Use of machine learning to establish limits in the classification of hyperaccumulator plants growing on serpentine, gypsum and dolomite soils

  1. Mota-Merlo, Marina 1
  2. Martos, Vanessa 2
  1. 1 Uppsala University
    info

    Uppsala University

    Upsala, Suecia

    ROR https://ror.org/048a87296

  2. 2 Universidad de Granada
    info

    Universidad de Granada

    Granada, España

    ROR https://ror.org/04njjy449

Revista:
Mediterranean Botany

ISSN: 2603-9109

Año de publicación: 2021

Volumen: 42

Tipo: Artículo

DOI: 10.5209/MBOT.67609 DIALNET GOOGLE SCHOLAR lock_openAcceso abierto editor

Otras publicaciones en: Mediterranean Botany

Resumen

The so-called hyperaccumulator plants are capable of storing hundred or thousand times bigger quantities of heavy metals than normal plants, which makes hyperaccumulators very useful in fields such as phytoremediation and phytomining. Among these plants there are many serpentinophytes, i.e., plants that grow exclusively on ultramafic rocks which produce soils with a great proportion of heavy metals. Even though there are multiple classifications, the lack of consensus regarding which parameters to use to determine whether a plant is a hyperaccumulator, as well as the arbitrariness of stablished thresholds, bring about the need to propose more objective criteria. To this end, plant mineral composition data from different vegetal species were analysed using machine learning techniques. Three complementary case studies were established. Firstly, plants were classified in three types of soils: dolomite, gypsum and serpentine. Secondly, data about normal and hyperaccumulator plant Ni composition were analysed with machine learning to find differentiated subgroups. Lastly, association studies were carried out using data about mineral composition and soil type. Results in the classification task reach a success rate over 75%. Clustering of plants by Ni concentration in parts per million (ppm) resulted in four groups with cut-off points in 2.25, 100 (accumulators) and 3000 ppm (hyperaccumulators). Associations with a confidence level above 90% were found between high Ni levels and serpentine soils, as well as between high Ni and Zn levels and the same type of soil. Overall, this work demonstrates the potential of machine learning to analyse data about plant mineral composition. Finally, after consulting the red list of the IUCN and those of countries with high richness in hyperaccumulator species, it is evident that a greater effort should be made to establish the conservation status of this type of flora.

