Skip to main content
SpringerLink
Log in

The potential of hyperspectral images and partial least square regression for predicting total carbon, total nitrogen and their isotope composition in forest litterfall samples

  • Soils, Sec 2 • Global Change, Environ Risk Assess, Sustainable Land Use • Research Article
  • Published:
Journal of Soils and Sediments Aims and scope Submit manuscript

Abstract

Purpose

The main objective of this study was to examine the potential of using hyperspectral image analysis for prediction of total carbon (TC), total nitrogen (TN) and their isotope composition (δ13C and δ15N) in forest leaf litterfall samples.

Materials and methods

Hyperspectral images were captured from ground litterfall samples of a natural forest in the spectral range of 400–1700 nm. A partial least-square regression model (PLSR) was used to correlate the relative reflectance spectra with TC, TN, δ13C and δ15N in the litterfall samples. The most important wavelengths were selected using β coefficient, and the final models were developed using the most important wavelengths. The models were, then, tested using an external validation set.

Results and discussion

The results showed that the data of TC and δ13C could not be fitted to the PLSR model, possibly due to small variations observed in the TC and δ13C data. The model, however, was fitted well to TN and δ15N. The cross-validation R2 cv of the models for TN and δ15N were 0.74 and 0.67 with the RMSEcv of 0.53% and 1.07‰, respectively. The external validation R2 ex of the prediction was 0.64 and 0.67, and the RMSEex was 0.53% and 1.19 ‰, for TN and δ15N, respectively. The ratio of performance to deviation (RPD) of the predictions was 1.48 and 1.53, respectively, for TN and δ15N, showing that the models were reliable for the prediction of TN and δ15N in new forest leaf litterfall samples.

Conclusions

The PLSR model was not successful in predicting TC and δ13C in forest leaf litterfall samples using hyperspectral data. The predictions of TN and δ15N values in the external litterfall samples were reliable, and PLSR can be used for future prediction.

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
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

References

  • Abdi H (2010) Partial least squares regression and projection on latent structure regression (PLS regression). Wiley Interdiscip Rev Comput Stat 2:97–106

    Article  Google Scholar 

  • Ariana DP, Lu R, Guyer DE (2006) Near-infrared hyperspectral reflectance imaging for detection of bruises on pickling cucumbers. Comput Electron Agr 53:60–70

    Article  Google Scholar 

  • Bai SH, Sun F, Xu Z, Blumfield TJ (2013) Ecophysiological status of different growth stage of understorey Acacia leiocalyx and Acacia disparrima in an Australian dry sclerophyll forest subjected to prescribed burning. J Soils Sediments 13:1378–1385

    Article  Google Scholar 

  • Bai SH, Xu Z, Blumfield TJ, Reverchon F (2015) Human footprints in urban forests: implication of nitrogen deposition for nitrogen and carbon storage. J Soils Sediments 15:1927–1936

    Article  Google Scholar 

  • Bai SH, Dempsey R, Reverchon F, Blumfield TJ, Ryan S, Cernusak LA (2016) Effects of forest thinning on soil-plant carbon and nitrogen dynamics. Plant Soil:1–13

  • Bansal S, Sheley RL, Blank B, Vasquez EA (2014) Plant litter effects on soil nutrient availability and vegetation dynamics: changes that occur when annual grasses invade shrub-steppe communities. Plant Ecol 215:367–378

    Article  Google Scholar 

  • Barbin DF, ElMasry G, Sun D-W, Allen P (2012) Predicting quality and sensory attributes of pork using near-infrared hyperspectral imaging. Anal Chim Acta 719:30–42

    Article  CAS  Google Scholar 

  • Barrett JP (1974) The coefficient of determination—some limitations. Am Stat 28:19–20

    Google Scholar 

  • Bellon-Maurel V, Fernandez-Ahumada E, Palagos B, Roger J-M, McBratney A (2010) Critical review of chemometric indicators commonly used for assessing the quality of the prediction of soil attributes by NIR spectroscopy. TrAC Trends Anal Chem 29:1073–1081

