Skip to main content
SpringerLink
Log in

Soil organic matter content prediction using Vis-NIRS based on different wavelength optimization algorithms and inversion models

  • Soils, Sec 5 • Soil and Landscape Ecology • Research Article
  • Published:
Journal of Soils and Sediments Aims and scope Submit manuscript

Abstract

Purpose

Visible and near-infrared reflectance spectroscopy has been proven to be an efficient method for predicting soil properties, and the wavelength optimization can improve the simulation accuracy of SOM (soil organic matter), but the best combination of wavelength optimization algorithms and inversion model is unknown for alpine ecosystem soil.

Methods

In this study, 269 topsoil samples were collected in the Three-Rivers Source Region of China and were used to build the inversion model of SOM content. Four kinds of wavelength optimization algorithms were conducted, i.e., correlation analysis, uninformative variable elimination (UVE), successive projection algorithm, and competitive adaptive reweighted sampling (CARS) after spectral pre-treatments. Then, partial least squares regression, support vector machine, and random forest (RF) were used to develop the inversion model of SOM content. Various combinations of wavelength optimization algorithms and inversion models were constructed, and the accuracies were compared.

Results

The combination of the UVE-CARS-RF achieved the highest simulation accuracy (R2 = 0.902, RPD = 3.218). For the single band selection method, the CARS algorithm has the highest simulation accuracy, especially the combination of CARS-RF (R2 = 0.899, RPD = 3.133).

Conclusion

Appropriate combination of the wavelength optimization algorithm and inversion model not only can significantly reduce computational load but improve the prediction precision. In total, RF obtained the best predication effect.

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

  • Araújo M, Saldanha T, Galvao R (2011) The successive projections algorithm for variable selection in spectroscopic multicomponent analysis. Chemometr Intell Lab 57:65–73

    Article  Google Scholar 

  • Bangelesa F, Adam E, Knigh J, Dhau I, Mokotjomela TM (2020) Predicting soil organic carbon content using hyperspectral remote sensing in a degraded mountain landscape in Lesotho. Appl Environ Soil Sc 31:1026–1038

    Google Scholar 

  • Bao N, Wu L, Ye B, Yang K, Zhou W (2017) Assessing soil organic matter of reclaimed soil from a large surface coal mine using a field spectroradiometer in laboratory. Geoderma 288:47–55

    Article  CAS  Google Scholar 

  • Baritz R, Seufert G, Montanarella L, Van Ranst E (2010) Carbon concentrations and stocks in forest soils of Europe. For Ecol Manag 260:262–277

    Article  Google Scholar 

  • Ben-Dor E, Banin A (1995) Near-Infrared analysis as a rapid method to simultaneously evaluate several soil properties. Soil Sci Soc Am J 59:364–372

    Article  CAS  Google Scholar 

  • Castaldi F, Palombo A, Santini F, Pascucci S, Pignatti S, Casa R (2016) Evaluation of the potential of the current and forthcoming multispectral and hyperspectral imagers to estimate soil texture and organic carbon. Remote Sens Environ 179:54–65

    Article  Google Scholar 

  • Castaldi F, Chabrillat S, Van Wesemael B (2019) Sampling strategies for soil property mapping using multispectral Sentinel-2 and hyperspectral EnMAP satellite data. Remote Sens-Basel 11:1–19

    Google Scholar 

  • Centner V, Massart DL, Denoord OE, Dejong S, Vandeginste BM, Sterna (1996) Elimination of uninformative variables for multivariate calibration. Anal Chem 68:3851–3858

    Article  CAS  Google Scholar 

  • Chang CW, Laird DA, Mausbach MJ, Hurburgh CR (2001) Near-infrared reflectance spectroscopy-principal components regression analyses of soil properties. Soil Sci Soc Am J 65:480–490

    Article  CAS  Google Scholar 

  • Chen L, He Z, Du J, Yang J, Zhu X (2015) Patterns and controls of soil organic carbon and nitrogen in alpine forests of Northwestern China. Forest Sci 61:1033–1040

