Skip to main content

Advertisement

SpringerLink
Log in

Soil organic carbon prediction by multi-digital data fusion for nitrogen management in a sugarcane field

  • Original Article
  • Published:
Nutrient Cycling in Agroecosystems Aims and scope Submit manuscript

Abstract

In the sugarcane industry, the SIX EASY STEPS nutrient management guidelines were developed to recommend nitrogen (N) fertiliser rates based on soil organic carbon (SOC) content. In this study, various models of topsoil (0–0.3 m) SOC predictions were compared for digital soil mapping (DSM), including geostatistical models [e.g., multiple linear regression (MLR)] and their hybrid models which include regression residuals. Digital data including electromagnetic induction and gamma-ray (γ-ray) spectrometry are studied with different calibration (i.e., n = 165, 150, … , 15) and validation sites (i.e., n = 55). To reduce the SOC measurements, a visible-near infrared (Vis–NIR) library was developed from a number of calibration samples (i.e., n = 15, 30, …, 150) with the prediction of SOC on the remaining samples to the maximum (165). For the full dataset (165), all non-hybrid models produce Lin’s concordance correlation coefficient moderate agreement between predicted and measured SOC (0.65–0.80), and most hybrid models had a substantial agreement (> 0.80). As for the least calibration samples, only 75 were required to achieve near substantial agreement using the hybrid model of MLR. In comparison, only 60 SOC measurements are needed when using a Vis–NIR library to predict another 105 samples, which enable a substantial agreement. There was not much cost difference of N fertiliser application among different sample sizes, but DSM by using the hybrid model of MLR and 75 calibration samples will lead to around 36% cost reduction compared to average industry rate.

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

Similar content being viewed by others

References

  • Arshad M, Li N, Zhao D, Sefton M, Triantafilis J (2019) Comparing management zone maps to address infertility and sodicity in sugarcane fields. Soil Tillage Res 193:122–132

    Article  Google Scholar 

  • Arshad M, Zhao D, Khongnawang T, Triantafilis J (2021) A systematic evaluation of multisensor data and multivariate prediction methods for digitally mapping exchangeable cations: a case study in Australian sugarcane field. Geoderma Reg 25:e00400

    Article  Google Scholar 

  • Asabere SB, Zeppenfeld T, Nketia KA, Sauer D (2018) Urbanization leads to increases in pH, carbonate, and soil organic matter stocks of arable soils of Kumasi, Ghana (West Africa). Front Environ Sci 6:119

    Article  Google Scholar 

  • Bell MJ (2014) A review of nitrogen use efficiency in sugarcane

  • Bruce P, Bruce A, Gedeck P (2020). Practical statistics for data scientists: 50+ essential concepts using R and Python. O'Reilly Media

  • Calcino D, Schroeder B, Panitz J, Hurney A, Skocaj D, Wood A, Salter B (2018) Australian sugarcane nutrition manual

  • Clark RN, Rencz AN (1999) Spectroscopy of rocks and minerals, and principles of spectroscopy. Manual Remote Sens 3:3–58

    Google Scholar 

  • Coops NC, Waring RH, Hilker T (2012) Prediction of soil properties using a process-based forest growth model to match satellite-derived estimates of leaf area index. Remote Sens Environ 126:160–173

    Article  Google Scholar 

  • Dairy Australia (2013) Dairy soils and fertiliser manual Australian Nutrient Management Guidelines Department of Primary Industries, Victorian State Government, Melbourne, Victoria

  • Davies BE (1974) Loss-on-ignition as an estimate of soil organic matter. Soil Sci Soc Am J 38:150–151

    Article  Google Scholar 

  • Dierke C, Werban U (2013) Relationships between gamma-ray data and soil properties at an agricultural test site. Geoderma 199:90–98

    Article  CAS  Google Scholar 

  • Erdi-Krausz G, Matolin M, Minty B, Nicolet J, Reford W, Schetselaar E (2003) Guidelines for radioelement mapping using gamma ray spectrometry data: also as open access e-book. International Atomic Energy Agency (IAEA)

  • FAO (1998) World reference base for soil resources. Food and Agriculture Organizationof the United Nations, Rome

    Google Scholar 

  • Garcia-Tomillo A, Mirás-Avalos JM, Dafonte-Dafonte J, Paz-González A (2017) Estimating soil organic matter using interpolation methods with a electromagnetic induction sensor and topographic parameters: a case study in a humid region. Precision Agric 18:882–897

    Article  Google Scholar 

  • Software G (2022) Surfer 21 user’s guide Golden Software Inc Golden. CO, USA

  • Guo P, Li M, Luo W, Tang Q, Liu Z, Lin Z (2015) Digital mapping of soil organic matter for rubber plantation at regional scale: an application of random forest plus residuals kriging approach. Geoderma 237:49–59