    Article  CAS  Google Scholar 

  • Berrueta LA, Alonso-Salces RM, Héberger K (2007) Supervised pattern recognition in food analysis. J Chromatogr A 1158:196–214

    Article  CAS  Google Scholar 

  • Blackmer TM, Schepers JS, Varvel GE (1994) Light reflectance compared with other nitrogen stress measurements in corn leaves. Agron J 86:934–938

    Article  Google Scholar 

  • Bragazza L, Buttler A, Habermacher J, Brancaleoni L, Gerdol R, Fritze H, Hanajík P, Laiho R, Johnson D (2012) High nitrogen deposition alters the decomposition of bog plant litter and reduces carbon accumulation. Glob Change Biol 18:1163–1172

    Article  Google Scholar 

  • Catterall C, Wallace C (1987) An island in suburbia: the natural and social history of Toohey Forest. Griffith University, Brisbane

    Google Scholar 

  • Catterall CP, Piper SD, Bunn SE, Arthur JM (2001) Flora and fauna assemblages vary with local topography in a subtropical eucalypt forest. Aus Ecol 26:56–69

    Google Scholar 

  • Chai T, Draxler RR (2014) Root mean square error (RMSE) or mean absolute error (MAE)?—arguments against avoiding RMSE in the literature. Geosci Model Deve 7:1247–1250

    Article  Google Scholar 

  • Chang-shan W, Yueqin X, Lanfen Z, Qing-xi T (2000) Estimating chlorophyll density of crop canopies by using hyperspectral data. Remote Sens 4:228–232

    Google Scholar 

  • Cheng J-H, Sun D-W (2017) Partial least squares regression (PLSR) applied to NIR and HSI spectral data modeling to predict chemical properties of fish muscle. Food Eng Rev 9:36–49

    Article  CAS  Google Scholar 

  • Chong I-G, Jun C-H (2005) Performance of some variable selection methods when multicollinearity is present. Chemometr Intell Lab 78:103–112

    Article  CAS  Google Scholar 

  • Coops NC, Smith M-L, Martin ME, Ollinger SV (2003) Prediction of eucalypt foliage nitrogen content from satellite-derived hyperspectral data. IEEE T Geosci Remote 41:1338–1346

    Article  Google Scholar 

  • Curran PJ (1989) Remote sensing of foliar chemistry. Remote Sens Environ 30:271–278

    Article  Google Scholar 

  • Curran PJ, Dungan JL, Peterson DL (2001) Estimating the foliar biochemical concentration of leaves with reflectance spectrometry: testing the Kokaly and Clark methodologies. Remote Sens Environ 76:349–359

    Article  Google Scholar 

  • Dai Q, Sun DW, Xiong Z, Cheng JH, Zeng XA (2014) Recent advances in data mining techniques and their applications in hyperspectral image processing for the food industry. Compr Rev Food Sci F 13:891–905

    Article  Google Scholar 

  • Elmasry G, Kamruzzaman M, Sun D-W, Allen P (2012) Principles and applications of hyperspectral imaging in quality evaluation of agro-food products: a review. Crit Rev Food Sci 52:999–1023

    Article  Google Scholar 

  • Fearn T (2000) On orthogonal signal correction. Chemometr Intell Lab 50:47–52

    Article  CAS  Google Scholar 

  • Feng W, Yao X, Zhu Y, Tian YC, Cao WX (2008) Monitoring leaf nitrogen status with hyperspectral reflectance in wheat. Eur J Agron 28:394–404

    Article  CAS  Google Scholar 

  • Ferrari M, Norris K, Sowac M (2012) Medical near infrared spectroscopy 35 years after the discovery. J Near Infrared Spectrosc 20:vii–ix. doi:10.1255/jnirs.982

  • Ferwerda JG, Skidmore AK, Mutanga O (2005) Nitrogen detection with hyperspectral normalized ratio indices across multiple plant species. Int J Remote Sens 26:4083–4095