    Article  Google Scholar 

  • Chen Y, Wang J, Liu G, Yang Y, Liu Z, Deng H (2019) Hyperspectral estimation model of forest soil organic matter in northwest Yunnan province. China Forests 10:217

    Article  Google Scholar 

  • Cozzolino D, Morón A (2006) Potential of near-infrared reflectance spectroscopy and chemometrics to predict soil organic carbon fractions. Soil Till Res 85:78–85

    Article  Google Scholar 

  • Dong ZY, Wang N, Liu JB, Xie JC, Han JC (2021) Combination of machine learning and VIRS for predicting soil organic matter. J Soil Sediment 21:2578–2588

    Article  Google Scholar 

  • Dunn BW, Batten GD, Beecher HG, Ciavarella S (2002) The potential of near-infrared reflectance spectroscopy for soil analysis-a case study from the Riverine Plain of south-eastern Australia. Aust J Exp Agr 42:607–611

    Article  Google Scholar 

  • Enescu R, Dinca L, Vasile D, Vlad R (2022) Does the slope aspect influence the soil organic matter concentration in forest soils. Forests 13:f13091472

    Article  Google Scholar 

  • Gao LL, Zhu XC, Han ZY, Wang L, Zhao GX, Jiang YM (2019) Spectroscopy-based soil organic matter estimation in brown forest soil areas of the Shandong peninsula, China. Pedosphere 29:810–818

    Article  Google Scholar 

  • Garnier J, Billen G, Tournebize J, Barre P, Mary B, Baudin F (2022) Storage or loss of soil active carbon in cropland soils: the effect of agricultural practices and hydrology. Geoderma 407:115538

    Article  CAS  Google Scholar 

  • Garten CT (2006) Measured forest soil C stocks and estimated turnover times along an elevation gradient. Geoderma 136:342–352

    Article  CAS  Google Scholar 

  • Gholizadeh A, Bor Vka L, Saberioon MM, Kozák J, Át RV, Ek N (2015) Comparing different data preprocessing methods for monitoring soil heavy metals based on soil spectral features. Soil Water Res 10:218–227

    Article  CAS  Google Scholar 

  • Gholizadeh A, Žižala D, Saberioon M, Borůvka L (2018) Soil organic carbon and texture retrieving and mapping using proximal, airborne and sentinel-2 spectral imaging. Remote Sens Environ 218:89–103

    Article  Google Scholar 

  • Gomez C, Rossel RAV, Mcbratney AB (2008) Soil organic carbon prediction by hyperspectral remote sensing and field vis-NIR spectroscopy: an Australian case study. Geoderma 146:403–411

    Article  CAS  Google Scholar 

  • Guo L, Shi TZ, Linderman M, Chen YY, Fu P (2019) Exploring the influence of spatial resolution on the digital mapping of soil organic carbon by airborne hyperspectral VNIR imaging. Remote Sens-Basel 11:1032

    Article  Google Scholar 

  • Gu X, Wang Y, Sun Q, Yang G, Zhang C (2019) Hyperspectral inversion of soil organic matter content in cultivated land based on wavelet transform. Comput Electron Agr 167:105053

    Article  Google Scholar 

  • He JL, Jiang JJ, Zhou SL, Jun X, Cai HL, Zhang CY (2007) The hyperspectral characteristics and retrieval of soil organic matter content. Sci Agric Sini (in Chinese) 3:638–643

  • Hong Y (2018) Application of fractional-order derivative in the quantitative estimation of soil organic matter content through visible and near-infrared spectroscopy. Geoderma 337:758–769

    Article  Google Scholar 

  • Ji WJ, Li X, Li CX, Zhou Y, Shi Z (2012) Using different data mining algorithms to predict soil organic matter based on Visible-Near infrared spectroscopy. Spectrosc Spect Anal 32:2393

