Skip to main content

Advertisement

SpringerLink
Log in

Comparison of Cubist models for soil organic carbon prediction via portable XRF measured data

  • Published:
Environmental Monitoring and Assessment Aims and scope Submit manuscript

Abstract

Soil organic carbon (SOC) tends to form complexes with most metallic ions within the soil system. Relatively few studies compare SOC predictions via portable X-ray fluorescence (pXRF) measured data coupled with the Cubist algorithm. The current study applied three different Cubist models to estimate SOC while using several pXRF measured data. Soil samples (n = 158) were collected from the Litavka floodplain area during two separate sampling campaigns in 2018. Thirteen pXRF data or predictors (K, Ca, Rb, Mn, Fe, As, Ba, Th, Pb, Sr, Ti, Zr, and Zn) were selected to develop the proposed models. Validation and comparison of the models applied the mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R2). The results revealed that Cubist 1, utilizing all the predictors yielded the best model outcome (MAE = 0.51%, RMSE = 0.68%, R2 = 0.78) followed by Cubist 2, using predictors with relatively high importance (VarImp. predictors) (MAE = 0.64%, RMSE = 0.82%, R2 = 0.68), and lastly Cubist 3 with predictors showing a significantly positive correlation (MAE = 0.69%, RMSE = 0.90%, R2 = 0.62). The Cubist 1 model was considered more promising for explaining the complex relationships between SOC and the pXRF data used. Moreover, for the estimation of SOC in temperate floodplain soils all the Cubist models gave an acceptable model. However, future research should focus on using other auxiliary data [e.g., soil properties, data from other sensors (e.g., FieldSpec)] as well as extend the study area to cover more soil types hence improve model robustness as well as parsimoniousness.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  • Adhikari, K., Hartemink, A.E. (2016). Linking soils to ecosystem services — a global review Geoderma, 262:101–111.

  • Agyeman, P.C., Ahado, S.K., Kingsley, J., Kebonye, N.M., Biney, J.K.M., Borůvka, L., Vasat, R., & Kocarek, M. (2020). Source apportionment, contamination levels, and spatial prediction of potentially toxic elements in selected soils of the Czech Republic. Environmental Geochemistry and Health,1–20.

  • Andersson, S., Nilsson, I., & Valeur, I. (1999). Influence of dolomitic lime on DOC and DON leaching in a forest soil. Biogeochemistry, 47(3), 295–315.

    Article  Google Scholar 

  • Appelhans, T., Mwangomo, E., Hardy, D. R., Hemp, A., & Nauss, T. (2015). Evaluating machine learning approaches for the interpolation of monthly air temperature at Mt. Kilimanjaro. Tanzania. Spatial Statistics, 14, 91–113.

    Article  Google Scholar 

  • Basile-Doelsch, I., Brun, T., Borschneck, D., Masion, A., Marol, C., & Balesdent, J. (2009). Effect of landuse on organic matter stabilized in organomineral complexes: a study combining density fractionation, mineralogy and δ13C. Geoderma, 151(3), 77–86.

    Article  CAS  Google Scholar 

  • Batty, M., & Torrens, P. M. (2005). Modelling and prediction in a complex world. Futures, 37(7), 745–766.

    Article  Google Scholar 

  • Bhunia, G. S., Shit, P. K., & Maiti, R. (2018). Comparison of GIS-based interpolation methods for spatial distribution of soil organic carbon (SOC). Journal of theSaudi Society of Agricultural Sciences, 17(2), 114–126.

  • Borůvka, L., & Drábek, O. (2004). Heavy metal distribution between fractions of humic substances in heavily polluted soils. Plant, Soil and Environment, 50, 339–345.

    Article  Google Scholar 

  • Borůvka, L., & Vácha, R. (2006). Litavka river alluvium as a model area heavily polluted with potentially risk elements. In Morel, J.-L., Echevarria, G., Goncharova, N. (eds.): Phytoremediation of metal-contaminated soils (pp267–298). Springer, Dordrecht.

  • Borůvka, L., Huan-Wei, C., Kozák, J., & Krištoufková, S. (1996). Heavy contamination of soil with cadmium, lead and zinc in the alluvium of the Litavka River. Rostlinná Výroba, 42, 543–550.

