Advertisement

Journal of Soils and Sediments

, Volume 19, Issue 5, pp 2265–2276 | Cite as

Machine learning methods for estimation the indicators of phosphogypsum influence in soil

  • Maria A. PukalchikEmail author
  • Alexandr M. Katrutsa
  • Dmitry Shadrin
  • Vera A. Terekhova
  • Ivan V. Oseledets
Soils, Sec 2 • Global Change, Environ Risk Assess, Sustainable Land Use • Research Article

Abstract

Purpose

The full understanding of the effect of mineral waste-based fertilizer in soil is still unrelieved, because of the extreme complex chemical composition and plethora of their action pathways. The purposes of this paper is to quantify the input of PG into the soil ecosystem process, considering the direct effects of PG as a whole on soil environment using of a plethora of chemical, toxicological, and biological tests.

Materials and methods

Greenhouse experiment includes different PG doses (0, 1%, 3%, 7.5%, 15%, 25%, and 40%) and two-time collection points after treatments—7 and 28 days. For each treatment and each time collection point, we measure (i) soil pH, bioavailable (H20 and NH4COOH-extractable) element content (S, P, K, Na, Mg, Ca, Fe, Zn, Sr, Ba, F); (ii) soil enzyme activities—dehydrogenase, urease, acid phosphatase, FDA; (iii) soil CO2 respiration activity with and without glucose addition; (iv) Eisenia fetida, Sinapis alba, and Avena sativa responses. Finally, we combine the ordinary chemical, toxicology, and biological measuring of soil properties with state-of-the-art mathematical analysis, namely (i) support vector machines (used for prediction), (ii) mutual information test (variable importance tasks), (iii) t-SNE and LLE algorithms (used for unsupervised classification).

Results and discussion

The results show similarity between the 0%, 1%, and 3% PG treatments in all collection times based on the toxicological and biological properties. Beyond 7.5% PG, some biological test was significantly inhibited in response to trace element stress. Among all tested parameters, soil urease activities, soil respiration activities after glucose addition, S. alba root lengths, and E. fetida survival rates show sensitivity to PG addition. Furthermore, the machine learning algorithms revealed that only several elements (mobile and water-soluble forms of Ca, Ba, Sr, S, and Na; water-soluble F) could be responsible to elevated soil toxicity for those indicators. SVR models were able to predict soil biological and ecotoxicity properties, and increasing numbers of randomly selected training examples from 50 to 90% of initial experimental data significantly improved model performance.

Conclusions

At this study, we demonstrate benefits of unsupervised machine learning methods for investigating toxicity of man-made substances in soil that can be further applied to risk assessments of various toxins, which are of significant interest to environmental protection.

Keywords

Bioassay Biological properties Feature relevance Machine learning Pollution Regression Soil Trace element Waste 

Notes

Acknowledgments

The research was supported by the Skoltech Next Generation Program and the Russian Found of Basic Research (Project No. 16-34-00063 mol_a). We are grateful to Anastasia Sharapkova (Rosetta Stone MSU) for proofreading the final version of the manuscript.

Supplementary material

11368_2019_2253_MOESM1_ESM.xlsx (40 kb)
ESM 1 (XLSX 40 kb)

