Sage Journals: Discover world-class research

Abstract

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.

Graphical abstract

This is a visual representation of the abstract.

Keywords

Classification support vector machines SVM stacked generalization multivariate analysis Convention on International Trade in Endangered Species of Wild Fauna and Flora CITES

Get full access to this article

View all access options for this article.

References

U.S. Customs and Border Protection. “Illegal Logging”. https://www.cbp.gov/trade/programs-administration/natural-resources-protection/illegal-logging [accessed 7 April 2026].

The International Criminal Police Organization (INTERPOL). “Forestry Crime”. https://www.interpol.int/en/Crimes/Environmental-crime/Forestry-crime [accessed 7 April 2026].

Elias

. “Logging and the Law: How the U.S. Lacey Act Helps Reduce Illegal Logging in the Tropics”. https://www.ucs.org/sites/default/files/2019-09/illegal-logging-and-lacey-act.pdf [accessed 7 April 2026].

Asia–Pacific Economic Cooperation (APEC). “As Climate Change Gets Worse, Forests Must be Protected from Illegal Activity”. https://www.apec.org/press/features/2023/as-climate-change-gets-worse-forests-must-be-protected-from-illegal-activity [accessed 7 April 2026].

Observatory of Economic Complexity (OEC). “Wood Products”. https://oec.world/en/profile/hs/wood-products [accessed 7 April 2026].

Sheikh

P.A.

. “The Lacey Act: Compliance Issues Related to Importing Plants and Plant Products”. https://www.congress.gov/crs-product/R42119 [accessed 7 April 2026]. Pp. 29–57.

Cody

R.B.

Dane

A.J.

Dawson-Andoh

Adedipe

E.O.

Nkansah

. “Rapid Classification of White Oak (Quercus alba) and Northern Red Oak (Quercus rubra) by Using Pyrolysis Direct Analysis in Real Time (DARTTM) and Time-of-Flight Mass Spectrometry”. J. Anal. Appl. Pyrolysis. 2012. 95: 134–137. 10.1016/j.jaap.2012.01.018

Price

E.R.

McClure

P.J.

Huffman

A.N.

Voin

Espinoza

E.O.

. “Reliability of Wood Identification Using DART-TOFMS and the ForeST Database: A Validation Study”. Forensic Sci. Int. Anim. Environ. 2022. 2: 100045. 10.1016/j.fsiae.2022.100045

Kisser

J.G.

Ylinen

Freudenberg

, et al. “History of Wood Science”. Wood Sci. Technol. 1967. 1: 161–190. 10.1007/BF00350460

10.

Wheeler

E.A.

. “Inside Wood: A Web Resource for Hardwood Anatomy”. IAWA J. 2011. 32(2): 199–211.

11.

Van Brusselen

Cramm

Tegegne

Y.T.

. “Wood Identification Services in Support of Legal Supply Chains: A Market Study”. Sustain. Futur. 2023. 6: 100128. 10.1016/j.sftr.2023.100128

12.

Convention on International Trade in Endangered Species of Wild Fauna and Flora (CITES). “The CITES Appendices”. https://cites.org/eng/app/index.php [accessed 7 April 2026].

13.

Fatima

Srivastava

Hanur

V.S.

Rao

M.S.

. “An Effective Wood DNA Extraction Protocol for Three Economic Important Timber Species of India”. Am. J. Plant Sci. 2018. 9(2): 139–149.

14.

Convention on International Trade in Endangered Species of Wild Fauna and Flora (CITES). “Ninth Meeting of the Conference of Parties: Proposals for Amendment of the Appendices”. https://cites.org/eng/cop/19/amendment-proposals [accessed 7 April 2026].

15.

Convention on International Trade in Endangered Species of Wild Fauna and Flora (CITES). “New Guidance to Protect Priority Rosewood Species in Trade”. https://cites.org/eng/news/pr/new-guidance-to-protect-priority-rosewood-species-in-trade-pc27 [accessed 7 April 2026].

16.

Groves

Rutherford

. “CITES and Timber: A Guide to CITES-Listed Tree Species”. https://cites.org/sites/default/files/timber_id_materials/files/CITES%20%20Timber%20-%20A%20guide%20to%20CITES-listed%20tree%20species%202023.pdf [accessed 7 April 2026].

17.

U.S. Department of Agriculture, Animal, and Plant Health Inspection Service (APHIS). “Lacey Act Declaration Requirements”. https://www.aphis.usda.gov/plant-imports/file-lacey-act-declaration/requirements [accessed 7 April 2026].

18.

Celani

C.P.

Lancaster

C.A.

Jordan

J.A.

Espinoza

E.O.