    Google Scholar 

  • Cardelli, V., Weindorf, D. C., Chakraborty, S., Li, B., De Feudis, M., Cocco, S., & Corti, G. (2017). Non-saturated soil organic horizon characterization via advanced proximal sensors. Geoderma, 288, 130–142.

    Article  CAS  Google Scholar 

  • Chan, K. Y., & Heenan, D. P. (1999). Lime-induced loss of soil organic carbon and effect on aggregate stability. Soil Science Society of America Journal, 63(6), 1841–1844.

    Article  CAS  Google Scholar 

  • Clough, A., & Skjemstad, J. O. (2000). Physical and chemical protection of soil organic carbon in three agricultural soils with different contents of calcium carbonate. Australian Journal of Soil Research, 38(5), 1005–1016.

    Article  CAS  Google Scholar 

  • Dakora, F. D., & Phillips, D. A. (2002). Root exudates as mediators of mineral acquisition in low-nutrient environments. Food security in nutrient-stressed environments: exploiting plants’ genetic capabilities. Plant and Soil, 245, 35–47.

    Article  CAS  Google Scholar 

  • Dengiz, O., & Başkan, O. (2010). Characterization of soil profile development on different landscape in semi-arid region of Turkey A case study; Ankara-Soğulca Catchment. Anadolu J Agric Sci, 25, 106–112.

    Google Scholar 

  • dos Santos Teixeira, A. F., Pelegrino, M. H. P., Faria, W. M., Silva, S. H. G., Gonçalves, M. G. M., Júnior, F. W. A., et al. (2020). Tropical soil pH and sorption complex prediction via portable X-ray fluorescence spectrometry. Geoderma, 361, 114132.

    Article  Google Scholar 

  • Duchaufour, R. (1982). Pedology: pedogenesis and classification. Springer, Dordrecht.

  • Duda, B. M., Weindorf, D. C., Chakraborty, S., Li, B., Man, T., Paulette, L., & Deb, S. (2017). Soil characterization across catenas via advanced proximal sensors. Geoderma, 298, 78–91.

    Article  CAS  Google Scholar 

  • Environmental Protection Agency (EPA). (2010). Method 6200: Field portable X-ray fluorescence spectrometry for the determination of elemental concentrations in soil and sediment [online]. Available at http://www.epa.gov/. (Verified 27 May 2020).

  • Ettler, V., Mihaljevič, M., & Komárek, M. (2004). ICP-MS measurements of lead isotopic ratios in soils heavily contaminated by lead smelting: tracing the sources of pollution. Analytical and Bioanalytical Chemistry, 378, 311–317.

    Article  CAS  Google Scholar 

  • Gomes, L. C., Faria, R. M., de Souza, E., Veloso, G. V., Schaefer, C. E. G., & Fernandes Filho, E. I. (2019). Modelling and mapping soil organic carbon stocks in Brazil. Geoderma, 340, 337–350.

    Article  CAS  Google Scholar 

  • Giacalone, A., Gianguzza, A., Orecchio, S., Piazzese, D., Dongarrà, G., Sciarrino, S., & Varrica, D. (2005). Metals distribution in the organic and inorganic fractions of soil: a case study on soils from Sicily Chem. Speciat. Bioavailab., 17, 83–93.

    Article  CAS  Google Scholar 

  • Gröngröft, A., Krüger, F., Grunewald, K., Meißner, R., & G,. (2005). Miehlich Plant and soil contamination with trace metals in the Elbe floodplains: a case study after the flood in August 2002 Acta Hydrochim. Hydrobiol., 33, 466–474.

    Google Scholar 

  • Gray, J. M., Bishop, T. F. A., & Yang, X. (2015). Pragmatic models for the prediction and digital mapping of soil properties in eastern Australia. Soil Research, 53(1), 24.

    Article  Google Scholar 

  • Hengl, T., Heuvelink, G. B., Kempen, B., Leenaars, J. G., Walsh, M. G., Shepherd, K. D., et al. (2015). Mapping soil properties of Africa at 250m resolution: random forests significantly improve current predictions. PLoS One, 10(6), e0125814.

    Article  Google Scholar 

  • Hounkpatin, O. K. L., Op de Hipt, F., Bossa, A. Y., Welp, G., & Amelung, W. (2018). Soil organic carbon stocks and their determining factors in the Dano catchment (Southwest Burkina Faso). CATENA, 166, 298–309.