References

  1. Al-Hwaiti M, Al-Khashman O (2015) Health risk assessment of heavy metals contamination in tomato and green pepper plants grown in soils amended with phosphogypsum waste materials. Environ Geochem Health 37:287–304CrossRefGoogle Scholar
  2. Alvarenga P, Clemente R, Garbisu C, Becerril JM (2018) Indicators for monitoring mine site rehabilitation. In: Bio-Geotechnologies for Mine Site Rehabilitation. Elsevier, pp 49–66Google Scholar
  3. Ascari JP, Mendes IRN (2018) Desenvolvimento agronômico e produtivo da soja sob diferentes doses de gesso agrícola. Revista Agrogeoambiental 9Google Scholar
  4. Ayadi A, Chorriba A, Fourati A, Gargouri-Bouzid R (2015) Investigation of the effect of phosphogypsum amendment on two Arabidopsis thaliana ecotype growth and development. Environ Technol 36:1547–1555CrossRefGoogle Scholar
  5. Blum SC, Caires EF, Alleoni LRF (2013) Lime and phosphogypsum application and sulfate retention in subtropical soils under no-till system. J Soil Sci Plant Nutr 13(2):279–300Google Scholar
  6. Boluda R, Roca-Pérez L, Marimón L (2011) Soil plate bioassay: an effective method to determine ecotoxicological risks. Chemosphere 84:1–8CrossRefGoogle Scholar
  7. Bouma J (2014) Soil science contributions towards sustainable development goals and their implementation: linking soil functions with ecosystem services. J Plant Nutri Soil Sci 177(2):111–120CrossRefGoogle Scholar
  8. Bünemann EK, Bongiorno G, Bai Z, Creamer RE, De Deyn G, de Goede R, Fleskens L, Geissen V, Kuyper TW, Mäder P, Pulleman M, Sukkel W, van Groenigen JW, Brussaard L (2018) Soil quality – a critical review. Soil Biol Biochem 120:105–125CrossRefGoogle Scholar
  9. Bunte K, Biehl M, Hammer B (2012) A general framework for dimensionality reducing data visualization mapping. Neural Comp 24(3):771–804CrossRefGoogle Scholar
  10. Burns RG, DeForest JL, Marxsen J, Sinsabaugh RL, Stromberger ME, Wallenstein MD, Weintraub MN, Zoppini A (2013) Soil enzymes in a changing environment: Current knowledge and future directions. Soil Biol Biochem 58:216–234CrossRefGoogle Scholar
  11. Caldwell BA (2005) Enzyme activities as a component of soil biodiversity: a review. Pedobiologia 49(6):637–644CrossRefGoogle Scholar
  12. Carmeis Filho ACA, Penn CJ, Crusciol CAC, Calonego JC (2017) Lime and phosphogypsum impacts on soil organic matter pools in a tropical Oxisol under long-term no-till conditions. Agr Ecosyst Environ 241:11–23CrossRefGoogle Scholar
  13. Chae Y, Kim D, An YJ (2018) Effects of fluorine on crops, soil exoenzyme activities, and earthworms in terrestrial ecosystems. Ecotoxicol Environ Saf 151:21–27CrossRefGoogle Scholar
  14. Chaudhari MS (2016) Acute toxicity of diammonium phosphate to earthworm (Eudrilus eugeniae). J Entomol Zool Stud 4(6):501–503Google Scholar
  15. Cheng Z, Lee L, Dayan S, Grinshtein M, Shaw R (2011) Speciation of heavy metals in garden soils: evidences from selective and sequential chemical leaching. J Soils Sediments 11:628–638CrossRefGoogle Scholar
  16. Cipullo S, Snapira D, Prpich G, Campo P, Coulona F (2019) Prediction of bioavailability and toxicity of complex chemical mixtures through machine learning models. Chemosphere 215:388–395CrossRefGoogle Scholar
  17. Cui X, Wang XD, Fan WH, Wang JM, Cui KY (2011) Effects of fluoride on soil properties and yield and quality of maize. Chin J Eco-Agric 19(4):897–901CrossRefGoogle Scholar