    Article  Google Scholar 

  • Gillon D, Houssard C, Joffre R (1999) Using near-infrared reflectance spectroscopy to predict carbon, nitrogen and phosphorus content in heterogeneous plant material. Oecologia 118:173–182

    Article  Google Scholar 

  • Guendehou GS, Liski J, Tuomi M, Moudachirou M, Sinsin B, Mäkipää R (2014) Decomposition and changes in chemical composition of leaf litter of five dominant tree species in a west African tropical forest. Trop Ecol 55:207–220

    Google Scholar 

  • Hansen P, Schjoerring J (2003) Reflectance measurement of canopy biomass and nitrogen status in wheat crops using normalized difference vegetation indices and partial least squares regression. Remote Sens Environ 86:542–553

    Article  Google Scholar 

  • He H-J, Wu D, Sun D-W (2013) Non-destructive and rapid analysis of moisture distribution in farmed Atlantic salmon (Salmo salar) fillets using visible and near-infrared hyperspectral imaging. Innov Food Sci Emerg 18:237–245

    Article  Google Scholar 

  • Höskuldsson A (1988) PLS regression methods. J Chemom 2:211–228

    Article  Google Scholar 

  • Hosseini Bai S, Sun F, Xu ZH, Blumfield TJ, Chen C, Wild C (2012) Appraisal of 15N enrichment and 15N natural abundance methods for estimating N2 fixation by understorey Acacia leiocalyx and A. disparimma in a native forest of subtropical Australia. J Soils Sediments 12:653–662

    Article  CAS  Google Scholar 

  • Hosseini Bai S, Blumfield TJ, Xu ZH (2014) Survival, growth and physiological status of Acacia disparrima and Eucalyptus crebra seedlings with respect to site management practices in Central Queensland, Australia. Eur J Forest Res 133:165–175

    Article  CAS  Google Scholar 

  • Huang M, Wang Q, Zhang M, Zhu Q (2014) Prediction of color and moisture content for vegetable soybean during drying using hyperspectral imaging technology. J Food Eng 128:24–30

    Article  Google Scholar 

  • Ibell PT, Xu Z, Blumfield TJ (2013a) The influence of weed control on foliar δ15N, δ13C and tree growth in an 8 year-old exotic pine plantation of subtropical Australia. Plant Soil 369:199–217

    Article  CAS  Google Scholar 

  • Ibell PT, Xu Z, Blake T, Blumfield TJ (2013b) Effects of weed control and fertilization at early establishment on tree nitrogen and water use in an exotic F1 hybrid pine of subtropical Australia. J Soils Sediments 13:1538–1552

    Article  CAS  Google Scholar 

  • Jamrógiewicz M (2012) Application of the near-infrared spectroscopy in the pharmaceutical technology. J Pharmaceut Biomed 66:1–10

    Article  Google Scholar 

  • Jiang Q, Chen Y, Guo L, Fei T, Qi K (2016) Estimating soil srganic carbon of cropland soil at different levels of soil moisture using VIS-NIR spectroscopy. Remote Sens 8:755

    Article  Google Scholar 

  • Kamruzzaman M, ElMasry G, Sun D-W, Allen P (2012) Prediction of some quality attributes of lamb meat using near-infrared hyperspectral imaging and multivariate analysis. Anal Chim Acta 714:57–67

    Article  CAS  Google Scholar 

  • Kamruzzaman M, Makino Y, Oshita S (2015) Non-invasive analytical technology for the detection of contamination, adulteration, and authenticity of meat, poultry, and fish: a review. Anal Chim Acta 853:19–29

    Article  CAS  Google Scholar 

  • Kamruzzaman M, Makino Y, Oshita S (2016a) Rapid and non-destructive detection of chicken adulteration in minced beef using visible near-infrared hyperspectral imaging and machine learning. J Food Eng 170:8–15