    Article  Google Scholar 

  • Heung B, Ho HC, Zhang J, Knudby A, Bulmer CE, Schmidt MG (2016) An overview and comparison of machine-learning techniques for classification purposes in digital soil mapping. Geoderma 265:62–77

    Article  Google Scholar 

  • Huang J, Pedrera-Parrilla A, Vanderlinden K, Taguas E, Gómez J, Triantafilis J (2017) Potential to map depth-specific soil organic matter content across an olive grove using quasi-2d and quasi-3d inversion of DUALEM-21 data. CATENA 152:207–217

    Article  CAS  Google Scholar 

  • Isbell R (2016) The Australian soil classification. CSIRO publishing

  • JMP®, Version <1520> (2021) SAS Institute Inc, Cary, NC

  • Knadel M, Thomsen A, Schelde K, Greve MH (2015) Soil organic carbon and particle sizes mapping using vis–NIR, EC and temperature mobile sensor platform. Comput Electron Agric 114:134–144

    Article  Google Scholar 

  • Kitchin R, Thrift N (2009) International encyclopedia of human geography. Elsevier

    Google Scholar 

  • Lawrence I, Lin K (1989) A concordance correlation coefficient to evaluate reproducibility. Biometrics 255–268

  • Ma Y, Minasny B, Wu C (2017) Mapping key soil properties to support agricultural production in Eastern China. Geoderma Reg 10:144–153

    Article  Google Scholar 

  • Mahmood HS, Hoogmoed WB, van Henten EJ (2012) Sensor data fusion to predict multiple soil properties. Precision Agric 13:628–645

    Article  Google Scholar 

  • McBratney AB, Santos MM, Minasny B (2003) On digital soil mapping. Geoderma 117(1–2):3–52

    Article  Google Scholar 

  • McBride G (2005) A proposal for strength-of-agreement criteria for Lin’s concordance correlation coefficient. NIWA client report: HAM2005-062 45:307–310

  • Metelka V, Baratoux L, Jessell MW, Barth A, Ježek J, Naba S (2018) Automated regolith landform mapping using airborne geophysics and remote sensing data, Burkina Faso, West Africa. Remote Sens Environ 204:964–978

    Article  Google Scholar 

  • Minasny B, McBratney AB (2006) A conditioned Latin hypercube method for sampling in the presence of ancillary information. Comput Geosci 32:1378–1388

    Article  Google Scholar 

  • Moore DS, Kirkland S (2007) The basic practice of statistics. WH Freeman, New York

  • Priori S, Bianconi N, Fantappiè M, Pellegrini S, Ferrigno G, Guaitoli F, Costantini EA (2013) The potential of γ-ray spectroscopy for soil proximal survey in clayey soils. EQA-Int J Environ Q 11:29–38

    Google Scholar 

  • Priori S, Fantappiè M, Bianconi N, Ferrigno G, Pellegrini S, Costantini EA (2016) Field-scale mapping of soil carbon stock with limited sampling by coupling gamma-ray and vis-NIR spectroscopy. Soil Sci Soc Am J 80:954–964

    Article  CAS  Google Scholar 

  • Rayment GE, Lyons DJ (2011) Soil chemical methods: Australasia. CSIRO Publishing

  • Rinnan Å, Van Den Berg F, Engelsen SB (2009) Review of the most common pre-processing techniques for near-infrared spectra. TrAC Trends Anal Chem 28:1201–1222

    Article  CAS  Google Scholar 

  • Robertson G, Groffman P (2007) Nitrogen transformations. Soil Microbiol Ecol Biochem 10:341–364

    Article  Google Scholar 

  • Rossel RV, Behrens T (2010) Using data mining to model and interpret soil diffuse reflectance spectra. Geoderma 158:46–54

    Article  CAS  Google Scholar 

  • Rossel RV, McBratney A (1998) Soil chemical analytical accuracy and costs: implications from precision agriculture. Aust J Exp Agric 38:765–775

    Article  Google Scholar 

  • RStudioTeam (2015) RStudio: integrated development for R RStudio, Inc, Boston, MA. http://www.rstudio.com

  • Sahu B, Ghosh AK (2021) Deterministic and geostatistical models for predicting soil organic carbon in a 60 ha farm on Inceptisol in Varanasi. India Geoderma Regional 26:e00413

    Article  Google Scholar 

  • Savitzky A, Golay MJ (1964) Smoothing and differentiation of data by simplified least squares procedures. Anal Chem 36:1627–1639

    Article  CAS  Google Scholar 

  • Schroeder B, Hurney A, Wood A, Moody P, Allsopp P (2010) Concepts and value of the nitrogen guidelines contained in the Australian sugar industry’s ‘six easy steps’ nutrient management program. In: Proceedings of the international society of sugar cane technologists

  • Sheykhmousa M, Mahdianpari M, Ghanbari H, Mohammadimanesh F, Ghamisi P, Homayouni S (2020) Support vector machine versus random forest for remote sensing image classification: a meta-analysis and systematic review. IEEE J Sel Topics Appl Earth Observ Remote Sens 13:6308–6325