  18. Delgado A, Madrid A, Kassem S, Andre L, del Carmen del Campillo M (2002) Phosphorus fertilizer recovery from calcareous soils amended with humic and fulvic acids. Plant Soil 2:277–286CrossRefGoogle Scholar
  19. Deng J, Chen X, Wang R et al (2017) LS-SVM data mining analysis: how does biochar influence soil net nitrogen mineralization in the field? J Soils Sediments 17(3):827–840CrossRefGoogle Scholar
  20. Eivazi F, Tabatabai MA (1977) Phosphatases in soils. Soil Biol Biochem 9:167–172CrossRefGoogle Scholar
  21. Elloumi N, Zouari M, Chaari L, Abdallah FB, Woodward S, Kallel M (2015) Effect of phosphogypsum on growth, physiology, and the antioxidative defense system in sunflower seedlings. Environ Sci Pollut Res 22:14829–14840CrossRefGoogle Scholar
  22. Fox DR (2015) Selection bias correction for species sensitivity distribution modeling and hazardous concentration estimation: correction for SSD modeling. Environ Toxicol Chem 34:2555–2563CrossRefGoogle Scholar
  23. Gisbrecht A, Hammer B (2015) Data visualization by nonlinear dimensionality reduction. Wiley Interdiscip Rev Data Min Knowl Discov 5(2):51–73CrossRefGoogle Scholar
  24. Haney RL, Franzluebbers AJ (2009) Soil CO2 evolution: response from arginine additions. Appl Soil Ecol 42:324–327CrossRefGoogle Scholar
  25. Hentati O, Abrantes N, Caetano AL, Bouguerra S, Gonçalves F, Römbke J, Pereira R (2015) Phosphogypsum as a soil fertilizer: ecotoxicity of amended soil and elutriates to bacteria, invertebrates, algae and plants. J Hazard Mater 294:80–89CrossRefGoogle Scholar
  26. Hurtado MD, Enamorado SM, Andreu L, Delgado A, Abril JM (2011) Drain flow and related salt losses as affected by phosphogypsum amendment in reclaimed marsh soils from SW Spain. Geoderma 161:43–49CrossRefGoogle Scholar
  27. Inbar Y, Boehm MJ, Hoitink HJ (1991) Hydrolysis of fluorescein diacetate in sphagnum peat container media for predicting suppressiveness to damping-off caused by Pythium ultimum. Soil Biol Biochem 23:479–483CrossRefGoogle Scholar
  28. International Atomic Energy Agency Report (2013) Radiation protection and management of norm residues in the phosphate industry. 308 P. https://www-pub.iaea.org/MTCD/Publications/PDF/Pub1582_web.pdf. checked 19.11.2018
  29. ISO 14240-1:1 (1997) Soil quality - determination of soil microbial biomass - Part 1: substrate-induced respiration methodGoogle Scholar
  30. ISO 16072 (2002) Soil quality - laboratory methods for determination of microbial soil respirationGoogle Scholar
  31. ISO 19204 (2017) Soil quality - procedure for site-specific ecological risk assessment of soil contamination (soil quality TRIAD approach)Google Scholar
  32. Jager T (2011) Some Good Reasons to ban EC x and related concepts in ecotoxicology. Environ Sci Technol 45:8180–8181CrossRefGoogle Scholar
  33. Kammoun M, Ghorbel I, Charfeddine S, Kamoun L, Gargouri-Bouzid R, Nouri-Ellouz O (2017) The positive effect of phosphogypsum-supplemented composts on potato plant growth in the field and tuber yield. J Environ Manag 200:475–483CrossRefGoogle Scholar
  34. Klose S, Tabatabai M (2000) Urease activity of microbial biomass in soils as affected by cropping systems. Biol Fertil Soils 31:191–199CrossRefGoogle Scholar
  35. Konarbaeva G (1997) Fluorine in the crusty solonetzes of Western Siberia and the impact of phosphogypsum on its content. Eurasian Soil Sci 30:977–981Google Scholar
  36. Kraskov A, Stögbauer H, Grassberger P (2004) Estimating mutual information. Phys Rev E 69.  https://doi.org/10.1103/PhysRevE.69.066138
