Caelin P. Celani
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Caelin P. Celani has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Karl S. Booksh
University of Delaware
8 shared publications - James A. Jordan
United States Geological Survey
6 shared publications - Hélder Vinicius Carneiro da Silva
University of Delaware
4 shared publications - Erin R. Price
U.S. Forest Service International Programs, Wood Identification and Screening Center, Ashland, Oregon, USA
3 shared publications Kierra R. Cano
U.S. Forest Service International Programs, Wood Identification and Screening Center, Ashland, Oregon, USA
3 shared publicationsMichael E. Ketterer
Department of Chemistry and Biochemistry, Northern Arizona University, Room 400, Building 36, 700 South Osborne Drive, Flagstaff, Arizona 86011-5698, USA
3 shared publications
Latest Publications
- 28 April 2026
- Published by SAGE Publications in Applied Spectroscopy
- Vol. 80 (7) , 720-733
-Stacked Machine Learning for Timber Identification Using LaserInduced Breakdown Spectroscopy
This study presents a new approach to wood species identification using laser-induced breakdown spectroscopy (LIBS) combined with stacked machine learning techniques. The research analyzed 700 samples comprising nine Dalbergia species and nine additional tropical timber species, utilizing a handheld LIBS analyzer. A stacking methodology was developed by integrating three support vector machine (SVM) models with different kernel functions (linear, polynomial, and radial) in a one-versus-all (OVA) configuration. These SVM outputs were then combined using a partial least squares discriminant analysis (PLS-DA) meta-learner. Through PCA-based variable selection, the dimensionality was reduced from 23 401 to wavelengths while maintaining classification accuracy. The stacking approach achieved a Cohen's kappa value of 0.8671 in the validation set, significantly outperforming traditional flat classifiers. Variable importance analysis revealed calcium, magnesium, and barium as crucial elements for species differentiation, with their concentrations reflecting environmental conditions and geographical origins. This research demonstrates the potential of combining LIBS spectroscopy with advanced machine learning techniques for rapid, non-invasive timber identification, which can support efforts against illegal logging and enforcement of international trade regulations.
- 28 April 2026
- Published by SAGE Publications in Applied Spectroscopy
- Vol. 80 (7) , 720-733
-Stacked Machine Learning for Timber Identification Using LaserInduced Breakdown Spectroscopy
This study presents a new approach to wood species identification using laser-induced breakdown spectroscopy (LIBS) combined with stacked machine learning techniques. The research analyzed 700 samples comprising nine Dalbergia species and nine additional tropical timber species, utilizing a handheld LIBS analyzer. A stacking methodology was developed by integrating three support vector machine (SVM) models with different kernel functions (linear, polynomial, and radial) in a one-versus-all (OVA) configuration. These SVM outputs were then combined using a partial least squares discriminant analysis (PLS-DA) meta-learner. Through PCA-based variable selection, the dimensionality was reduced from 23 401 to wavelengths while maintaining classification accuracy. The stacking approach achieved a Cohen's kappa value of 0.8671 in the validation set, significantly outperforming traditional flat classifiers. Variable importance analysis revealed calcium, magnesium, and barium as crucial elements for species differentiation, with their concentrations reflecting environmental conditions and geographical origins. This research demonstrates the potential of combining LIBS spectroscopy with advanced machine learning techniques for rapid, non-invasive timber identification, which can support efforts against illegal logging and enforcement of international trade regulations.