    Article  CAS  Google Scholar 

  • Kabata-Pendias, A. (2011). Trace elements in soils and plants (4th ed.pp. 33487–32742). 6000 Broken Sound Parkway N.W., Suite 300. Boca Raton: CRC Press. Taylor and Francis Group.

  • Kebonye, N. M., & Eze, P. N. (2019). Zirconium as a suitable reference element for estimating potentially toxic element enrichment in treated wastewater discharge vicinity. Environmental Monitoring and Assessment, 191(11), 705.

    Article  CAS  Google Scholar 

  • Kebonye, N. M., Eze, P. N., & Akinyemi, F. O. (2017). Long term treated wastewater impacts and source identification of heavy metals in semi-arid soils of Central Botswana. Geoderma Regional, 10, 200–214.

    Article  Google Scholar 

  • Kebonye, N.M., Eze, P.N., Ahado, S.K., & John, K. (2020). Structural equation modeling of the interactions between trace elements and soil organic matter in semiarid soils. International Journal of Environmental Science and Technology, 1–10.

  • Kebonye, N. M., John, K., Chakraborty, S., Agyeman, P. C., Ahado, S. K., Eze, P. N., et al. (2021). Comparison of multivariate methods for arsenic estimation and mapping in floodplain soil via portable X-ray fluorescence spectroscopy. Geoderma, 384, 114792.

    Article  Google Scholar 

  • Kotková, K., Nováková, T., Tůmová, Š, Kiss, T., Popelka, J., & Faměra, M. (2019). Migration of risk elements within the floodplain of the Litavka River, the Czech Republic. Geomorphology, 329, 46–57.

    Article  Google Scholar 

  • Kuhn, M., Weston, S., Keefer, C., Coulter, N., Quinlan, R. (2014). Cubist: rule-and instance based regression modeling, R package version 0.0.18; CRAN: Vienna, Austria.

  • Li, L., Lu, J., Wang, S., Ma, Y., Wei, Q., Li, X., et al. (2016). Methods for estimating leaf nitrogen concentration of winter oilseed rape (Brassica napus L.) using in situ leaf spectroscopy. Industrial Crops and Products, 91, 194–204.

    Article  CAS  Google Scholar 

  • Mandal, N., Dwivedi, B. S., Meena, M. C., Singh, D., Datta, S. P., Tomar, R. K., & Sharma, B. M. (2013). Effect of induced defoliation in pigeonpea, farmyard manure and sulphitation pressmud on soil organic carbon fractions, mineral nitrogen and crop yields in a pigeonpea–wheat cropping system. Field Crops Research, 154, 178–187.

    Article  Google Scholar 

  • Margon, A., Mondini, C., Valentini, M., Ritota, M., & Leita, L. (2013). Soil microbial biomass influence on strontium availability in mine soil. Chemical Speciation and Bioavailability, 25(2), 119–124.

    Article  CAS  Google Scholar 

  • Mikutta, R., Mikutta, C., Kalbitz, K., Scheel, T., Kaiser, K., & Jahn, R. (2007). Biodegradation of forest floor organic matter bound to minerals via different binding mechanisms. Geochimica et Cosmochimica Acta, 71(10), 2569–2590.

    Article  CAS  Google Scholar 

  • Oades, J. M. (1988). The retention of organic matter in soils. Biogeochemistry, 5(1), 35–70.

    Article  CAS  Google Scholar 

  • O’Rourke, S. M., Minasny, B., Holden, N. M., & McBratney, A. B. (2016). Synergistic use of Vis-NIR, MIR, and XRF spectroscopy for the determination of soil geochemistry. Soil Science Society of America Journal, 80, 888–899.

    Article  CAS  Google Scholar 

  • O’Rourke, S. M., Stockmann, U., Holden, N. M., McBratney, A. B., & Minasny, B. (2016). An assessment of model averaging to improve predictive power of portable vis-NIR and XRF for the determination of agronomic soil properties. Geoderma, 279, 31–44.

    Article  CAS  Google Scholar 

  • Ottoy, S., De Vos, B., Sindayihebura, A., Hermy, M., & Van Orshoven, J. (2017). Assessing soil organic carbon stocks under current and potential forest cover using digital soil mapping and spatial generalization. Ecological Indicators, 77, 139–150.