  37. Li H, Leng W, Zhou Y, Chen F, Xiu Z, Yang D (2014) Evaluation models for soil nutrient based on support vector machine and artificial neural networks. Sci World J 478569:7.  https://doi.org/10.1155/2014/478569 CrossRefGoogle Scholar
  38. Liu Z, Rong Q, Zhou W, Liang G (2017) Effects of inorganic and organic amendment on soil chemical properties, enzyme activities, microbial community and soil quality in yellow clayey soil. PLOS One 12.  https://doi.org/10.1371/journal.pone.0172767
  39. Liu J, Liu M, Wu M et al (2018) Soil pH rather than nutrients drive changes in microbial community following long-term fertilization in acidic Ultisols of southern China. J Soils Sediments 18:1853–1864CrossRefGoogle Scholar
  40. Maaten LVD, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Res 9:2579–2605Google Scholar
  41. McBride M (1989) Reactions controlling heavy metal solubility in soils. Adv Soil Sci 26:1–56Google Scholar
  42. Morgado RG, Loureiro S, González-Alcaraz MN (2018) Changes in Soil Ecosystem Structure and Functions Due to Soil Contamination. Soil Pollution. Elsevier, pp 59–87Google Scholar
  43. Morgan JE, Morgan AJ (1988) Calcium-lead interactions involving earthworms. Part 2: The effect of accumulated lead on endogenous calcium in Lumbricus rubellus. Environ Pollut 55(1):41–54CrossRefGoogle Scholar
  44. Negrão S, Schmöckel SM, Tester M (2017) Evaluating physiological responses of plants to salinity stress. Ann Bot 119(1):1–11CrossRefGoogle Scholar
  45. Niell S, Jesús F, Díaz R, Mendoza Y, Notte G, Santos E, Gérez N, Cesio V, Cancela H, Heinzen H (2018) Beehives biomonitor pesticides in agroecosystems: simple chemical and biological indicators evaluation using Support Vector Machines (SVM). Ecol Ind 91:149–154CrossRefGoogle Scholar
  46. Nikolaeva OV, Terekhova VA (2017) Improvement of laboratory phytotest for the ecological evaluation of soils. Eurasian Soil Sci 50:1105–1114CrossRefGoogle Scholar
  47. OECD Guideline for testing chemicals 222 (2004). Earthworm reproduction test (Eisenia fetida/Eisenia andrei)Google Scholar
  48. Palmer DS, Mišin M, Fedorov MV, Llinas A (2015) Fast and general method to predict the physicochemical properties of druglike molecules using the integral equation theory of molecular liquids. Mol Pharm 12:3420–3432CrossRefGoogle Scholar
  49. Pan Y, Koopmans GF, Bonten LTC et al (2014) Influence of pH on the redox chemistry of metal (hydr)oxides and organic matter in paddy soils. J Soils Sediments 14:1713–1726CrossRefGoogle Scholar
  50. Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blindel M, Prettenhofer P, Wiess R, Dubourg V et al (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825–2830Google Scholar
  51. Pereira R, Cachada A, Sousa JP, Niemeyer J, Markwiese J, Andersen CP (2018) Ecotoxicological effects and risk assessment of pollutants. Soil Pollution. Elsevier, pp 91–216Google Scholar
  52. Pickering WF (1985) The mobility of soluble fluoride in soils. Environ Pollut Series B 9:281–308CrossRefGoogle Scholar
  53. Reinwarth B, Miller JK, Glotzbach C et al (2017) Applying regularized logistic regression (RLR) for the discrimination of sediment facies in reservoirs based on composite fingerprints. J Soils Sediments 17(6):1777–1795CrossRefGoogle Scholar
  54. Rodríguez-Pérez R, Vogt M, Bajorath J (2017) Influence of varying training set composition and size on support vector machine-based prediction of active compounds. J Chem Inf Model 57(4):710–716.  https://doi.org/10.1021/acs.jcim.7b00088 CrossRefGoogle Scholar
