Skip to main navigation menu Skip to main content Skip to site footer
Plant Science Today (PST)

Research Articles

Vol. 13 No. sp5 (2026): Recent Advances in Agriculture

Improving soil organic carbon prediction using visible and near infrared spectroscopy: A comparative evaluation of spectral preprocessing and modelling approaches under semi-arid conditions

DOI
https://doi.org/10.14719/pst.15142
Submitted
21 April 2026
Published
01-08-2026

Abstract

Accurate estimation of soil organic carbon (SOC) is essential for soil quality assessment, carbon management and sustainable agriculture, particularly in semi-arid regions characterised by high spatial variability. Visible and near infrared (Vis–NIR) spectroscopy has emerged as a rapid and non-destructive technique for SOC prediction; however, its performance is strongly influenced by spectral preprocessing and modelling approaches. Despite growing interest, systematic evaluation of preprocessing-model interactions for SOC prediction under semi-arid conditions in India remains limited. This study aimed to systematically evaluate the effect of different preprocessing techniques and modelling methods on SOC prediction using Vis-NIR spectral data from a semi-arid region of southern India. A total of 300 surface soil samples were collected and analysed for SOC using the Walkley–Black method. Spectral data (400–2400 nm) were preprocessed using raw spectra, Savitzky–Golay first and second derivatives (SG-1D and SG-2D), multiplicative scatter correction (MSC) and standard normal variate (SNV). Partial least squares regression (PLSR) and random forest (RF) models were developed using calibration (75 %) and validation (25 %) datasets. Results showed that spectral preprocessing significantly influenced model performance, with SG-1D and MSC providing consistent improvements by enhancing spectral features and reducing scattering effects. The RF model outperformed PLSR, with the best performance achieved using RF combined with MSC and SG-1D (validation R2 = 0.50, RMSE = 0.27 %, RPIQ ≈ 1.66–1.67). The findings indicate that optimal SOC prediction depends on the combined selection of preprocessing techniques and modelling approaches. This study provides a practical and reliable framework for improving soil spectroscopy applications in digital soil mapping and precision agriculture.