    Article  CAS  Google Scholar 

  • Quinlan, R. (1992). Learning with continuous classes. In Proceedings of the 5th Australian Joint Conference on Artificial Intelligence, Hobart, Australia, 16–18 November, pp. 343–348.

  • R Core Team. (2019). R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing. Vienna, Austria. [online]. Available at https://www.r-project.org/. (Verified 13 May 2020).

  • Ravansari, R., Wilson, S. C., & Tighe, M. (2020). Portable X-ray fluorescence for environmental assessment of soils: not just a point and shoot method. Environment International, 134, 105250.

    Article  CAS  Google Scholar 

  • Rossel, R. V., Brus, D., Lobsey, C., Shi, Z., & McLachlan, G. (2016). Baseline estimates of soil organic carbon by proximal sensing: comparing design-based, model-assisted and model-based inference. Geoderma, 265, 152–163.

    Article  Google Scholar 

  • Rowley, M. C., Grand, S., & Verrecchia, É. P. (2018). Calcium-mediated stabilization of soil organic carbon. Biogeochemistry, 137(1–2), 27–49.

    Article  CAS  Google Scholar 

  • Rudiyanto, M., & B., Setiawan, B.I., Saptomo, S.K., McBratney, A.B. (2018). Open digital mapping as a cost-effective method for mapping peat thickness and assessing the carbon stock of tropical peatlands. Geoderma, 313, 25–40.

    Article  CAS  Google Scholar 

  • Sevastas, S., Gasparatos, D., Botsis, D., Siarkos, I., Diamantaras, K. I., & Bilas, G. (2018). Predicting bulk density using pedotransfer functions for soils in the Upper Anthemountas basin. Greece. Geoderma Regional, 14, e00169.

    Article  Google Scholar 

  • Sherene T (2010). Mobility and transport of heavy metals in polluted soil environment. Biol. Forum—An Int. J., 2:112–121.

  • Sharma, A., Weindorf, D. C., Man, T., Aldabaa, A. A., & A., Chakraborty, S. (2014). Characterizing soils via portable X-ray fluorescence spectrometer: 3. Soil reaction (pH). Geoderma, 232–234, 141–147.

    Article  Google Scholar 

  • Sharma, A., Weindorf, D. C., Wang, D., & Chakraborty, S. (2015). Characterizing soils via portable X-ray fluorescence spectrometer: 4. Cation exchange capacity (CEC). Geoderma, 239, 130–134.

    Article  Google Scholar 

  • Sokoloff, V. P. (1938). Effect of neutral salts of sodium and calcium on carbon and nitrogen of soils. Journal of Agricultural Research, 57, 0201–0216.

    CAS  Google Scholar 

  • Tan, Z. X., Lal, R., Smeck, N. E., & Calhoun, F. G. (2004). Relationships between surface soil organic carbon pool and site variables. Geoderma, 121, 187–195.

    Article  CAS  Google Scholar 

  • Thirukkumaran., C.M., & Morrison., I.K. 1996 Impact of simulated acid rain on microbial respiration, biomass, and metabolic quotient in a mature sugar maple (Acer Saccharum) forest floor Canadian Journal of Forest Research 26 8 1446 1453

    Article  Google Scholar 

  • Vaněk, V., Balík, J., Šilha, J., & Černý, J. (2008). Spatial variability of total soil nitrogen and sulphur content at two conventionally managed fields. Plant, Soil and Environment, 54(10), 413-419.

  • Viscarra-Rossel, R. A., & Behrens, T. (2010). Using data mining to model and interpret soil diffuse reflectance spectra. Geoderma, 158, 46–54.

    Article  Google Scholar 

  • Walkley, A., & Black, I. A. (1934). An examination of the Degtjareff method for determining soil organic matter, and a proposed modification of the chromic acid titration method. Soil Science, 37, 29–38.

    Article  CAS  Google Scholar 

  • Walton, J. T. (2008). Subpixel urban land cover estimation. Photogrammetric Engineering & Remote Sensing, 74(10), 1213–1222.