  55. Roweis ST, Saul L (2000) Nonlinear dimensionality reduction by locally linear embedding. Science 290:2323–2326.  https://doi.org/10.1126/science.290.5500.2323 CrossRefGoogle Scholar
  56. Russian National Report (2015) On the state and protection of the environment issued annually by the Ministry of Natural Resources and Environment (in Russian)Google Scholar
  57. Saadaoui E, Ghazel N, Ben Romdhane C, Massoudi N (2017) Phosphogypsum: potential uses and problems – a review. Int J Environ Studies 74:558–567CrossRefGoogle Scholar
  58. Saha JK, Kundu S (2003) Determination of fluoride in soil water extract through ion chromatography. Commun Soil Sci Plant Anal 34:181–188CrossRefGoogle Scholar
  59. Shatar TM, Mcbratney AB (2004) Boundary-line analysis of field-scale yield response to soil properties. J Agric Sci 142:553–560CrossRefGoogle Scholar
  60. Tabatabai MA (1977) Effects of trace elements on urease activity in soils. Soil Biol Biochem 9(1):9–13CrossRefGoogle Scholar
  61. Tayibi H, Choura M, López FA, Alguacil FJ, López-Delgado A (2009) Environmental impact and management of phosphogypsum. J Environ Manag 90:2377–2386CrossRefGoogle Scholar
  62. Telesiński A, Siwczyk F, Zakrzewska H (2012) An attempt to determination of the 50% phytotoxicity threshold for different fluoride concentrations affecting the spring wheat (Triticum aestivum L.) and white mustard (Sinapis alba L.) seedlings. Fluoride 45(3/1):213–214Google Scholar
  63. Thalmann A (1968) Zur methodic derestimung der. Dehydrogenaseaktivität i. Boden mittels. Triphenyltetrazoliumchlorid (TTC). Landwirdschaft. Forschung 21:249–258Google Scholar
  64. Twarakavi NCK, Šimůnek J, Schaap MG (2009) Development of pedotransfer functions for estimation of soil hydraulic parameters using support vector machines. Soil Sci Soc Am J 73(5):1443–1452CrossRefGoogle Scholar
  65. Vapnik VN (1995) The nature of statistical learning theory. Springer, New YorkCrossRefGoogle Scholar
  66. Vapnik VN, Golowich S, Smola A (1997) Support vector method for function approximation, regression estimation, and signal processing. In: Mozer MC, Jordan MI, Petsche T (eds) Advances in neural information processing systems, vol 9. MIT Press, Cambridge, pp 281–287Google Scholar
  67. Vyshpolsky F, Mukhamedjanov K, Bekbaev U, Ibatullin S, Yuldashev T, Noble AD, Mirzabaev A, Aw-Hassan A, Qadir M (2010) Optimizing the rate and timing of phosphogypsum application to magnesium-affected soils for crop yield and water productivity enhancement. Agric Water Manag 97:1277–1286.  https://doi.org/10.1016/j.agwat.2010.02.020 CrossRefGoogle Scholar
  68. Wu CH, Ho JM, Lee DT (2004) Travel time prediction with support vector regression. IEEE Trans Intell Transp Syst 5(4):276–281CrossRefGoogle Scholar
  69. Yakovlev AS, Kaniskin MA, Terekhova VA (2013) Ecological evaluation of artificial soils treated with phosphogypsum. Eurasian Soil Sci 46:697–703CrossRefGoogle Scholar
  70. Zaman AU (2014) Identification of key assessment indicators of the zero waste management systems. Ecol Ind 36:682–693CrossRefGoogle Scholar
  71. Zhu J, Wang J, Ding Y, Liu B, Xiao W (2018) A systems-level approach for investigating organophosphorus pesticide toxicity. Ecotox Environ Saf 149:26–35Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Skolkovo Institute of Science and TechnologyMoscowRussia
  2. 2.A.N. Severtsov Institute of Ecology and EvolutionRussian Academy of SciencesMoscowRussia
  3. 3.M.V. Lomonosov Moscow State UniversityMoscowRussia

Personalised recommendations