    Article  Google Scholar 

  • Sleutel S, De Neve S, Singier B, Hofman G (2007) Quantification of organic carbon in soils: a comparison of methodologies and assessment of the carbon content of organic matter. Commun Soil Sci Plant Anal 38:2647–2657

    Article  CAS  Google Scholar 

  • Tziachris P, Aschonitis V, Chatzistathis T, Papadopoulou M (2019) Assessment of spatial hybrid methods for predicting soil organic matter using DEM derivatives and soil parameters. CATENA 174:206–216

    Article  CAS  Google Scholar 

  • Vallis I, Keating B (1997) Uptake and loss of fertilizer and soil nitrogen in sugarcane crops. Proc Aust Soc Sugar Cane Tech

  • Wackernagel H (2003) Ordinary kriging. Multivariate geostatistics. Springer, pp 79–88

  • Wedepohl KH, Correns CW, Shaw DM, Turekian KK, Zemann J (1969) Vol. 2, part 5. elements La (57) to U (92). Handbook of geochemistry

  • Walkley A (1947) A critical examination of a rapid method for determining organic carbon in soils—effect of variations in digestion conditions and of inorganic soil constituents. Soil Sci 63:251–264

    Article  CAS  Google Scholar 

  • Wang J, Zhao D, Zare E, Sefton M, Triantafilis J (2022) Unravelling drivers of field-scale digital mapping of topsoil organic carbon and its implications for nitrogen practices. Comput Electron Agric 193:106640

    Article  Google Scholar 

  • Wang J, Zhao X, Zhao D, Triantafilis J (2021) Selecting optimal calibration samples using proximal sensing EM induction and γ-ray spectrometry data: an application to managing lime and magnesium in sugarcane growing soil. J Environ Manage 296:113357

    Article  CAS  PubMed  Google Scholar 

  • Wilson PR, Baker DE (1990) Soils and agricultural land suitability of the wet tropical west of North Queensland: Ingham area. Land Resources Bulletin-Queensland Department of Primary Industries (Australia)

  • Zhao X, Arshad M, Li N, Zare E, Triantafilis J (2020) Determination of the optimal mathematical model, sample size, digital data and transect spacing to map CEC (Cation exchange capacity) in a sugarcane field. Comput Electron Agric 173:105436

    Article  Google Scholar 

  • Zhao X, Wang J, Zhao D, Li N, Zare E, Triantafilis J (2019) Digital regolith mapping of clay across the Ashley irrigation area using electromagnetic induction data and inversion modelling. Geoderma 346:18–29

    Article  Google Scholar 

  • Zhao X, Zhao D, Wang J, Triantafilis J (2022). Soil organic carbon (SOC) prediction in Australian sugarcane fields using Vis–NIR spectroscopy with different model setting approaches. Geoderma Regional, e00566

Download references

Acknowledgements

The Australian Federal Government’s Sugar Research Australia (SRA) is acknowledged for the financial support to conduct the γ-ray and EM surveys, soil sampling, and laboratory analysis as part of project (2017/014) entitled "Seeing is believing: managing soil variability, improve crop yield and minimising off-site impacts in sugarcane using digital soil mapping". The first author acknowledges a University of New South Wales “University International Postgraduate Award (UIPA)” scholarship which supported his Ph.D. candidature. We also thank Luke Venables, Sam Lemari, and Dion Cawthorne who carried out the soil sampling, Michael Sefton, Rod Nielson from Herbert Cane Productivity Services Ltd., for technical support with proximal sensed digital data collection. We acknowledge farmers who provided unrestricted access to the study fields.

Author information

Authors and Affiliations

  1. School of Biological, Earth and Environmental Sciences, Faculty of Science, UNSW Sydney, Kensington, NSW, 2052, Australia

    Xueyu Zhao & Jie Wang

  2. Manaaki Whenua Landcare Research, PO Box 69040, Lincoln, 7640, New Zealand

    John Triantafilis

  3. Centre for Crop Science, Queensland Alliance for Agriculture and Food Innovation, The University of Queensland, Gatton, Australia

    Dongxue Zhao

Authors
  1. Xueyu Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jie Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Dongxue Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. John Triantafilis
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

X.Z.: Formal analysis, Visualisation, writing original draft. J.W.: Methodology. D.Z.: Methodology. J.T.: Supervision, Writing-review & editing.

Corresponding author

Correspondence to John Triantafilis.

Additional information

Publisher's Note

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

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 354 kb)

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhao, X., Wang, J., Zhao, D. et al. Soil organic carbon prediction by multi-digital data fusion for nitrogen management in a sugarcane field. Nutr Cycl Agroecosyst 127, 119–136 (2023). https://doi.org/10.1007/s10705-022-10233-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10705-022-10233-1

Keywords

Search

Navigation