Leaf spectrum analysis of three tropical timber species: Diomate (Astronium graveolens), Choibá (Dipteryx oleifera), and Algarrobo (Hymenaea courbaril)
Análisis del espectro foliar de tres especies tropicales maderables: Diomate (Astronium graveolens), Choibá (Dipteryx oleifera), y Algarrobo (Hymenaea courbaril)
DOI:
https://doi.org/10.15446/rfnam.v77n3.112180Keywords:
Classification, Leaves, Separability, Spectral signature, Spectroradiometry, Tropical forest (en)Clasificación, Hojas, Separabilidad, Firma espectral, Espectrorradiometría, Bosque tropical (es)
Downloads
This study analyzed the leaf spectral response of three native timber forest species in the tropical dry forest: Diomate (Astronium graveolens Jacq.), Choibá (Dipteryx oleifera Benth.), and Algarrobo (Hymenaea courbaril L.). The study was conducted at the León Morales Soto Arboretum and Palmetum, at the Universidad Nacional de Colombia in Medellín, Antioquia, Colombia. Spectral data from the leaves were collected in situ using the portable spectroradiometer ASD FieldSpec HandHeld-2, which operates with a spectral resolution of 1 nm (resampled to 10 nm) and covers a spectral range between 325 and 1,075 nm (limited to 400-900 nm). Based on the measurements, the behavior and spectral variability of the species were evaluated. One-factor Analysis of Variance and Mann Whitney-Wilcoxon U-test were implemented in reflectance spectra to select the optimal narrow bands for species discrimination. The classification capacity of the selected narrow bands was assessed using the K-nearest neighbors’ algorithm. It was found that A. graveolens and H. courbaril exhibited spectral signatures typical of healthy vegetation, while D. oleifera showed spectral changes during the early stages of senescence. Regarding spectral separability, 23 narrow bands in the visible region and near-infrared region were identified as optimal for distinguishing the plant species. The supervised classification algorithm applied to these 23 narrow bands achieved an overall accuracy of 95.8%. In conclusion, these findings provide valuable insights into the spectral response of important tropical species and contribute to their conservation efforts by enhancing understanding of their unique spectral characteristics in diverse and heterogeneous ecosystems like tropical forests.
Esta investigación analizó la respuesta espectral foliar de tres especies forestales maderables nativas del bosque seco tropical, Diomate (Astronium graveolens Jacq.), Choibá (Dipteryx oleifera Benth.) y Algarrobo (Hymenaea courbaril L.). El estudio se efectuó en el Arboretum y Palmetum León Morales Soto de la Universidad Nacional de Colombia, sede Medellín, Antioquia, Colombia. Los datos espectrales de las hojas se colectaron in situ con el espectrorradiómetro portátil ASD FieldSpec HandHeld-2, que trabaja con una resolución espectral de 1 nm (remuestreada a 10 nm) y un rango espectral entre 325 y 1.075 nm (acotado entre 400 y 900 nm). A partir de las mediciones, se evaluó el comportamiento y la variabilidad espectral de las especies. Se implementó el Análisis de Varianza de un factor y la prueba U de Mann – Whitney – Wilcoxon en los espectros de reflectancia con el fin de seleccionar las bandas estrechas óptimas para discriminar las especies. Se evaluó la capacidad de clasificación de las especies en las bandas estrechas seleccionadas, utilizando el algoritmo de los K vecinos más cercanos. Encontrando que A. graveolens e H. courbaril presentaron firmas espectrales típicas de la vegetación saludable y D. oleifera evidenció cambios espectrales en el período inicial de la senescencia. Respecto a la separabilidad espectral, se encontraron 23 bandas estrechas en la región visible e infrarrojo cercano óptimas para diferenciar las especies vegetales. El algoritmo de clasificación supervisada aplicado en las 23 bandas estrechas, tuvo una precisión general del 95,8%. En conclusión, estos hallazgos proporcionan valiosos conocimientos sobre la respuesta espectral de importantes especies tropicales y contribuyen a sus esfuerzos de conservación al mejorar la comprensión de sus características espectrales únicas en ecosistemas diversos y heterogéneos como el bosque tropical.