    Article  Google Scholar 

  • Wang, B., Waters, C., Orgill, S., Gray, J., Cowie, A., Clark, A., & Li Liu, D. (2018). High resolution mapping of soil organic carbon stocks using remote sensing variables in the semi-arid rangelands of eastern Australia. Science of the Total Environment, 630, 367–378.

    Article  CAS  Google Scholar 

  • Wang, D., Chakraborty, S., Weindorf, D. C., Li, B., Sharma, A., Paul, S., & Ali, M. N. (2015). Synthesized use of VisNIR DRS and PXRF for soil characterization: total carbon and total nitrogen. Geoderma, 243–244, 157–167.

    Article  Google Scholar 

  • Wang, Y., & Witten, I. (1997). Inducing model trees for continuous classes. Proceedings of the Ninth European Conference on Machine Learning, Prague, Czech Republic, 23–25, 128–137.

    Google Scholar 

  • Wang, Y. Q., & Shao, M. A. (2013). Spatial variability of soil physica lproperties in a region of the Loess Plateau of PR China subject towind and water erosion. Land Degradation and Development, 24(3), 296–304.

    Article  Google Scholar 

  • Weindorf, D. C., & Chakraborty, S. (2016). Portable X-ray Fluorescence Spectrometry Analysis of Soils. Methods of Soil Analysis, 1(1), 1–8.

    Article  Google Scholar 

  • Weindorf, D. C., Zhu, Y., Haggard, B., Lofton, J., Chakraborty, S., Bakr, N., et al. (2012). Enhanced pedon horizonation using portable x-ray fluorescence spectroscopy. Soil Science Society of America Journal, 76(2), 522–531.

    Article  CAS  Google Scholar 

  • Wilford, J., & Thomas, M. (2013). Predicting regolith thickness in the complex weathering setting of the central Mt Lofty Ranges, South Australia. Geoderma, 206, 1–13.

    Article  CAS  Google Scholar 

  • Xu, D., Chen, S., Xu, H., Wang, N., Zhou, Y., & Shi, Z. (2020). Data fusion for the measurement of potentially toxic elements in soil using portable spectrometers. Environmental Pollution, 114649.

  • Zhang, Y., & Hartemink, A. E. (2020). Data fusion of vis–NIR and PXRF spectra to predict soil physical and chemical properties. European Journal of Soil Science, 71(3), 316–333.

Download references

Funding

This study was supported by an internal PhD grant no. SV20-5-21130 of the Faculty of Agrobiology, Food and Natural Resources of the Czech University of Life Sciences Prague (CZU). Secondly, the Czech Science Foundation projects no. 17–277265 (Spatial prediction of soil properties and classes based on position in the landscape and other environmental covariates) and 18–28126Y (Soil contamination assessment using hyperspectral orbital data) for the financial support. Thirdly, the Centre of Excellence (Centre of the investigation of synthesis and transformation of nutritional substances in the food chain in interaction with potentially risk substances of anthropogenic origin: comprehensive assessment of the soil contamination risks for the quality of agricultural products, NutRisk Centre) and the European project no. CZ.02.1.01/0.0/0.0/16_019/0000845. Furthermore, the authors are grateful for the data provided by Professor Luboš Borůvka and Dr Asa Gholizadeh.

Author information

Authors and Affiliations

  1. Department of Soil Science and Soil Protection, Faculty of Agrobiology, Food and Natural Resources, Czech University of Life Sciences Prague, Kamýcká 129, 165 00, Prague – Suchdol, Czech Republic

    Kingsley John, Ndiye M. Kebonye, Prince C. Agyeman & Samuel K. Ahado

Authors
  1. Kingsley John
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ndiye M. Kebonye
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Prince C. Agyeman
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Samuel K. Ahado
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Kingsley John.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Highlights

• We examined the influence of pXRF dataset and SOC estimation.

• SOC showed a significant correlation with Ca, Mn, Fe, Sr, Ba, and Thr.

• Ca2+ is easily attached to the SOC exchange site in a floodplain.

• The Cubist regression algorithm engaging all the predictors was more suitable for predicting SOC.

Supplementary Information

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

John, K., Kebonye, N.M., Agyeman, P.C. et al. Comparison of Cubist models for soil organic carbon prediction via portable XRF measured data. Environ Monit Assess 193, 197 (2021). https://doi.org/10.1007/s10661-021-08946-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s10661-021-08946-x

Keywords

Search

Navigation