Abstract
Laser-induced breakdown spectroscopy (LIBS) has been applied to the analysis of three chromium-doped soils. Two chemometric techniques, principal components analysis (PCA) and neural networks analysis (NNA), were used to discriminate the soils on the basis of their LIBS spectra. An excellent rate of correct classification was achieved and a better ability of neural networks to cope with real-world, noisy spectra was demonstrated. Neural networks were then used for measuring chromium concentration in one of the soils. We performed a detailed optimization of the inputs of the network so as to improve its predictive performances and we studied the effect of the presence of matrix-specific information in the inputs examined. Finally the inputs of the network—the spectral intensities—were replaced by the line areas. This provided the best results with a prediction accuracy and precision of about 5% in the determination of chromium concentration and a significant reduction of the data, too.
Similar content being viewed by others
References
Wisbrun R, Schechter I, Niessner R, Schroeder H, Kompa KL (1994) Anal Chem 66:2964–2975
Lazic V, Barbini R, Colao F, Fantoni R, Palucci A (2001) Spectrochim Acta Part B 56:807–820
Mosier-Boss PA, Lieberman SH, Theriault GA (2002) Environ Sci Technol 36:3968–3976
Bustamante MF, Rinaldi CA, Ferrero JC (2002) Spectrochim Acta Part B 57:303–309
Hilbk-Kortenbruck F, Noll R, Wintjens P, Falk H, Becker C (2001) Spectrochim Acta Part B 56:933–945
Wainner RT, Harmon RS, Miziolek AW, McNesby KL, French PD (2001) Spectrochim Acta Part B 56:777–793
Capitelli F, Colao F, Provenzano MR, Fantoni R, Brunetti G, Senesi N (2002) Geoderma 106:45–62
Eppler AS, Cremers DA, Hickmott DD, Ferris MJ, Koskelo AC (1996) Appl Spectrosc 50:1175–1181
Bauer HE, Leis F, Niemax K (1998) Spectrochim Acta Part B 53:1815–1825
Detalle V, Héon R, Sabsabi M, St-Onge L (2001) Spectrochim Acta Part B 56:1011–1025
Fichet P, Menut D, Brennetot R, Vors E, Rivoallan A (2003) Appl Opt 42:6029–6035
Sirven JB, Bousquet B, Canioni L, Sarger L (2005) Anal Chem (accepted)
Adams MJ (2004) Chemometrics in analytical spectroscopy, 2nd edn. RSC, Cambridge, UK
Hybl JD, Lithgow GA, Buckley SG (2003) Appl Spectrosc 57:1207–1215
Goode SR, Morgan SL, Hoskins R, Oxsher A (2000) J Anal At Spectrom 9:1133–1138
Martin MZ, Labbé N, Rials TG, Wullschleger SD (2005) Spectrochim Acta Part B 60:1179–1185
Samek O, Telle HH, Beddows DCS (2001) BMC Oral Health 1:1
Samuels AC, De Lucia FC Jr, McNesby KL, Miziolek AW (2003) Appl Opt 42:6205–6209
Munson CA, De Lucia FC Jr, Piehler T, McNesby KL, Miziolek AW (2005) Spectrochim Acta Part B 60:1217–1224
Beale R, Jackson T (1991) Neural computing: an introduction. Adam Hilger, Bristol
Dieterle F, Busche S, Gauglitz G (2004) Anal Bioanal Chem 380:383–396
Acknowledgements
We gratefully thank Jean-Pierre Dubost (Université Bordeaux 2, France) for the fruitful discussions on chemometrics. This research is financially supported by ANR, ADEME and Conseil Régional d’Aquitaine.
Author information
Authors and Affiliations
Corresponding author
Additional information
Awarded a poster prize on the occasion of the Euro-Mediterranean Symposium on Laser-induced Breakdown Spectroscopy (EMSLIBS 2005), Aachen, Germany, 6–9 September 2005.
Rights and permissions
About this article
Cite this article
Sirven, JB., Bousquet, B., Canioni, L. et al. Qualitative and quantitative investigation of chromium-polluted soils by laser-induced breakdown spectroscopy combined with neural networks analysis. Anal Bioanal Chem 385, 256–262 (2006). https://doi.org/10.1007/s00216-006-0322-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00216-006-0322-8