Referencias bibliográficas

  • Alloway, B.J. 2013. Heavy Metals in Soils. In: Alloway, B.J. & Trevors, J.T. (Eds.). Environmental Pollution, vol. 22, 3rd ed. Pp. 195–209. Springer, Dordrecht.
  • Alphy, M. & Sharma, A. 2020. A literature review on different types of machine learning methods in web mining. Int. J. Psychosoc. Rehabil. 24(1): 1761–1769. doi: 10.37200/IJPR/V24I1/PR200276.
  • Batool, S. 2018. Effect of nickel toxicity on growth, photosynthetic pigments and dry matter yield of Cicer arietinum L. varieties. https://www.asianjab.com/wp-content/uploads/2018/06/2.-OK_Effect-of-nickel-toxicity-on-growth-photosynthetic-pigments.pdf.
  • Berazain, R. 1999. Estudios en plantas acumuladoras e hiperacumuladoras de níquel en el Caribe. Rev del Jardín Botánico Nac. 20:17–30. doi: 10.2307/42597044.
  • Beygi, M. & Jalali, M. 2019. Assessment of trace elements (Cd, Cu, Ni, Zn) fractionation and bioavailability in vineyard soils from the Hamedan, Iran. Geoderma. 337: 1009–1020. doi: 10.1016/j.geoderma.2018.11.009.
  • Bilz, M., Kell, S.P., Maxted, N. & Lansdown, R.V. 2011. European Red List of Vascular Plants. [accessed 2020 Feb 7]. www.tasamim.net.
  • Brooks, R.R., Lee, J., Reeves, R.D. & Jaffre, T. 1977. Detection of nickeliferous rocks by analysis of herbarium specimens of indicator plants. J. Geochem. Explor. 7(C): 49–57. doi: 10.1016/0375-6742(77)90074-7.
  • Burger, A. & Lichtscheidl, I. 2018. Strontium in the environment: Review about reactions of plants towards stable and radioactive strontium isotopes. Sci. Total Environ. 653:1458–1512. doi: 10.1016/j.scitotenv.2018.10.312.
  • Buscaroli, A. 2017. An overview of indexes to evaluate terrestrial plants for phytoremediation purposes (Review). Ecol. Indic. 82:367–380. doi:10.1016/j.ecolind.2017.07.003. doi: 10.1016/j.ecolind.2017.07.003.
  • Al Chami, Z., Amer, N., Al Bitar, L. & Cavoski, I. 2015. Potential use of Sorghum bicolor and Carthamus tinctorius in phytoremediation of nickel, lead and zinc. Int. J. Environ. Sci. Technol. 12(12): 3957–3970. doi: 10.1007/s13762-015-0823-0.
  • Corzo Remigio, A., Chaney, R.L., Baker, A.J.M., Edraki, M., Erskine, P.D., Echevarria, G. & van der Ent, A. 2020. Phytoextraction of high value elements and contaminants from mining and mineral wastes: opportunities and limitations. Plant Soil 449(1–2): 11–37. doi: 10.1007/s11104-020-04487-3.
  • Drazin, S. & Montag, M. 2012. Decision Tree Analysis using Weka. Project report. 3p.
  • Echevarria, G. 2018. Genesis and Behaviour of Ultramafic Soils and Consequences for Nickel Biogeochemistry. In: Van der Ent, A., Echevarria, G., Baker, A. & Morel, J. (Eds.). Agromining: Farming for Metals. Pp. 135–156. Mineral Resource Reviews. Springer, Cham.
  • Ekim, T., Koyuncu, M., Vural, M., Duman, H., Aytaç, Z. & Adigüzel, N. 1989. Red data book of Turkish plants. (Pteridophyta and Spermatophyta). Turkish Assoc. Conserv. Nature, Ankara.
  • Faucon, M.P., Meersseman, A., Shutcha, M.N., Mahy, G., Luhembwe, M.N., Malaisse, F. & Meerts, P. 2010. Copper endemism in the congolese flora: A database of copper affinity and conservational value of cuprophytes. Plant Ecol. Evol. 143(1): 5–18. doi: 10.5091/plecevo.2010.411.
  • González Torres, L.R., Palmarola, A., González Oliva, L., Bécquer, E.R., Testé, E. & Barrios, D. 2016. Lista Roja de la Flora de Cuba. Bissea. 10(1): 352. doi: 10.13140/RG.2.2.24056.65288.
  • Guillén, F.J., Baeza, A. & Salas, A. 2011. Strontium. In: Atwood, D. (Ed.). Radionuclides in the environment. Pp. 1-17. Encyclopedia of Inorganic and Bioinorganic Chemistry. John Wiley & Sons Ltd., Chichester. http: //dx.doi.org/10.1002/9781119951438.eibc0416.
  • Han, J., Kamber, M. & Pei, J. 2006. Data Mining: Concepts and Techniques, 3rd ed. Elsevier, Amsterdam.
  • Jung, Y.G., Kang, M.S. & Heo, J. 2014. Clustering performance comparison using K-means and expectation maximization algorithms. Biotechnol. Biotechnol. Equip. 28(1):S44–S48. doi:10.1080/13102818.2014.949045. doi: 10.1080/13102818.2014.949045.
  • Khan, A., Khan, S., Khan, M.A., Qamar, Z. & Waqas, M. 2015. The uptake and bioaccumulation of heavy metals by food plants, their effects on plants nutrients, and associated health risk: a review. Environ. Sci. Pollut. R. 22(18): 13772–13799. doi: 10.1007/s11356-015-4881-0.
  • Kidd, P.S., Becerra Castro, C., Garcia Lestón, M. & Monterroso, C. 2007. Aplicación de plantas hiperacumuladoras de níquel en la fitoextracción natural: el género Alyssum L. Ecosistemas 2(2): 1–18.
  • Marschner, H. 2016. Marschner’s Mineral Nutrition of Higher Plants. 3rd ed. Academic Press.
  • Martínez-Hernández, F. 2013. Patrones biogeográficos de la flora gipsícola ibérica. Mem. Doc. (ined.). Universidad de Almería.
  • McCartha, G.L., Taylor, C.M., van der Ent, A., Echevarria, G., Navarrete Gutiérrez, D.M. & Pollard, A.J. 2019. Phylogenetic and geographic distribution of nickel hyperaccumulation in neotropical Psychotria. Am. J. Bot. 106(10): 1377–1385. doi: 10.1002/ajb2.1362.