    CAS  Google Scholar 

  • Ji WJ, Rossel RV, Shi Z (2015) Accounting for the effects of water and the environment on proximally sensed vis–NIR soil spectra and their calibrations. Eur J Soil Sci 66:555–565

    Article  Google Scholar 

  • Lei Y, Hong YS, Zhou Y, Zhu Q, Xu L, Li YY, Nie Y (2016) Wavelength variable selection methods for estimation of soil organic matter content using hyperspectral technique. Trans Chin Soc Agric Eng (in Chinese) 32:95–102

    Google Scholar 

  • Li GW, Gao XH, Xiao NW, Xiao YF (2019) Estimation soil organic matter contents with hyperspectral based on sCARS and RF Algorithms. Chin J Lumin (in Chinese) 40:1030–1039

    Article  Google Scholar 

  • Li HD, Liang YZ, Xu QS, Cao DS (2009) Key wavelengths screening using competitive adaptive reweighted sampling method for multivariate calibration. Anal Chim Acta 648:77–84

    Article  CAS  Google Scholar 

  • Li JY, Zhang DY, Liu M (2020) Factors controlling the spatial distribution of soil organic carbon in Daxing’anling Mountain. Sci Rep-UK 10:1–8

    Google Scholar 

  • Lin ZD, Wang YB, Wang RJ, Wang LS, Lu CP, Zhang ZY, Song LT, Liu Y (2016) Improvements of Vis-NIRS model in the prediction of soil organic matter content using wavelength optimization. Chin J Lumin (in Chinese) 37:1428–1435

    Article  Google Scholar 

  • Liu F, Wu HY, Zhao YG, Li DC, Yang JL, Song X, Shi Z, Zhu AX, Zhang GL (2021) Mapping high resolution National Soil Information Grids of China. Sci Bull 10:1016

    Google Scholar 

  • Liu J, Xu XL, Shao QQ (2008) The spatial and temporal characteristics of grassland degradation in the three-river headwaters region in Qinghai Province. J Geogr Sci 17:259–273

    Article  Google Scholar 

  • Luan FM, Zhang XL, Xiong HG, Zhang F, Wang F (2013) Comparative analysis of soil organic matter content based on different hyperspectral inversion models. Spectrosc Spect Anal 33:196–200

    CAS  Google Scholar 

  • Luo DF, Peng J, Feng CH, Liu WY, Ji WJ, Wang N (2021) Inversion of soil organic matter fraction in southern Xinjiang by visible-near-infrared and mid-infrared spectra. Spectrosc Spect Anal 41:3069–3076

    CAS  Google Scholar 

  • Manojlović M, Čabilovski R, Sitaula B (2011) Soil organic carbon in serbian mountain soils: effects of land use and altitude. Pol J Environ Stud 20:977–986

    Google Scholar 

  • Martin PD, Malley DF, Manning G, Fuller L (2002) Determination of soil organic carbon and nitrogen at the field level using near-infrared spectroscopy. Can J Soil Sci 82:413–422

    Article  CAS  Google Scholar 

  • Melgani F, Bruzzone L (2004) Classification of hyperspectral remote sensing images with support vector machines. IEEE T Geosci Remote 42:1778–1790

    Article  Google Scholar 

  • Meng XT, Bao YL, Liu JG, Liu HJ, Kong FC (2020) Regional soil organic carbon prediction model based on a discrete wavelet analysis of hyperspectral satellite data. Int J Appl Earth Obs 89:1–15

    Google Scholar 

  • Morra MJ, Hall MH, Freeborn LL (1991) Carbon and nitrogen analysis of soil fractions using near-infrared reflectance spectroscopy. Soil Sci Soc Am J 55(1):288–291

    Article  CAS  Google Scholar 

  • Podwojewski P, Poulenard J, Nguyet ML, de Rouw A, Nguyen VT, Pham QH, Tran DT (2011) Climate and vegetation determine soil organic matter status in an alpine inner-tropical soil catena in the Fan Si Pan Mountain, Vietnam. Catena 87:226–239