- 12 August 2025
- Published by SAGE Publications in Applied Spectroscopy
- Vol. 79 (9) , 1398-1408
Determination of Provenance Soil Type Using Inductively Coupled Plasma Mass Spectrometry (ICP-MS) Analyses of Pinus ponderosa Ash
This study demonstrates the feasibility of determining soil provenance from tree ash composition using elemental analysis and chemometric techniques. To date, no published studies have applied chemometric approaches to classify ash for provenance determination following forest fires. In this work, Pinus ponderosa ash was analyzed to distinguish samples based on soil type and geographic location. Pinus ponderosa , a widely distributed pine species in the western United States where wildfires are prevalent, was selected as a model system. Needles were collected from trees grown in five distinct soil types across northern Arizona and Colorado, then dry-ashed under controlled conditions. Classification was performed using three preprocessing techniques and five machine learning algorithms, including hierarchical modeling structures to optimize separation. Partial least squares discriminant analysis (PLS-DA) following a Box-Cox transformation yielded the highest classification accuracy, achieving a prediction kappa value of 0.98 for soil type identification. However, classification performance decreased when distinguishing both soil type and geographic location, indicating that additional variability may influence predictive accuracy in broader applications. These findings highlight the potential of inductively coupled plasma mass spectrometry (ICP-MS) and machine learning for post-wildfire forensic analysis and environmental monitoring.
- 12 August 2025
- Published by SAGE Publications in Applied Spectroscopy
- Vol. 79 (9) , 1398-1408
Determination of Provenance Soil Type Using Inductively Coupled Plasma Mass Spectrometry (ICP-MS) Analyses of Pinus ponderosa Ash
This study demonstrates the feasibility of determining soil provenance from tree ash composition using elemental analysis and chemometric techniques. To date, no published studies have applied chemometric approaches to classify ash for provenance determination following forest fires. In this work, Pinus ponderosa ash was analyzed to distinguish samples based on soil type and geographic location. Pinus ponderosa , a widely distributed pine species in the western United States where wildfires are prevalent, was selected as a model system. Needles were collected from trees grown in five distinct soil types across northern Arizona and Colorado, then dry-ashed under controlled conditions. Classification was performed using three preprocessing techniques and five machine learning algorithms, including hierarchical modeling structures to optimize separation. Partial least squares discriminant analysis (PLS-DA) following a Box-Cox transformation yielded the highest classification accuracy, achieving a prediction kappa value of 0.98 for soil type identification. However, classification performance decreased when distinguishing both soil type and geographic location, indicating that additional variability may influence predictive accuracy in broader applications. These findings highlight the potential of inductively coupled plasma mass spectrometry (ICP-MS) and machine learning for post-wildfire forensic analysis and environmental monitoring.
- 12 July 2025
- Published by Wiley in Journal of Chemometrics
- Vol. 39 (7) , e70048
The Classification Limit of Detection: Estimating Sample‐Level Classification Uncertainty in Spectroscopy Using Monte Carlo Error Propagation of Spectral Noise
This study presents a novel Monte Carlo–based methodology for estimating classification uncertainty in chemometric models by propagating spectral measurement noise. Unlike traditional approaches that treat classification as deterministic, this method simulates realistic noise structures, both independent and correlated, captured from multiple spectrum measurements to quantify sample‐specific uncertainty. The technique is applicable to both linear and non‐linear models, including partial least squares discriminant analysis (PLS‐DA) and various support vector machine (SVM) kernels. The methodology was validated using three datasets: synthetic 2D simulations for controlled model geometry, X‐ray fluorescence (XRF) spectra from colored glass rods, and laser‐induced breakdown spectroscopy (LIBS) data from Dalbergia wood species. Results revealed that uncertainty increases with spectral similarity and perpendicular alignment between noise structures and decision boundaries. In real‐world applications, classification metrics alone proved insufficient to assess model reliability. The inclusion of uncertainty intervals enabled identification of ambiguous predictions even in cases of perfect classification accuracy. This work advances chemometric analysis by linking measurement uncertainty to classification outcomes, offering a robust framework for decision‐making in high‐stakes analytical contexts.