    Article  CAS  Google Scholar 

  • Kamruzzaman M, Makino Y, Oshita S (2016b) Parsimonious model development for real-time monitoring of moisture in red meat using hyperspectral imaging. Food Chem 196:1084–1091

    Article  CAS  Google Scholar 

  • Koehler FW, Lee E, Kidder LH, Lewis EN (2002) Near infrared spectroscopy: the practical chemical imaging solution. Spectroscopy 14:12–19

    CAS  Google Scholar 

  • Li W, Qu H (2016) Determination of total organic carbon and soluble solids contents in Tanreqing injection intermediates with NIR spectroscopy and chemometrics. Chemometr Intell Lab 152:140–145

    Article  CAS  Google Scholar 

  • Li B, Morris J, Martin EB (2002) Model selection for partial least squares regression. Chemometr Intell Lab 64:79–89

    Article  CAS  Google Scholar 

  • Li F, Mistele B, Hu Y, Chen X, Schmidhalter U (2014) Reflectance estimation of canopy nitrogen content in winter wheat using optimised hyperspectral spectral indices and partial least squares regression. Eur J Agron 52(Part B):198–209

    Article  CAS  Google Scholar 

  • Li S, Shi Z, Chen S, Ji W, Zhou L, Yu W, Webster R (2015) In situ measurements of organic carbon in soil profiles using vis-NIR spectroscopy on the Qinghai–Tibet plateau. Environ Sci Technol 49:4980–4987

    Article  CAS  Google Scholar 

  • Lin C, Popescu S, Huang S, Chang P, Wen H (2015a) A novel reflectance-based model for evaluating chlorophyll concentrations of fresh and water-stressed leaves. Biogeosciences 12:49–66

    Article  Google Scholar 

  • Lin L, Wang Y, Teng J, Xi X (2015b) Hyperspectral analysis of soil total nitrogen in subsided land using the local correlation maximization-complementary superiority (LCMCS) method. Sensors 15:17990–18011

    Article  CAS  Google Scholar 

  • Lindgren F, Geladi P, Wold S (1993) The kernel algorithm for PLS. J Chemom 7:45–59

    Article  CAS  Google Scholar 

  • Liu Z, Cai W, Shao X (2008) Outlier detection in near-infrared spectroscopic analysis by using Monte Carlo cross-validation. Sci China Ser B Chem 51:751. doi:10.1007/s11426-008-0080-x

    Article  CAS  Google Scholar 

  • Ma L, Rao X, Lu P, Bai SH, Xu ZH, Chen X, Blumfield T, Xie J (2015) Ecophysiological and foliar nitrogen concentration responses of understorey Acacia spp. and eucalyptus sp. to prescribed burning. Environ Sci Pollut R 22:10254–10262

    Article  CAS  Google Scholar 

  • Manley M (2014) Near-infrared spectroscopy and hyperspectral imaging: non-destructive analysis of biological materials. Chem Soc Rev 43:8200–8214

    Article  CAS  Google Scholar 

  • Martin ME, Plourde L, Ollinger S, Smith M-L, McNeil B (2008) A generalizable method for remote sensing of canopy nitrogen across a wide range of forest ecosystems. Remote Sens Environ 112:3511–3519

    Article  Google Scholar 

  • Morellos A, Pantazi X-E, Moshou D, Alexandridis T, Whetton R, Tziotzios G, Wiebensohn J, Bill R, Mouazen AM (2016) Machine learning based prediction of soil total nitrogen, organic carbon and moisture content by using VIS-NIR spectroscopy. Biosyst Eng 152:104–116

    Article  Google Scholar 

  • Mouazen AM, Kuang B, De Baerdemaeker J, Ramon H (2010) Comparison among principal component, partial least squares and back propagation neural network analyses for accuracy of measurement of selected soil properties with visible and near infrared spectroscopy. Geoderma 158:23–31

    Article  CAS  Google Scholar 

  • Mullaney J, Trueman SJ, Lucke T, Bai SH (2015) The effect of permeable pavements with an underlying base layer on the ecophysiological status of urban trees. Urban For Urban Gree 14:686–693