., et al. “Assessing Utility of Handheld Laser Induced Breakdown Spectroscopy as a Means of Dalbergia Speciation”. Analyst. 2019. 144(17): 5117–5126.

19.

Kouiroukidis

Evangelidis

. “The Effects of Dimensionality Curse in High Dimensional KNN Search”. In: Proceedings 2011 Panhellenic Conference on Informatics. Kastoria, Greece; 30 September–2 October 2011. Pp. 41–45. 10.1109/PCI.2011.45

20.

Peng

Gui

. “Interpreting the Curse of Dimensionality from Distance Concentration and Manifold Effect”. ArXiv. 2023. 10.48550/arXiv.2401.00422

21.

Wolpert

D.H.

. “Stacked Generalization”. Neural Netw. 1992. 5(2): 241–259.

22.

Naimi

A.I.

Balzer

L.B.

. “Stacked Generalization: An Introduction to Super Learning”. Eur. J. Epidemiol. 2018. 33(5): 459–464.

23.

Sharma

S.R.

Singh

Kaur

. “A Novel Approach of Ensemble Methods Using the Stacked Generalization for High-Dimensional Datasets”. IETE J. Res. 2023. 69(1): 6802–6817.

24.

Cui

Wang

Wei

Teng

. “Laser-Induced Breakdown Spectroscopy for the Classification of Wood Materials Using Machine Learning Methods Combined with Feature Selection”. Plasma Sci. Technol. 2021. 23(5): 055505.

25.

Roman

Santana

Mendiburu

Lozano

J.A.

. “In-Depth Analysis of SVM Kernel Learning and Its Components”. Neural Comput. Appl. 2021. 33: 6575–6594. 10.1007/s00521-020-05419-z

26.

R Core Team. “The R Project for Statistical Computing”. https://www.r-project.org/ [accessed 7 April 2026].

27.

Posit Software, PBC. “RStudio: Integrated Development Environment for R”. https://posit.co/downloads/ [accessed 7 April 2026].

28.

Liland

K.H.

Almøy

Mevik

B.-H.

. “Optimal Choice of Baseline Correction for Multivariate Calibration of Spectra”. Appl. Spectrosc. 2010. 64(9): 1007–1016.

29.

Kuhn

. “Caret: Classification and Regression Training”. https://cran.r-project.org/web/packages/caret/caret.pdf [accessed 7 April 2026].

30.

Folashade

, Microsoft Corporation, Weston

Tenenbaum

. “DoParallel: Foreach Parallel Adaptor for the “parallel” Package”. 10.32614/CRAN.package.doParallel

31.

Wickham

Bryan

. “Readxl: Read Excel Files”. https://readxl.tidyverse.org/ [accessed 7 April 2026].

32.

Wickham

François

Henry

Müller

Vaughan

. “Dplyr: A Grammar of Data Manipulation”. https://dplyr.tidyverse.org/ [accessed 7 April 2026].

33.

Wickham

. Ggplot2: Elegant Graphics for Data Analysis. New York: Springer-Verlag, 2016.

34.

Crocombe

R.A

. “Portable Spectroscopy”. Appl. Spectrosc. 2018. 72(12): 1701–1751.

35.

Peng

Jiang

Wei

, et al. “Asymmetric Least Squares for Multiple Spectra Baseline Correction”. Anal. Chim. Acta. 2010. 683(1): 63–68.

36.

Cotacallapa

Saboya

Canas Rodrigues

Salas

, et al. “A Flat-Hierarchical Approach Based on Machine Learning Model for E-Commerce Product Classification”. IEEE Access. 2024. 12: 72730–72745. 10.1109/ACCESS.2024.3400693

37.

Borchers

H.W.

. “Pracma: Practical Numerical Math Functions”. https://cran.r-project.org/web/packages/pracma/pracma.pdf [accessed 7 April 2026].

38.

Kramida

Olsen

Ralchenko

Yu.

. “NIST LIBS Database”. https://physics.nist.gov/PhysRefData/ASD/LIBS/libs-form.html [accessed 7 April 2026].

39.

Nichols

T.R.

Wisner

P.M.

Cripe

Gulabchand

. “Putting the Kappa Statistic to Use”. Qual. Assur. J. 2010. 13: 57–61. 10.1002/qaj.481

40.

Greenwell

B.M.

Boehmke

B.C.

. “Variable Importance Plots: An Introduction to the Vip Package”. R J. 2020. 12: 343.

41.

White

P.J.

Broadley

M.R.

. “Calcium in Plants”. Ann. Bot. 2003. 92(4): 487–511.

42.