- 12 July 2025
- Published by Wiley in Journal of Chemometrics
- Vol. 39 (7) , e70048
The Classification Limit of Detection: Estimating Sample‐Level Classification Uncertainty in Spectroscopy Using Monte Carlo Error Propagation of Spectral Noise
This study presents a novel Monte Carlo–based methodology for estimating classification uncertainty in chemometric models by propagating spectral measurement noise. Unlike traditional approaches that treat classification as deterministic, this method simulates realistic noise structures, both independent and correlated, captured from multiple spectrum measurements to quantify sample‐specific uncertainty. The technique is applicable to both linear and non‐linear models, including partial least squares discriminant analysis (PLS‐DA) and various support vector machine (SVM) kernels. The methodology was validated using three datasets: synthetic 2D simulations for controlled model geometry, X‐ray fluorescence (XRF) spectra from colored glass rods, and laser‐induced breakdown spectroscopy (LIBS) data from Dalbergia wood species. Results revealed that uncertainty increases with spectral similarity and perpendicular alignment between noise structures and decision boundaries. In real‐world applications, classification metrics alone proved insufficient to assess model reliability. The inclusion of uncertainty intervals enabled identification of ambiguous predictions even in cases of perfect classification accuracy. This work advances chemometric analysis by linking measurement uncertainty to classification outcomes, offering a robust framework for decision‐making in high‐stakes analytical contexts.
- Open Access
- 19 March 2025
- Published by Elsevier in Talanta Open
- Vol. 11
Geographic determination of Pinus ponderosa using DART TOFMS, ICP-MS, and LIBS handheld analyzer
- 19 March 2025
- Published by Elsevier in Talanta Open
- Vol. 11
Open AccessGeographic determination of Pinus ponderosa using DART TOFMS, ICP-MS, and LIBS handheld analyzer
- 6 March 2025
- Published by Wiley in Journal of Chemometrics
- Vol. 39 (3)
Assessing Classification Models of Pharmaceuticals With Conformal Prediction
Conformal predictions transform a measurable, heuristic notion of uncertainty into statistically valid confidence intervals such that, for a future sample, the true class prediction will be included in the conformal prediction set at a predetermined confidence. In a Bayesian perspective, common estimates of uncertainty in multivariate classification, namely p ‐values, only provide the probability that the data fits the presumed class model, P(D|M) . Conformal predictions, on the other hand, address the more meaningful probability that a model fits the data, P(M|D) . Herein, two methods to perform inductive conformal predictions are investigated—the traditional Split Conformal Prediction that uses an external calibration set and a novel Bagged Conformal Prediction, closely related to Cross Conformal Predictions, that utilizes bagging to calibrate the heuristic notions of uncertainty. Methods for preprocessing the conformal prediction scores to improve performance are discussed and investigated. These conformal prediction strategies are applied to identifying four non‐steroidal anti‐inflammatory drugs (NSAIDs) from hyperspectral Raman imaging data. In addition to assigning meaningful confidence intervals on the model results, we herein demonstrate how conformal predictions can add additional diagnostics for model quality and method stability.
- 6 March 2025
- Published by Wiley in Journal of Chemometrics
- Vol. 39 (3)
Assessing Classification Models of Pharmaceuticals With Conformal Prediction
Conformal predictions transform a measurable, heuristic notion of uncertainty into statistically valid confidence intervals such that, for a future sample, the true class prediction will be included in the conformal prediction set at a predetermined confidence. In a Bayesian perspective, common estimates of uncertainty in multivariate classification, namely p ‐values, only provide the probability that the data fits the presumed class model, P(D|M) . Conformal predictions, on the other hand, address the more meaningful probability that a model fits the data, P(M|D) . Herein, two methods to perform inductive conformal predictions are investigated—the traditional Split Conformal Prediction that uses an external calibration set and a novel Bagged Conformal Prediction, closely related to Cross Conformal Predictions, that utilizes bagging to calibrate the heuristic notions of uncertainty. Methods for preprocessing the conformal prediction scores to improve performance are discussed and investigated. These conformal prediction strategies are applied to identifying four non‐steroidal anti‐inflammatory drugs (NSAIDs) from hyperspectral Raman imaging data. In addition to assigning meaningful confidence intervals on the model results, we herein demonstrate how conformal predictions can add additional diagnostics for model quality and method stability.