References
Aggarwal S (2004) Earth resources satellites. pp 39–65. In: Sivakumar MVK, Roy PS, Harmsen K and Saha SK. (eds.). Satellite remote sensing and GIS applications in agricultural meteorology. World Meteorological Organization, Dehra Dun. 44 p.
Amat J (2016) Comparación entre Regresión Logística, Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA) y K-Nearest-Neighbors. In: RPubs. https://rpubs.com/Joaquin_AR/236130
Bachman S (2023) Hymenaea courbaril.In: IUCN - Red list of threatened species. https://www.iucnredlist.org/es/species/19891869/68101847
Cárdenas D and Salinas R (2007) Libro rojo de plantas de Colombia. SINCHI - Instituto Amazónico de Investigaciones Científicas, Bogotá. 75-78 p. https://sinchi.org.co/files/publicaciones/publicaciones/pdf/LR_MADERABLES.pdf
Castillo R, Contreras D, Freer J et al (2008) Supervised pattern recognition techniques for classification of Eucalyptus species from leaves NIR spectra. Journal of the Chilean Chemical Society 53: 1709–1713. https://doi.org/10.4067/S0717-97072008000400016
Castro-Esau KL, Sánchez-Azofeita, Rivard B et al (2006) Variability in leaf optical properties of mesoamerican trees and the potential for species classification. American Journal of Botany 93: 517–530. https://doi.org/10.3732/ajb.93.4.517
Clark ML and Roberts DA (2012) Species-level differences in hyperspectral metrics among tropical rainforest trees as determined by a tree-based classifier. Remote Sensing 4: 1820–1855. https://doi.org/10.3390/rs4061820
Clark ML, Roberts DA and Clark DB (2005) Hyperspectral discrimination of tropical rain forest tree species at leaf to crown scales. Remote Sensing of Environment 96: 375 – 398. https://doi.org/10.1016/j.rse.2005.03.009
Cogollo A, Castrillón J and Vélez L (2004) Manejo in situ y ex situ del Almendro (Dipteryx oleifera Benth) como base para un modelo de uso sostenible de productos vegetales no maderables en la región del Bajo Cauca antioqueño. Jardín Botánico de Medellín Joaquín Antonio Uribe, Medellín. 11 p.
Cover T and Hart P (1967) Nearest neighbor pattern classification. IEEE Transactions on Information Theory 13: 21–27. https://doi.org/10.1109/TIT.1967.1053964
Féret JB and Asner GP (2011) Spectroscopic classification of tropical forest species using radiative transfer modeling. Remote Sensing of Environment 115: 2415–2422. https://doi.org/10.1016/j.rse.2011.05.004
Ferreira MP, Zortea M, Zanotta DC et al (2016) Mapping tree species in tropical seasonal semi-deciduous forests with hyperspectral and multispectral data. Remote Sensing of Environment 179: 66–78. https://doi.org/10.1016/j.rse.2016.03.021
Gómez M and Toro J (2008) Manejo de las semillas y la propagación de diez especies forestales del bosque seco tropical. First edition. CORANTIOQUIA - Corporación Autónoma Regional del Centro de Antioquia, Medellín. 5-43 p. http://hdl.handle.net/20.500.12324/1106
IDEAM - Instituto de Hidrología, Meteorología y Estudios Ambientales de Colombia (2010) Promedios climatológicos 1981-210. In: Tiempo y Clima. http://www.ideam.gov.co/web/tiempo-y-clima/clima
Karadağ K, Tenekeci ME, Taşaltın R and Bilgili A (2020) Detection of pepper fusarium disease using machine learning algorithms based on spectral reflectance. Sustainable Computing Informatics and Systems 28: 1-8. https://doi.org/10.1016/j.suscom.2019.01.001
Kumar A, Manjunath K, Meenakshi et al (2013) Field hyperspectral data analysis for discriminating spectral behavior of tea plantations under various management practices. International Journal of Applied Earth Observation and Geoinformation 23: 352–359. https://doi.org/10.1016/j.jag.2012.10.006
Lu J, Ehsani R, Shi Y et al (2017) Field detection of anthracnose crown rot in strawberry using spectroscopy technology. Computers and Electronics in Agriculture 135: 289–299. https://doi.org/10.1016/j.compag.2017.01.017