    Article  Google Scholar 

  • Mullaney J, Lucke T, Trueman S, Hosseini Bai S (2016) The growth and health of street trees planted in permeable pavements. Acta Hortic 1108:77–82

    Article  Google Scholar 

  • Pellegrini AF, Hoffmann WA, Franco AC (2014) Carbon accumulation and nitrogen pool recovery during transitions from savanna to forest in central Brazil. Ecology 95:342–352

    Article  Google Scholar 

  • Prasolova N, Xu ZH, Farquhar GD, Saffigna PG, Dieters MJ (2000) Variation in branchlet δ13C in relation to branchlet nitrogen concentration and growth in 8-year-old hoop pine families (Araucaria cunninghamii) in subtropical Australia. Tree Physiol 20:1049–1055

    Article  CAS  Google Scholar 

  • Qin J, Chao K, Kim MS, Lu R, Burks TF (2013) Hyperspectral and multispectral imaging for evaluating food safety and quality. J Food Eng 118:157–171

    Article  CAS  Google Scholar 

  • Rinnan Å, Berg FVD, 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 

  • Schulze ED (2000) The carbon and nitrogen cycle of forest ecosystems. In: Schulze ED (ed) Carbon and nitrogen cycling in European forest ecosystems. Springer, Germany, pp 3–13

  • Shearer G, Kohl DH (1986) N2-fixation in field settings: estimations based on natural 15N abundance. Func Plant Biol 13:699–756

    CAS  Google Scholar 

  • Shi T, Liu H, Wang J, Chen Y, Fei T, Wu G (2014) Monitoring arsenic contamination in agricultural soils with reflectance spectroscopy of rice plants. Environ Sci Technol 48:6264–6272

    Article  CAS  Google Scholar 

  • Siripatrawan U, Makino Y, Kawagoe Y, Oshita S (2011) Rapid detection of Escherichia coli contamination in packaged fresh spinach using hyperspectral imaging. Talanta 85:276–281

    Article  CAS  Google Scholar 

  • Starks PJ, Brown MA, Turner KE, Venuto BC (2016) Canopy visible and near-infrared reflectance data to estimate alfalfa nutritive attributes before harvest. Crop Sci 56:484–496

    Article  CAS  Google Scholar 

  • Sun Y, Liu Y, Yu H, Xie A, Li X, Yin Y, Duan X (2017) Non-destructive prediction of moisture content and freezable water content of purple-fleshed sweet potato slices during drying process using hyperspectral imaging technique. Food Anal Methods 10:1535–1546

    Article  Google Scholar 

  • Taavitsainen VM (2010) Ridge and PLS based rational function regression. J Chemom 24:665–673

    Article  CAS  Google Scholar 

  • Tian Y, Yao X, Yang J, Cao W, Hannaway D, Zhu Y (2011) Assessing newly developed and published vegetation indices for estimating rice leaf nitrogen concentration with ground-and space-based hyperspectral reflectance. Field Crop Res 120:299–310

    Article  Google Scholar 

  • Tutua SS, Xu ZH, Blumfield TJ (2014) Foliar and litter needle carbon and oxygen isotope compositions relate to tree growth of an exotic pine plantation under different residue management regimes in subtropical Australia. Plant Soil 375:189–204

    Article  CAS  Google Scholar 

  • Wang Y, Xu Z, Zhou Q (2014) Impact of fire on soil gross nitrogen transformations in forest ecosystems. J Soils Sediments 14:1030–1040

    Article  CAS  Google Scholar 

  • Wang Y, Xu Z, Zheng J, Abdullah KM, Zhou Q (2015) δ 15N of soil nitrogen pools and their dynamics under decomposing leaf litters in a suburban native forest subject to repeated prescribed burning in southeast Queensland, Australia. J Soils Sediments 15:1063–1074