- 12 February 2025
- Published by USDA Forest Service
Geographic determination data for southern Oregon Pinus ponderosa using DART TOFMS, ICP-MS, and LIBS handheld analyzer
This archive contains research data collected and/or funded by Forest Service Research and Development (FS R&D), U.S. Department of Agriculture. It is a resource for accessing both short and long-term FS R&D research data, which includes Experimental Forest and Range data. It is a way to both preserve and share the quality science of our researchers.
- 12 February 2025
- Published by USDA Forest Service
Geographic determination data for southern Oregon Pinus ponderosa using DART TOFMS, ICP-MS, and LIBS handheld analyzer
This archive contains research data collected and/or funded by Forest Service Research and Development (FS R&D), U.S. Department of Agriculture. It is a resource for accessing both short and long-term FS R&D research data, which includes Experimental Forest and Range data. It is a way to both preserve and share the quality science of our researchers.
- 23 October 2023
- Published by Royal Society of Chemistry (RSC) in The Analyst
- Vol. 148 (23) , 6097-6108
Supervised discretization for decluttering classification models
Supervised discretization ‘declutters’ chemical sensor data to sharpen the observed differences between classes and improve multivariate classification models.
- 23 October 2023
- Published by Royal Society of Chemistry (RSC) in The Analyst
- Vol. 148 (23) , 6097-6108
Supervised discretization for decluttering classification models
Supervised discretization ‘declutters’ chemical sensor data to sharpen the observed differences between classes and improve multivariate classification models.
- 8 May 2023
- Published by Wiley in Journal of Chemometrics
- Vol. 38 (5)
Evaluation of spectral collection strategies for identification of Dalbergia spp. using handheld laser‐induced breakdown spectroscopy
The illegal timber trade has significant impact on the survival of endangered tropical hardwood species like Dalbergia spp. (rosewood), a world‐wide protected genus from the Convention on International Trade in Endangered Species of Wild Fauna and Flora (CITES). Due to increased threat to Dalbergia spp., and lack of action to reduce threats, port of entry analysis methods are required to identify Dalbergia spp. Handheld laser‐induced breakdown spectroscopy (LIBS) has been shown to be capable of identifying species and establishing provenance of Dalbergia spp. and other tropical hardwoods, but analysis methods for this work have yet to be investigated in detail. The present work investigates five well‐known algorithms—partial least squares discriminant analysis (PLS‐DA), classification and regression trees (CART), k‐nearest neighbor (k‐NN), random forest (RF), and support vector machine (SVM)—two training/test set sampling regimes, and data collection at two signal‐to‐noise (S/N) ratios to assess the potential for handheld LIBS analyses. Additionally, imbalanced classes are addressed. For this application, SVM and RF yield near identical results (though RF takes nearly 100 longer to compute), while the S/N ratio has a significant effect on model success assuming all else is equal. It was found that forming a training set with replicate low S/N analyses can perform as well as higher precision training sets for true prediction, even if the predicted samples have low signal to noise! This work confirms handheld LIBS analyzers can provide a viable method for classification of hardwood species, even within the same genus.
- 8 May 2023
- Published by Wiley in Journal of Chemometrics
- Vol. 38 (5)
Evaluation of spectral collection strategies for identification of Dalbergia spp. using handheld laser‐induced breakdown spectroscopy
The illegal timber trade has significant impact on the survival of endangered tropical hardwood species like Dalbergia spp. (rosewood), a world‐wide protected genus from the Convention on International Trade in Endangered Species of Wild Fauna and Flora (CITES). Due to increased threat to Dalbergia spp., and lack of action to reduce threats, port of entry analysis methods are required to identify Dalbergia spp. Handheld laser‐induced breakdown spectroscopy (LIBS) has been shown to be capable of identifying species and establishing provenance of Dalbergia spp. and other tropical hardwoods, but analysis methods for this work have yet to be investigated in detail. The present work investigates five well‐known algorithms—partial least squares discriminant analysis (PLS‐DA), classification and regression trees (CART), k‐nearest neighbor (k‐NN), random forest (RF), and support vector machine (SVM)—two training/test set sampling regimes, and data collection at two signal‐to‐noise (S/N) ratios to assess the potential for handheld LIBS analyses. Additionally, imbalanced classes are addressed. For this application, SVM and RF yield near identical results (though RF takes nearly 100 longer to compute), while the S/N ratio has a significant effect on model success assuming all else is equal. It was found that forming a training set with replicate low S/N analyses can perform as well as higher precision training sets for true prediction, even if the predicted samples have low signal to noise! This work confirms handheld LIBS analyzers can provide a viable method for classification of hardwood species, even within the same genus.
