Rapid classification of archaeological ceramics via laser-induced breakdown spectroscopy coupled with random forest

Abstract A laser-induced breakdown spectroscopy (LIBS) technique coupled with random forest (RF) was developed and used to classify ceramics from different dynasties. LIBS spectra of the ceramic surfaces were collected, and the major elements (Fe, Ca, Si, Al and Mg) in the ceramics identified using the NIST database. To obtain a better classification results, the LIBS spectra were subjected to five different pre-processing techniques (normalized by maximum integrated intensity, by extremum integrated intensity, mean centering, first-order derivative and second-order derivative). The input variables for RF modeling were selected and optimized by different variable importance threshold values (from 0 to 0.20) and four assessment criteria of out-of-bag (OOB) error, sensitivity, specificity and accuracy. LIBS spectra pre-processed by mean centering with a variable importance threshold value of 0.02 as the input variable were used to construct a RF classification model for different dynasty ceramics. Finally, the classification performance of the RF model was verified by the train set, OOB data and test set. The sensitivity, specificity and accuracy obtained by the RF model for the ceramics samples of test set were 0.8528, 0.9710 and 0.9433, respectively, which indicated a good classification performance.

[1]  Robert L. Tokar,et al.  Application of distance correction to ChemCam laser-induced breakdown spectroscopy measurements , 2016 .

[2]  J. A. Aguilera,et al.  Characterization of laser induced plasmas by optical emission spectroscopy: A review of experiments and methods , 2008 .

[3]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[4]  Zhihua Wang,et al.  In-situ Measurement of Sodium and Potassium Release during Oxy-Fuel Combustion of Lignite using Laser-Induced Breakdown Spectroscopy: Effects of O-2 and CO2 Concentration , 2013 .

[5]  A. Gualtieri,et al.  Accuracy in quantitative phase analysis of mixtures with large amorphous contents. The case of stoneware ceramics and bricks , 2014 .

[6]  Guanghui Niu,et al.  Classification of iron ores by laser-induced breakdown spectroscopy (LIBS) combined with random forest (RF) , 2015 .

[7]  Celio Pasquini,et al.  Ring-oven based preconcentration technique for microanalysis: simultaneous determination of Na, Fe, and Cu in fuel ethanol by laser induced breakdown spectroscopy. , 2013, Analytical chemistry.

[8]  Vincenzo Palleschi,et al.  Quantitative micro-analysis by laser-induced breakdown spectroscopy: a review of the experimental approaches☆ , 2002 .

[9]  G. Haertling.  Ferroelectric ceramics : History and technology , 1999 .

[10]  Michael D. Glascock,et al.  The forest or the trees? Behavioral and methodological considerations for geochemical characterization of heavily-tempered ceramic pastes using NAA and LA-ICP-MS , 2012 .

[11]  M. Carvalho,et al.  Synchrotron micro-XRF with Compound Refractive Lenses (CRLs) for tracing key elements on Portuguese glazed ceramics , 2012 .

[12]  F. J. Fortes,et al.  Laser-induced breakdown spectroscopy. , 2013, Analytical chemistry.

[13]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[14]  Hongsheng Tang,et al.  Classification of different types of slag samples by laser-induced breakdown spectroscopy (LIBS) coupled with random forest based on variable importance (VIRF) , 2015 .

[15]  B. Genc Oztoprak,et al.  Composition analysis of medieval ceramics by laser-induced breakdown spectroscopy (LIBS) , 2016 .

[16]  G. Malcheva,et al.  Investigation by laser induced breakdown spectroscopy, X-ray fluorescence and X-ray powder diffraction of the chemical composition of white clay ceramic tiles from Veliki Preslav , 2013 .

[17]  Roger C Wiens,et al.  Examining natural rock varnish and weathering rinds with laser-induced breakdown spectroscopy for application to ChemCam on Mars. , 2012, Applied optics.

[18]  M. Oujja,et al.  Laser induced breakdown spectroscopy for analysis and characterization of degradation pathologies of Roman glasses , 2013 .

[19]  C. Knappett,et al.  Mineralogical analysis and provenancing of ancient ceramics using automated SEM-EDS analysis (QEMSCAN®): a pilot study on LB I pottery from Akrotiri, Thera , 2011 .

[20]  Tianlong Zhang,et al.  Classification of steel samples by laser-induced breakdown spectroscopy and random forest , 2016 .

[21]  D. Cremers,et al.  Detection of pesticides and dioxins in tissue fats and rendering oils using laser-induced breakdown spectroscopy (LIBS). , 2013, Journal of agricultural and food chemistry.

[22]  Ulrich Panne,et al.  Multivariate classification of pigments and inks using combined Raman spectroscopy and LIBS , 2012, Analytical and Bioanalytical Chemistry.

[23]  R. Edrada-Ebel,et al.  A chemometric study of chromatograms of tea extracts by correlation optimization warping in conjunction with PCA, support vector machines and random forest data modeling. , 2009, Analytica chimica acta.

[24]  Reinhard Noll,et al.  Laser-induced breakdown spectroscopy for 24/7 automatic liquid slag analysis at a steel works. , 2014, Analytical chemistry.

[25]  M. Chen,et al.  Validation of an inductively coupled plasma mass spectrometry (ICP-MS) method for the determination of cerium, strontium, and titanium in ceramic materials used in radiological dispersal devices (RDDs). , 2007, Analytica chimica acta.

[26]  F. J. Fortes,et al.  Chronocultural sorting of archaeological bronze objects using laser-induced breakdown spectrometry , 2005 .

[27]  A. Ramil,et al.  Application of artificial neural networks for the rapid classification of archaeological ceramics by means of laser induced breakdown spectroscopy (LIBS) , 2008 .

[28]  Jeremiah Remus,et al.  Robust validation of pattern classification methods for laser-induced breakdown spectroscopy. , 2012, Applied optics.

[29]  Yixiang Duan,et al.  Laser-Induced Breakdown Spectroscopy: From Experimental Platform to Field Instrument , 2017 .

[30]  Yvette D. Mattley,et al.  Laser-induced breakdown spectroscopy: Sparking new applications , 2008 .

[31]  Ye Tian,et al.  Classification of wines according to their production regions with the contained trace elements using laser-induced breakdown spectroscopy , 2017 .

[32]  V. Detalle,et al.  Trace element quantification of lead based roof sheets of historical monuments by Laser Induced Breakdown Spectroscopy , 2015 .

[33]  D. Massart,et al.  Standardization of near-infrared spectrometric instruments , 1996 .

[34]  Demetrios Anglos,et al.  The application of LIBS for the analysis of archaeological ceramic and metal artifacts , 2002 .

[35]  Suresh D. Kulkarni,et al.  Analytical predictive capabilities of Laser Induced Breakdown Spectroscopy (LIBS) with Principal Component Analysis (PCA) for plastic classification , 2013 .