    Article  CAS  Google Scholar 

  • Poggio L, Gimona A (2017) Assimilation of optical and radar remote sensing data in 3D mapping of soil properties over large areas. Sci Total Environ 579:1094–1110

    Article  CAS  Google Scholar 

  • Rokach L (2015) Decision forest: twenty years of research. Inform Fusion 27:111–125

    Article  Google Scholar 

  • Rossel R, Lark RM (2010) Improved analysis and modelling of soil diffuse reflectance spectra using wavelets. Eur J Soil Sci 60:453–464

    Article  Google Scholar 

  • Tian G, Justicia R, Coleman DC, Carroll CR (1986) Assessment of soil and plant carbon levels in two ecosystems (woody bamboo and pasture) in Montane Ecuador. Soil Sci 172:459–468

    Article  Google Scholar 

  • Tomislav H, Jorge MDJ, Heuvelink GBM, Maria RG, Milan K (2017) Soil Grids 250m: Global gridded soil information based on machine learning. PLoS ONE 12:e0169748

    Article  Google Scholar 

  • Vasat R, Kodesova R, Klement A, Boruvka L (2017) Simple but efficient signal pre-processing in soil organic carbon spectroscopic estimation. Geoderma 298:46–53

    Article  CAS  Google Scholar 

  • Veum KS, Goyne KW, Kremer RJ, Miles RJ, Sudduth KA (2014) Biological indicators of soil quality and soil organic matter characteristics in an agricultural management continuum. Biogeochemistry 117:81–99

    Article  CAS  Google Scholar 

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

    Article  Google Scholar 

  • Vohland M, Besold J, Hill J, Fründ HC (2011) Comparing different multivariate calibration methods for the determination of soil organic carbon pools with visible to near infrared spectroscopy. Geoderma 166:198–205

    Article  CAS  Google Scholar 

  • Vohland M, Ludwig M, Thiele-Bruhn S, Ludwig B (2014) Determination of soil properties with visible to near- and mid-infrared spectroscopy: effects of spectral variable selection. Geoderma 223:88–96

    Article  Google Scholar 

  • Wang XM, Yang C, Zhou MJ (2021) Partial least squares improved multivariate adaptive regression splines for visible and near-infrared-based soil organic matter estimation considering spatial heterogeneity. Appl Sci 11:566

    Article  CAS  Google Scholar 

  • Wang XY, Cao ZY, Wang CY, Xu L, Zong N, Zhang JJ, He NP (2022) Influence of simulated warming on soil nitrogen fractions in a Tibetan alpine meadow. J Soil Sediment 11368

  • Ward KJ, Chabrillat S, Brell M, Castaldi F, Foerster S (2020) Mapping soil organic carbon for airborne and simulated EnMAP imagery using the LUCAS soil database and a local PLSR. Remote Sens-Basel 12:451

    Google Scholar 

  • Wehrens R, Mevik BH (2007) The pls package: principal component and partial least squares regression in R. J Statl Softw 18:1–24

    Google Scholar 

  • Yang H, Kuang B, Mouazen AM (2012) Quantitative analysis of soil nitrogen and carbon at a farm scale using visible and near infrared spectroscopy coupled with wavelength reduction. Eur J Soil Sci 63:410–420

    Article  CAS  Google Scholar 

  • Yang RM, Rossiter DG, Liu F, Lu Y, Yang F (2015a) Predictive mapping of topsoil organic carbon in an alpine environment aided by Landsat TM. PLoS ONE 10:1–20

    Google Scholar 

  • Yang Y, Gao XH, Jia W, Zhang W, Li JS, Zhang YJ, Tian CM (2015b) Hyperspectral inversion of organic matter for different soil types in the three-river headwaters region. Remote Sens Technol Applic (in Chinese) 30:186–198