Machuca K, Martínez E and Samain M (2022) Astronium graveolens. In: IUCN - Red List of Threatened Species. https://www.iucnredlist.org/es/species/61530992/61531208
Maxwell AE, Warner TA and Fang F (2018) Implementation of machine-learning classification in remote sensing: An applied review. International Journal of Remote Sensing 39: 2784–2817. https://doi.org/10.1080/01431161.2018.1433343
Miyoshi G, Imai N, Tommaselli AM and Honkavaara E (2020) Spectral differences of tree species belonging to Atlantic forest obtained from UAV hyperspectral images. Remote Sensing and Spatial Information Sciences 49–54. https://doi.org/10.1109/LAGIRS48042.2020.9165616
Nalepa J (2021) Recent advances in multi-and hyperspectral image analysis. Sensors 21: 1-7. https://doi.org/10.3390/s21186002
O’Shaughnessy SA and Rush C (2014) Precision agriculture: irrigation. Encyclopedia of Agriculture and Food Systems 4: 521–535. https://doi.org/10.1016/B978-0-444-52512-3.00235-7
Papeş M, Tupayachi R, Martinez P et al (2013) Seasonal variation in spectral signatures of five genera of rainforest trees. Journal of Selected Topics in Applied Earth Observations and Remote Sensing 6: 339–350. https://doi.org/10.1109/JSTARS.2012.2228468
Prasad K and Gnanappazham L (2014) Species discrimination of mangroves using derivative spectral analysis. Remote Sensing and Spatial Information Sciences 2: 45–52. https://doi.org/10.5194/isprsannals-ii-8-45-2014
Rasaiah BA, Jones SD, Bellman C and Malthus TJ (2014) Critical metadata for spectroscopy field campaigns. Remote Sensing 6: 3662-3680. https://doi.org/10.3390/rs6053662
Thenkabail P, Enclona E, Ashton M and Van Der Meer B (2004) Accuracy assessments of hyperspectral waveband performance for vegetation analysis applications. Remote Sensing of Environment Journal 91: 354–376. https://doi.org/10.1016/j.rse.2004.03.013
Triola M (2009) Estadística. Tenth edition. Pearson Educación, México. 634–673 p.
Yue S and Wang C (2002) The influence of serial correlation on the Mann–Whitney test for detecting a shift in median. Advances in Water Resources 25: 325–333. https://doi.org/10.1016/S0309-1708(01)00049-5
Zulfa AW, Norizah K, Hamdan O et al (2020) Discriminating tree species from the relationship between spectral reflectance and chlorophyll contents of mangrove forest in Malaysia. Ecological Indicators 111: 1-9. https://doi.org/10.1016/j.ecolind.2019.106024
How to Cite
APA
ACM
ACS
ABNT
Chicago
Harvard
IEEE
MLA
Turabian
Vancouver
Download Citation
License
Copyright (c) 2024 Revista Facultad Nacional de Agronomía Medellín
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
The journal allows the author(s) to maintain the exploitation rights (copyright) of their articles without restrictions. The author(s) accept the distribution of their articles on the web and in paper support (25 copies per issue) under open access at local, regional, and international levels. The full paper will be included and disseminated through the Portal of Journals and Institutional Repository of the Universidad Nacional de Colombia, and in all the specialized databases that the journal considers pertinent for its indexation, to provide visibility and positioning to the article. All articles must comply with Colombian and international legislation, related to copyright.
Author Commitments
The author(s) undertake to assign the rights of printing and reprinting of the material published to the journal Revista Facultad Nacional de Agronomía Medellín. Any quotation of the articles published in the journal should be made given the respective credits to the journal and its content. In case content duplication of the journal or its partial or total publication in another language, there must be written permission of the Director.
Content Responsibility
The Faculty of Agricultural Sciences and the journal are not necessarily responsible or in solidarity with the concepts issued in the published articles, whose responsibility will be entirely the author or the authors.