  • Medina-Cazorla, J.M. 2015. Conservación y biogeografía de la flora dolomitófila bética. Mem. Doc. (ined.). Universidad de Almería.
  • Mengoni, A., Schat, H. & Vangronsveld, J. 2010. Plants as extreme environments? Ni-resistant bacteria and Ni-hyperaccumulators of serpentine flora. Plant Soil. 331(1):5–16. doi: 10.1007/s11104-009-0242-4.
  • Mganga, N., Manoko, M. & Rulangaranga, Z. 2011. Classification of Plants According to Their Heavy Metal Content around North Mara Gold Mine, Tanzania: Implication for Phytoremediation. Tanzania J. Sci. 37(1): 109–119.
  • Mohseni, R., Ghaderian, S.M. & Schat, H. 2019. Nickel uptake mechanisms in two Iranian nickel hyperaccumulators, Odontarrhena bracteata and Odontarrhena inflata. Plant Soil 434(1–2): 263–269. doi: 10.1007/s11104-018-3814-3.
  • Monson, R.K. (Ed.). 2014. Ecology and the environment. Springer-Verlag, New York.
  • Navarrete Gutiérrez, D.M., Pons, M.N., Cuevas Sánchez, J.A. & Echevarria, G. 2018. Is metal hyperaccumulation occurring in ultramafic vegetation of central and southern Mexico? Ecol. Res. 33(3): 641–649. doi: 10.1007/s11284-018-1574-4.
  • Okereafor, U., Makhatha, M., Mekuto, L., Uche-Okereafor, N., Sebola, T. & Mavumengwana, V. 2020. Toxic metal implications on agricultural soils, plants, animals, aquatic life and human health. Int. J. Environ. Res. Pu. 17(7): 1–24. doi: 10.3390/ijerph17072204.
  • Prance, G.T. & Brooks, R.R. 1988. Serpentine and Its Vegetation. A Multidisciplinary Approach. Brittonia 40(3): 268. doi: 10.2307/2807470.
  • Quinlan, J.R. 1993. C4.5: Programs for Machine Learning. San Mateo, California: Morgan Kaufmann Publishers.
  • Rajakaruna, N., Harris, T.B. & Alexander, E.B. 2009. Serpentine Geoecology of Eastern North America: A Review. Rhodora 111(945): 21–108. doi: 10.3119/07-23.1.
  • Rajkumar, M., Prasad, M.N.V., Freitas, H. & Ae, N. 2009. Biotechnological applications of serpentine soil bacteria for phytoremediation of trace metals. Crit. Rev. Biotechnol. 29(2): 120–130. doi: 10.1080/07388550902913772.
  • Reeves, R.D., Baker, A.J.M., Jaffré, T., Erskine, P.D., Echevarria, G. & van der Ent, A. 2017. A global database for plants that hyperaccumulate metal and metalloid trace elements. New Phytol. 218(2): 407–411. doi: 10.1111/nph.14907.
  • Rooney, N., Patterson, D. & Galushka, M. 2004. A comprehensive review of recursive Naïve Bayes Classifiers. Intell. Data Anal. 8(6): 615–628. doi: 10.3233/ida-2004-8607.
  • Rostami, S. & Azhdarpoor, A. 2019. The application of plant growth regulators to improve phytoremediation of contaminated soils: A review. Chemosphere 220: 818–827. doi: 10.1016/j.chemosphere.2018.12.203.
  • Salmerón-Sánchez, E., Martínez-Nieto, M.I., Martínez-Hernández, F., Garrido-Becerra, J.A., Mendoza-Fernández, A.J., de Carrasco, C.G., Ramos-Miras, J.J., Lozano, R., Merlo, M.E. & Mota, J.F. 2014. Ecology, genetic diversity and phylogeography of the Iberian endemic plant Jurinea pinnata (Lag.) DC. (Compositae) on two special edaphic substrates: dolomite and gypsum. Plant Soil. 374(1–2): 233–250. doi: 10.1007/s11104-013-1857-z.
  • Shabala, S. 2013. Plant stress physiology. Choice Rev. Online 50(05): 50–2652. doi: 10.5860/choice.50-2652.
  • Shah, V. & Daverey, A. 2020. Phytoremediation: A multidisciplinary approach to clean up heavy metal contaminated soil. Environ. Technol. Innov. 18: 100774. doi: 10.1016/j.eti.2020.100774.
  • Taiz, L. & Zeiger, E. 2010. Plant physiology. Sinauer Associates, Sunderland.
  • Wang, X., Chen, C., Wang, J. 2017. Phytoremediation of strontium contaminated soil by Sorghum bicolor (L.) Moench and soil microbial community-level physiological profiles (CLPPs). Environ. Sci. Pollut. Res. 24(8): 7668–7678. doi: 10.1007/s11356-017-8432-8.
  • Watanabe, T., Broadley, M.R., Jansen, S., White, P.J., Takada, J., Satake, K., Takamatsu, T., Tuah, S.J. & Osaki, M. 2007. Evolutionary control of leaf element composition in plants: Rapid report. New Phytol. 174(3): 516–523. doi: 10.1111/j.1469-8137.2007.02078.x.
  • Witten, I.H., Frank, E., Hall, M.A. & Pal, C.J. 2017. Data Mining - Practical Machine Learning Tools and Techniques, 4th ed. Kaufmann ed. Elsevier Inc, Cambridge.
  • Wright, J.W. & Wettberg, E. von. 2009. "Serpentinomics" - An Emerging New Field of Study. Northeast Nat. 16(sp5): 285–296. doi: 10.1656/045.016.0521.
  • Wulff, A.S., Hollingsworth, P.M., Ahrends, A., Jaffré, T., Veillon, J.M., L'Huillier, L. & Fogliani B. 2013. Conservation Priorities in a Biodiversity Hotspot: Analysis of Narrow Endemic Plant Species in New Caledonia. PLoS One. 8(9). doi: 10.1371/journal.pone.0073371.
  • Xue, H., Xu, H., Chen, X. & Wang, Y. 2020. A primal perspective for indefinite kernel SVM problem. Front. Comput. Sci-Chi. 14(2): 349–363. doi: 10.1007/s11704-018-8148-z.
  • DSEWPC. 2009. EPBC Act List of Threatened Flora. SPRATT Profile. [accessed 2020 Jun 7]. http://www.environment.gov.au/cgi-bin/sprat/public/publicthreatenedlist.pl?wanted=flora#flora_critically_endangered.
Fuente de los datos: Dialnet