References

  1. 1. Ramesh T, Bolan NS, Kirkham MB, Wijesekara H, Kanchikerimath M, Rao CS, et al. Soil organic carbon dynamics: Impact of land use changes and management practices: A review. Adv Agron. 2019;156:1–107. https://doi.org/10.1016/bs.agron.2019.02.001
  2. 2. Dharumarajan S, Adhikari K, Chakraborty R, Kalaiselvi B, Vasundhara R, Lalitha M, et al. Prediction and mapping of soil organic carbon stock via large datasets coupled with pedotransfer functions. Earth Sci Inform. 2025;18(3):314. https://doi.org/10.1007/s12145-025-01822-z
  3. 3. Dharumarajan S, Gomez C, Kusuma CG, Vasundhara R, Kalaiselvi B, Lalitha M, et al. Prediction of soil organic carbon stock along layers and profiles using Vis-NIR laboratory spectroscopy. Catena. 2025;257:109150. https://doi.org/10.1016/j.catena.2025.109150
  4. 4. McBratney AB, Stockmann U, Angers DA, Minasny B, Field DJ. Challenges for soil organic carbon research. In: Soil carbon. Cham: Springer; 2014. p. 3–16. https://doi.org/10.1007/978-3-319-04084-4_1
  5. 5. Ng WK, Maxfield PJ, Crew AP, Teixeira DL, Bevan T, Bell MJ. Comparison of soil organic carbon measurement methods. Agronomy. 2025;15(8):1826. https://doi.org/10.3390/agronomy15081826
  6. 6. Stenberg B, Viscarra Rossel RA, Mouazen AM, Wetterlind J. Visible and near infrared spectroscopy in soil science. Adv Agron. 2010;107:163–215. https://doi.org/10.1016/S0065-2113(10)07005-7
  7. 7. Viscarra Rossel RA, Behrens T, Ben-Dor E, Chabrillat S, Demattê JAM, Ge Y, et al. Diffuse reflectance spectroscopy for estimating soil properties: A technology for the 21st century. Eur J Soil Sci. 2022;73(4):e13271. https://doi.org/10.1111/ejss.13271
  8. 8. Kusuma CG, Dharumarajan S, Vasundhara R, Gomez C, Manjunatha MH, Hegde R. Predicting soil nutrient classes using Vis–NIR spectroscopy to support sustainable farming decisions. Land Degrad Dev. 2025;36(15):5313–23. https://doi.org/10.1002/ldr.70007
  9. 9. Mozaffari H, Moosavi AA, Ostovari Y, Nematollahi MA, Rezaei M. Developing spectrotransfer functions (STFs) to predict basic soil properties. Geoderma. 2022;428:116174. https://doi.org/10.1016/j.geoderma.2022.116174
  10. 10. Sweta K, Dharumarajan S, Kalaiselvi B, Gomez C, Lalitha M, Das B, et al. Reviewing the trajectory of Vis-NIR and MIR spectroscopic soil studies in India. J Indian Soc Soil Sci. 2024;72(1):23–34. https://doi.org/10.5958/0974-0228.2024.00026.3
  11. 11. Kusuma CG, Bhoomika SA, Dharumarajan S. Prediction of soil nutrients using visible-near-infrared reflectance spectroscopy. In: Remote sensing of soils. Elsevier; 2024. p. 493–502. https://doi.org/10.1016/B978-0-443-18773-5.00001-6
  12. 12. Chinilin AV, Vindeker GV, Savin IY. Vis-NIR spectroscopy for soil organic carbon assessment: A meta-analysis. Eurasian Soil Sci. 2023;56(11):1605–17. https://doi.org/10.1134/S1064229323601841
  13. 13. Stevens A, Nocita M, Tóth G, Montanarella L, van Wesemael B. Prediction of soil organic carbon at European scale using spectroscopy. PLoS One. 2013;8(6):e66409. https://doi.org/10.1371/journal.pone.0066409
  14. 14. Sharififar A, Francos N, Ng W, Minasny B, Gholizadeh A, Karunaratne S, et al. Navigating challenges of spectral soil sensing. Soil Environ Health. 2025;3(3):100160. https://doi.org/10.1016/j.seh.2025.100160
  15. 15. Ghosh AK, Das BS, Reddy N. VIS-NIR spectroscopy for SOC estimation with preprocessing techniques. Geoderma Reg. 2020;23:e00349. https://doi.org/10.1016/j.geodrs.2020.e00349
  16. 16. Reyes J, Ließ M. Spectral data processing for field-scale SOC monitoring. Sensors. 2024;24(3):849. https://doi.org/10.3390/s24030849
  17. 17. Dotto AC, Dalmolin RSD, ten Caten A, Grunwald S. Preprocessing for SOC prediction using Vis-NIR spectra. Geoderma. 2018;314:262–74. https://doi.org/10.1016/j.geoderma.2017.11.006
  18. 18. Eslamifar M, Tavakoli H, Thiessen E, Kock R, Correa J, Hartung E. Spectral preprocessing improves soil prediction accuracy. Discover Appl Sci. 2025;7(8):896. https://doi.org/10.1007/s42452-025-07580-3
  19. 19. Wang Y, Yang S, Yan X, Yang C, Feng M, Xiao L, et al. Evaluation of preprocessing and regression models for SOC estimation. J Soils Sediments. 2023;23(2):634–45. https://doi.org/10.1007/s11368-022-03337-2
  20. 20. Wu M, Huang Y, Zhao X, Jin J, Ruan Y. Effects of spectral processing on soil organic matter prediction. J Soils Sediments. 2024;24(2):914–27. https://doi.org/10.1007/s11368-023-03691-9
  21. 21. Zhang Z, Ding J, Zhu C, Wang J. Signal preprocessing and band selection for SOM prediction. Spectrochim Acta A. 2020;240:118553. https://doi.org/10.1016/j.saa.2020.118553