- 28 July 2022
- Published by Wiley in Journal of Chemometrics
- Vol. 37 (3)
Visualization of confusion matrices with network graphs
The use of network analysis as a means of visualizing the off‐diagonal (misclassified) elements of a confusion matrix is demonstrated, and the potential to use the network graphs as a guide for developing hierarchical classification models is presented. A very brief summary of graph theory is described. This is followed by an explanation and code with examples of how these networks can then be used for visualization of confusion matrices. The use of network graphs to provide insight into differing model performance is also addressed.
- 28 July 2022
- Published by Wiley in Journal of Chemometrics
- Vol. 37 (3)
Visualization of confusion matrices with network graphs
The use of network analysis as a means of visualizing the off‐diagonal (misclassified) elements of a confusion matrix is demonstrated, and the potential to use the network graphs as a guide for developing hierarchical classification models is presented. A very brief summary of graph theory is described. This is followed by an explanation and code with examples of how these networks can then be used for visualization of confusion matrices. The use of network graphs to provide insight into differing model performance is also addressed.
- 10 July 2019
- Published by Royal Society of Chemistry (RSC) in The Analyst
- Vol. 144 (17) , 5117-5126
Assessing utility of handheld laser induced breakdown spectroscopy as a means ofDalbergiaspeciation
Many species of Dalbergia are prized hardwoods, generally referred to as ‘Rosewood,’ and used in high-end products due to their distinctive hue and scent. Despite more than 58 species of Dalbergia being listed as endangered in Appendix 1 of The Convention on International Trade in Endangered Species of Fauna and Flora (CITES), the illegal logging and trade of this timber is ongoing. In this work, a handheld laser induced breakdown spectrometer (LIBS) was used to analyze seven Dalbergia species and two other exotic hardwood species to evaluate the ability of handheld LIBS for rapid classification of Dalbergia in the field. The KNN model of the classification presented 80% to 90% sensitivity for discriminating between Dalbergia species in the training set. PLS-DA models were based on a binary decision tree structure. Cumulatively, the PLS-DA decision tree model showed greater than 97% sensitivity and 99% selectivity for prediction of Dalbergia species included in the training set. The data presented in the following study are promising for the use of handheld LIBS devices and both KNN and PLS-DA models for applications in customs screenings at the port of entry of hard woods, among others.
- 10 July 2019
- Published by Royal Society of Chemistry (RSC) in The Analyst
- Vol. 144 (17) , 5117-5126
Assessing utility of handheld laser induced breakdown spectroscopy as a means ofDalbergiaspeciation
Many species of Dalbergia are prized hardwoods, generally referred to as ‘Rosewood,’ and used in high-end products due to their distinctive hue and scent. Despite more than 58 species of Dalbergia being listed as endangered in Appendix 1 of The Convention on International Trade in Endangered Species of Fauna and Flora (CITES), the illegal logging and trade of this timber is ongoing. In this work, a handheld laser induced breakdown spectrometer (LIBS) was used to analyze seven Dalbergia species and two other exotic hardwood species to evaluate the ability of handheld LIBS for rapid classification of Dalbergia in the field. The KNN model of the classification presented 80% to 90% sensitivity for discriminating between Dalbergia species in the training set. PLS-DA models were based on a binary decision tree structure. Cumulatively, the PLS-DA decision tree model showed greater than 97% sensitivity and 99% selectivity for prediction of Dalbergia species included in the training set. The data presented in the following study are promising for the use of handheld LIBS devices and both KNN and PLS-DA models for applications in customs screenings at the port of entry of hard woods, among others.