    Article  CAS  Google Scholar 

  • Whittinghill KA, Currie WS, Zak DR, Burton AJ, Pregitzer KS (2012) Anthropogenic N deposition increases soil C storage by decreasing the extent of litter decay: analysis of field observations with an ecosystem model. Ecosystems 15:450–461

    Article  CAS  Google Scholar 

  • Wold S, Ruhe A, Wold H, Dunn WJ III (1984) The collinearity problem in linear regression. The partial least squares (PLS) approach to generalized inverses. SIAM J Sci Stat Comp 5:735–743

    Article  Google Scholar 

  • Wold JP, Jakobsen T, Krane L (1996) Atlantic salmon average fat content estimated by near-infrared transmittance spectroscopy. J Food Sci 61:74–77

    Article  CAS  Google Scholar 

  • Wold S, Sjöström M, Eriksson L (2001) PLS-regression: a basic tool of chemometrics. Chemometr Intell Lab 58:109–130

    Article  CAS  Google Scholar 

  • Xu ZH, Saffigna P, Farquhar G, Simpson J, Haines R, Walker S, Osborne D, Guinto D (2000) Carbon isotope discrimination and oxygen isotope composition in clones of the F1 hybrid between slash pine and Caribbean pine in relation to tree growth, water-use efficiency and foliar nutrient concentration. Tree Physiol 20:1209–1217

    Article  CAS  Google Scholar 

  • Xu XG, Yang XD, Gu XH, Yang H, Feng HK, Yang GJ, Song XY (2015) Monitoring the ratio of leaf carbon to nitrogen in winter wheat with hyperspectral measurements. Proc. SPIE 9637, Remote Sensing for Agriculture, Ecosystems, and Hydrology XVII, 96371N. doi:10.1117/12.2194937

  • Zhang X, Liu F, He Y, Gong X (2013) Detecting macronutrients content and distribution in oilseed rape leaves based on hyperspectral imaging. Biosyst Eng 115:56–65

    Article  Google Scholar 

  • Zhao Y, Wang Y, Xu Z, Fu L (2015) Impacts of prescribed burning on soil greenhouse gas fluxes in a suburban native forest of south-eastern Queensland, Australia. Biogeosciences 12:6279–6290

    Article  CAS  Google Scholar 

Download references

Acknowledgements

The authors would like to gratefully thank Dr. Jie Liang, Ms. Suhad Lateef Mahmood Al-Khafaji, Mr. Naim Rastgoo and Ms. Negar Omidvar for their support and sharing their knowledge. This study has been funded by the Griffith University, Australia (grant number NSC 1010).

Author information

Authors and Affiliations

  1. Environmental Futures Research Institute, School of Natural Sciences, Griffith University, Nathan, Brisbane, QLD, 4111, Australia

    Iman Tahmasbian, Zhihong Xu, Kadum Abdullah & Shahla Hosseini Bai

  2. School of Information and Communication Technology, Nathan Campus, Griffith University, 170 Kessels Road, Brisbane, QLD, 4111, Australia

    Jun Zhou

  3. Faculty of Computing, University Technology Malaysia, 81300, Skudai, Johor, Malaysia

    Roya Esmaeilani

  4. Faculty of Science, Health, Education and Engineering, University of the Sunshine Coast, Maroochydore DC, QLD, 4558, Australia

    Thi Thu Nhan Nguyen & Shahla Hosseini Bai

Authors
  1. Iman Tahmasbian
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhihong Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Kadum Abdullah
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jun Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Roya Esmaeilani
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Thi Thu Nhan Nguyen
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Shahla Hosseini Bai
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Iman Tahmasbian or Zhihong Xu.

Additional information

Responsible editor: Xiuping Jia

Electronic supplementary material

ESM 1

(DOCX 23 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tahmasbian, I., Xu, Z., Abdullah, K. et al. The potential of hyperspectral images and partial least square regression for predicting total carbon, total nitrogen and their isotope composition in forest litterfall samples. J Soils Sediments 17, 2091–2103 (2017). https://doi.org/10.1007/s11368-017-1751-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11368-017-1751-z

Keywords

Search

Navigation