  22. 22. Nocita M, Stevens A, Toth G, Panagos P, van Wesemael B, Montanarella L. SOC prediction using local PLSR. Soil Biol Biochem. 2014;68:337–47. http://dx.doi.org/10.1016/j.soilbio.2013.10.022
  23. 23. Karthikeyan K, Kumar N, Naitam RK, Tiwary P. SOC prediction using Random Forest model. J Sustain For. 2025;44(10):1269–85. https://doi.org/10.1080/10549811.2025.2576759
  24. 24. Vestergaard RJ, Vasava HB, Aspinall D, Chen S, Gillespie A, Adamchuk V, et al. Optimized preprocessing and modeling for soil prediction. Sensors. 2021;21(20):6745. https://doi.org/10.3390/s21206745
  25. 25. Walkley A, Black IA. Examination of Degtjareff method for soil organic matter. Soil Sci. 1934;37(1):29–38.
  26. 26. Savitzky A, Golay MJ. Smoothing and differentiation of data. Anal Chem. 1964;36(8):1627–39. https://doi.org/10.1021/ac60214a047
  27. 27. Duckworth J. Mathematical data preprocessing. In: Near-infrared spectroscopy in agriculture. 2004. p. 113–32. https://doi.org/10.2134/agronmonogr44.c6
  28. 28. Rinnan Å, Van den Berg F, Engelsen SB. Review of preprocessing techniques for NIR spectra. TrAC Trends Anal Chem. 2009;28(10):1201–22. https://doi.org/10.1016/j.trac.2009.07.007
  29. 29. Maleki MR, Mouazen AM, Ramon H, De Baerdemaeker J. Multiplicative scatter correction in NIR. Biosyst Eng. 2007;96(3):427–33. https://doi.org/10.1016/j.biosystemseng.2006.11.014
  30. 30. Barnes RJ, Dhanoa MS, Lister SJ. Standard normal variate transformation. Appl Spectrosc. 1989;43(5):772–7. https://doi.org/10.1366/0003702894202201
  31. 31. Mechram S, Ayu IW, Farni Y. SNV preprocessing for soil nitrogen prediction. IOP Conf Ser Earth Environ Sci. 2024;1290:012026. https://doi.org/10.1088/1755-1315/1290/1/012026
  32. 32. Wold S, Sjöström M, Eriksson L. PLS regression: basic tool of chemometrics. Chemom Intell Lab Syst. 2001;58(2):109–30. https://doi.org/10.1016/S0169-7439(01)00155-1
  33. 33. Breiman L. Random forests. Mach Learn. 2001;45(1):5–32. https://doi.org/10.1023/A:1010933404324
  34. 34. R Core Team. R: A language and environment for statistical computing. Vienna: R Foundation; 2016.
  35. 35. Odebiri O, Mutanga O, Odindi J, Slotow R, Mafongoya P, Lottering R, et al. Mapping SOC in arid landscapes. Geoderma Reg. 2024;37:e00817. https://doi.org/10.1016/j.geodrs.2024.e00817
  36. 36. Miloš B, Bensa A. Prediction of SOC using VIS-NIR spectroscopy. Eurasian J Soil Sci. 2017;6(4):365–73. https://doi.org/10.18393/ejss.319208
  37. 37. Liu S, Shen H, Chen S, Zhao X, Biswas A, Jia X, et al. Forest SOC estimation using spectroscopy. Geoderma. 2019;348:37–44. https://doi.org/10.1016/j.geoderma.2019.04.003
  38. 38. Castaldi F, Stenberg B, Liebisch F, Metzger K, Ben-Dor E, Knadel M, et al. SOC estimation using spectral libraries. Smart Agric Technol. 2025:101353. https://doi.org/10.1016/j.atech.2025.101353
  39. 39. Heil K, Schmidhalter U. Evaluation of NIR preprocessing methods. Sensors. 2021;21(4):1423. https://doi.org/10.3390/s21041423
  40. 40. Minu S, Shetty A, Gopal B. Review of preprocessing techniques in hyperspectral soil analysis. Cogent Geosci. 2016;2(1):1145878. https://doi.org/10.1080/23312041.2016.1145878
  41. 41. Yang J, Dong H, Zhang H, Wang J, Dai H, Zhou L, et al. Enhancing SOC estimation using hyperspectral data. Int J Remote Sens. 2025;46(13):4941–58. https://doi.org/10.1080/01431161.2025.2506158
  42. 42. Dotto AC, Dalmolin RSD, Grunwald S, ten Caten A, Pereira Filho W. Preprocessing to reduce model covariables. Soil Tillage Res. 2017;172:59–68. https://doi.org/10.1016/j.still.2017.05.008
  43. 43. Shin SK, Lee SJ, Park JH. Soil property prediction using Vis-NIR and ML: A review. Sensors. 2025;25(16):5045. https://doi.org/10.3390/s25165045
  44. 44. Zhou Y, Biswas A, Hong Y, Chen S, Hu B, Shi Z, et al. Soil profile analysis using hyperspectral imaging. Geoderma. 2024;450:117036. https://doi.org/10.1016/j.geoderma.2024.117036
  45. 45. He J, Matsui T, Tanaka TS. Soil property estimation using FTIR and ML. Soil Sci Plant Nutr. 2025;71(6):670–83. https://doi.org/10.1080/00380768.2025.2558584
  46. 46. Canero FM, Rodriguez-Galiano V, Aragones D. Machine learning for soil spectroscopy. Heliyon. 2024;10(9):e30228. https://doi.org/10.1016/j.heliyon.2024.e30228
  47. 47. Wu X, Wu K, Hao S, Yu E, Zhao J, Li Y. Machine learning ensemble for soil evolution. Sci Rep. 2025;15(1):24332. https://doi.org/10.1038/s41598-025-10608-8

Downloads

Download data is not yet available.