    Google Scholar 

  • Zhang ZP, Ding JL, Wang JZ, Ge XY (2020) Prediction of soil organic matter in Northwestern China using fractional- order derivative spectroscopy and modified normalized difference indices. Catena 185:104257

    Article  CAS  Google Scholar 

  • Zhou T, Geng YJ, Ji C, Xu XR, Hong W, Pan JJ, Bumberger J, Haase D, Lausch A (2020) Prediction of soil organic carbon and the C: N ratio on a national scale using machine learning and satellite data: a comparison between Sentinel-2, Sentinel-3 and Landsat-8 images. Sci Total Environ 755:661

    Google Scholar 

  • Zhou W, Li H, Wen S, Xie L, Wang T, Tian Y, Yu W (2022) Simulation of soil organic carbon content based on laboratory spectrum in the three-rivers source region of china. Remote Sens-Basel 14:1521

    Article  Google Scholar 

  • Zhou W, Xie LJ, Yang H, Huang L, Li HR, Yang M (2021a) Hyperspectral inversion of soil organic matter content in the three-rivers source region. Chin J Soil Sci (in Chinese) 52:564–574

    Google Scholar 

  • Zhou W, Yang H, Xie LJ, Li HR, Yue TX (2021b) Hyperspectral inversion of soil heavy metals in Three-river source region based on random forest model. Catena 202:105222

    Article  CAS  Google Scholar 

  • Zhou Y, Chen SC, Zhu AX, Hu BF, Li Y (2021c) Revealing the scale- and location-specific controlling factors of soil organic carbon in Tibet. Geoderma 382:114713

    Article  CAS  Google Scholar 

  • Zhu B, Wang X, Fang J, Piao S, Shen H, Zhao S, Peng C (2010) Altitudinal changes in carbon storage of temperate forests on Mt Changbai, Northeast China. J Plant Res 123:439–452

    Article  Google Scholar 

  • Zhu YX, Yu L, Hong YS (2017) Hyperspectral Features and Wavelength Variables Selection Methods of Soil Organic Matter Sci Agric Sinica ( in Chinese) 50:4325–4337

    Google Scholar 

  • Zou XB, Zhao JW, Povey MJ, Holmes M, Mao HP (2010) Variables selection methods in near-infrared spectroscopy. Analy Chim Acta 667:14–32

    Article  CAS  Google Scholar 

Download references

Funding

This work and article processing charge were funded by the Project of Chongqing Science and Technology Bureau (cstc2021jcyj-msxmX0384), the Fundamental Research Funds for the Central Universities (SWU020015), the National Natural Science Foundation of China (41930647, 41501575), the Strategic Priority Research Program (A) of the Chinese Academy of Sciences (XDA20030203), and the Innovation Project of LREIS (O88RA600YA).

Author information

Authors and Affiliations

  1. Chongqing Jinfo Mountain Karst Ecosystem National Observation and Research Station, School of Geographical Sciences, Southwest University, Chongqing, 400715, China

    Wei Zhou, Jieyun Xiao, Haoran Li & Ting Wang

  2. State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, CAS, Beijing, 100101, China

    Wei Zhou & Tianxiang Yue

  3. Shandong Agricultural University, College of Resources and Environment, Taian, 271018, China

    Qi Chen

  4. School of Geography and Environment, Liaocheng University, Liaocheng, 252059, Shandong, China

    Qian Wang

Authors
  1. Wei Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jieyun Xiao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Haoran Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Qi Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Ting Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Qian Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Tianxiang Yue
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Wei Zhou or Tianxiang Yue.

Ethics declarations

Conflict of interest

The authors declare no competing interests.

Additional information

Responsible editor: Jun Zhou

Publisher's Note

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

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) 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

Zhou, W., Xiao, J., Li, H. et al. Soil organic matter content prediction using Vis-NIRS based on different wavelength optimization algorithms and inversion models. J Soils Sediments 23, 2506–2517 (2023). https://doi.org/10.1007/s11368-023-03480-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11368-023-03480-4

Keywords

Search

Navigation