar
  51. Park YS, Céréghino R, Compin A, Lek S (2003) Applications of artificial neural networks for patterning and predicting aquatic insect species richness in running waters. Ecol Model 160:265–280CrossRefGoogle Scholar
  52. Penczak T, Glowacki L, Kruk A, Galicka W (2012) Implementation of a self-organizing map for investigation of impoundment impact on fish assemblages in a large, lowland river: long-term study. Ecol Model 227:64–71CrossRefGoogle Scholar
  53. Peres CK, Branco CCZ, Krupek RA (2009) Distribuição ambiental e temporal das comunidades de macroalgas de riachos da Serra da Prata, Estado do Paraná, sul do Brasil. Braz J Bot 32:625–633CrossRefGoogle Scholar
  54. Peres CK, Branco CCZ, Krupek RA, Rocha JC (2010) Longitudinal distribution and seasonality of macroalgae in a subtropical stream impacted by organic pollution. Acta Limnol Bras 22:199–207CrossRefGoogle Scholar
  55. Pottier J, Dubuis A, Pellisier L, Maiorano L, Rossier L, Randin CF, Vittoz P, Guisan A (2013) The accuracy of plant assemblage prediction from species distribution models varies along environmental gradients. Glob Ecol Biogeogr 22:52–63CrossRefGoogle Scholar
  56. Rakocevic-Nedovic J, Hollert H (2005) Phytoplankton community and chlorophyll a as trophic state indices of Lake Skadar (Montenegro, Balkan). Environ Sci Pollut Res 12:146–152CrossRefGoogle Scholar
  57. Randin CF, Dirnböck T, Dullinger S, Zimmermann NE, Zappa M, Guisan A (2006) Are niche-based species distribution models transferable in space? J Biogeogr 33:1689–1703CrossRefGoogle Scholar
  58. Recknagel F (1997) ANNA – artificial neural network model for predicting species abundance and succession of blue-green algae. Hydrobiologia 349:47–57CrossRefGoogle Scholar
  59. Reynoldson TB, Bailey RC, Day KE, Norris RH (1995) Biological guidelines for freshwater sediment based on benthic assessment of sediment (the BEAST) using a multivariate approach for predicting biological state. Aust J Ecol 20:198–219CrossRefGoogle Scholar
  60. Rier ST, Stevenson RJ (2006) Response of periphytic algae to gradients in nitrogen and phosphorus in streamside mesocosms. Hydrobiologia 561:131–147CrossRefGoogle Scholar
  61. Rovzar C, Gillespie TW, Kawelo K (2016) Landscape to site variations in species distribution models for endangered plants. Forest Ecol Manag 369:20–28CrossRefGoogle Scholar
  62. Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323:533–536CrossRefGoogle Scholar
  63. Schneider SC, Kahlert MK, Kelly MG (2013) Interactions between pH and nutrients on benthic algae in streams and consequences for ecological status assessment and species richness patterns. Sci Total Environ 444:73–84CrossRefPubMedGoogle Scholar
  64. Schoeninger ER, Koehler HS, Botelho MF, Watzlawick LF, Oliveira PC (2008) Uso de redes neurais artificiais para mapeamento de biomassa e carbono orgânico no componente arbóreo de uma floresta ombrófila densa. Ambiência 4:179–195Google Scholar
  65. Sheath RG, Cole KM (1992) Biogeography of stream macroalgae in North America. J Phycol 28:448–460CrossRefGoogle Scholar
  66. Simpson J, Norris RH (2000) Biological assessment of water quality: development of AUSRIVAS models and outputs. In: Wright JF, Sutcliffe DM, Furse MT (eds) RIVPACS and similar techniques for assessing the biological quality of freshwaters. Freshwater Biological Association and Environment Agency, Ambleside, pp 125–142Google Scholar
  67. Stancheva R, Sheath RG (2016) Benthic spft-body algae as bioindicators of stream water quality. Knowl Manag Aquat Ecosyst 417:15CrossRefGoogle Scholar
  68. Stancheva R, Fetscher AE, Sheath RG (2012) A novel quantification method for stream-inhabiting, non-diatom benthic algae, and its application in bioassessment. Hydrobiologia 684:225–239CrossRefGoogle Scholar
  69. Stevenson RJ (2014) Ecological assessments with algae: a review and synthesis. J Phycol 50:437–461CrossRefPubMedGoogle Scholar
  70. Stevenson RJ, Rier ST, Riseng CM, Schultz RE, Wiley MJ (2006) Comparing effects of nutrients on algal biomass in streams in two regions with different disturbance regimes and with applications for developing nutrient criteria. Hydrobiologia 561:149–165CrossRefGoogle Scholar
  71. Teittinen A, Kallajoki L, Meier S, Stigzelius T, Soininen J (2016) The roles of evaluation and local environmental factors as drivers of diatom diversity in subarctic streams. Freshw Biol 61:1509–1521CrossRefGoogle Scholar
  72. Verb RG, Vis ML (2001) Macroalgal communities from an acid mine drainage impacted watershed. Aquat Bot 71:93–107CrossRefGoogle Scholar
  73. Verb RG, Vis ML (2005) Periphyton assemblage as bioindicator of mine-drainage in unglaciated western allegheny plateau lotic systems. Water Air Soil Pollut 161:227–265CrossRefGoogle Scholar
  74. Wisz MS, Pottier J, Kissling D, Pellissier L, Lenoir J, Damgaard CF, Dormann CF, Prachhammer MC, Grytnes JA, Guisan A, Heikkinen RK, Hoyer TT, Kühn I, Luoto M, Maiorano L, Nilsson MC, Normand S, Öckinger E, Schmidt NM, Termanssen M, Timmermann A, Wardle DA, Aastrup P, Svenning JC (2013) The role of biotic interactions in shaping distributions and realised assemblages of species: implications for species distribution modeling. Biol Rev 88:15–30CrossRefPubMedGoogle Scholar
  75. Wright JF (1995) Development and use of a system for predicting the macroinvertebrate fauna in flowing waters. Aust J Ecol 20:181–197CrossRefGoogle Scholar
  76. Yang J, Yu X, Liu L, Zhang W, Guo P (2012) Algae community and trophic state of subtropical reservoirs in Southeast Fujian, China. Environ Sci Pollut Res Int 19:1432–1442CrossRefPubMedGoogle Scholar
  77. Yoo JW, Lee Y, Lee CG, Kim CS (2013) Effective prediction of biodiversity in tidal flat habitats using an artificial neural network. Mar Environ Res 83:1–9CrossRefPubMedGoogle Scholar
  78. Zanchettin C, Ludermir TB (2005) Sistemas neurais híbridos para reconhecimento de padrões em narizes artificiais. SBA Controle & Automação 2:159–172CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2017

Authors and Affiliations

  • José Celso Rocha
    • 1
  • Cleto K. Peres
    • 2
  • José Leonel L. Buzzo
    • 1
  • Vinícius de Souza
    • 1
  • Eric A. Krause
    • 1
  • Pitágoras C. Bispo
    • 1
  • Fernando Frei
    • 1
  • Lucas S. M. Costa
    • 1
  • Ciro C. Z. Branco
    • 1
    Email author
  1. 1.Department of Biological SciencesSão Paulo State University—UNESPAssisBrazil
  2. 2.Federal University for Latin American Integration—UNILAFoz do IguaçuBrazil

Personalised recommendations