Ishfaq

Wang

Yan

Wang

, et al. “Physiological Essence of Magnesium in Plants and Its Widespread Deficiency in the Farming System of China”. Front. Plant Sci. 2022. 13: 802274. 10.3389/fpls.2022.802274

43.

Sleimi

Kouki

Hadj Ammar

Ferreira

, et al. “Barium Effect on Germination, Plant Growth, and Antioxidant Enzymes in Cucumis sativus L. Plants”. Food Sci. Nutr. 2021. 9(4): 2086–2094.

44.

Hänsch

Mendel

R.R.

. “Physiological Functions of Mineral Micronutrients (Cu, Zn, Mn, Fe, Ni, Mo, B, Cl)”. Curr. Opin. Plant Biol. 2009. 12(3): 259–266.

45.

Yang

Wendroth

Walton

R.J.

. “Field-Scale Bromide Leaching as Affected by Land Use and Rain Characteristics”. Soil Sci. Soc. Am. J. 2013. 77(4): 1157–1167.

46.

Land

Ingri

Andersson

P.S.

Öhlander

. “Ba/Sr, Ca/Sr and 87Sr/86Sr Ratios in Soil Water and Groundwater: Implications for Relative Contributions to Stream Water Discharge”. Appl. Geochem. 2000. 15(3): 311–325.

47.

Flem

Reimann

Fabian

. “Excess Cr and Ni in Top Soil: Comparing the Effect of Geology, Diffuse Contamination, and Biogenic Influence”. Sci. Total Environ. 2022. 843: 157059. 10.1016/j.scitotenv.2022.157059

48.

Kathpalia

Bhatla

S.C.

. “Plant Mineral Nutrition”. In: Plant Physiology, Development, and Metabolism. Singapore: Springer Nature, 2018. Chap. 2, Pp. 37–81.

49.

Singh

Schulze

D.G.

. “Soil Minerals and Plant Nutrition”. Nat. Educ. Knowl. Proj. 2015. 6(1): 1.

50.

Sotuyo

Contreras-Jiménez

Gagnon

Lewis

G.P.

. “A Synopsis of Coulteria (Leguminosae), Including New Names and Synonyms”. Phytotaxa. 2017. 291(1): 33–42.

51.

Campo

Maass

J.M.

Jaramillo

V.J.

Yrízar

A.M.

. “Calcium, Potassium, and Magnesium Cycling in a Mexican Tropical Dry Forest Ecosystem”. Biogeochemistry. 2000. 49: 21–36. 10.1023/A:1006207319622

52.

Mahatara

Acharya

A.K.

Dhakal

B.P.

Sharma

D.K.

, et al. “Maxent Modelling for Habitat Suitability of Vulnerable Tree Dalbergia latifolia in Nepal”. Silva Fenn. 2021. 55(4): 10441.

53.

Nogueira

F.C.B.

Filho

S.M.

Baldoni

R.N.

e Silva

T.A.S.

. “Is the Seed Dispersal Related to Spatial Pattern of Individuals in Populations? The Case of Dalbergia cearensis”. Am. J. Plant Sci. 2014. 5(20): 2997–3004.

54.

Speed

M.P.

Arbuckle

. “Quantification Provides a Conceptual Basis for Convergent Evolution”. Biol. Rev. 2017. 92(2): 815–829.

55.

Rehfeldt

G.E.

. “Genetic Differentiation among Populations of Pinus ponderosa from the Upper Colorado River Basin”. Bot. Gaz. 1990. 151(1): 125–137.

56.

Medvigy

Wang

Zhu

Riley

W.J.

, et al. “Observed Variation in Soil Properties Can Drive Large Variation in Modelled Forest Functioning and Composition During Tropical Forest Secondary Succession”. New Phytol. 2019. 223(4): 1820–1833.

57.

O'Green

A.T.

. “Soil Water Dynamics”. Nat. Educ. Knowl. 2013. 4(5): 9.

58.

Dehkordi

M.M.

Nodeh

Z.P.

Dehkordi

K.S.

Khorjestan

R.R.

, et al. “Soil, Air, and Water Pollution from Mining and Industrial Activities: Sources of Pollution, Environmental Impacts, and Prevention and Control Methods”. Results Eng. 2024. 102729. 10.1016/j.rineng.2024.102729

59.

Dror

Yaron

Berkowitz

. “The Human Impact on All Soil-Forming Factors During the Anthropocene”. ACS Environ. Au. 2022. 2(1): 11–19.

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

8.43 MB

-Stacked Machine Learning for Timber Identification Using LaserInduced Breakdown Spectroscopy

Abstract

Keywords

Get full access to this article

References

Supplementary Material