Please use this identifier to cite or link to this item: http://repositorio.ufla.br/jspui/handle/1/42903
Title: Artificial neural networks to distinguish charcoal from eucalyptus and native forests based on their mineral components
Keywords: Artificial neural networks
Charcoal
Redes neurais artificiais
Carvão vegetal
Issue Date: 2020
Publisher: American Chemical Society
Citation: RAMALHO, F. M. G. et al. Artificial neural networks to distinguish charcoal from eucalyptus and native forests based on their mineral componentes. Energy Fuels, [S. l.], v. 34, n. 8, p. 9599-9608, 2020. DOI: https://doi.org/10.1021/acs.energyfuels.0c01034.
Abstract: Charcoal is produced through the pyrolysis of wood. It is used as the main domestic energy source in many tropical countries from Africa and Asia, and it is used as a reductor product in the steel industry in Brazil. However, the indiscriminant use of wood from native forests is detrimental to sustainability. The development of rapid and efficient methodologies for distinguishing charcoal produced from native forest or Eucalyptus plantations, as found partially in Brazil, is essential to curb illegal charcoal transport and trade. The aim of this study was to distinguish charcoals from native or Eucalyptus woods by using artificial neural networks (ANNs) based on their mineral composition. Specimens from Brazilian native woods (Apuleia sp., Cedrela sp., Aspidosperma sp., Jacaranda sp., Peltogyne sp., Dipteryx sp., and Gochnatia sp.) and from Eucalyptus sp. hybrid woods of commercial forest plantations were pyrolyzed at temperatures from 300 °C to 700 °C in order to simulate the actual pyrolysis conditions and species widely used illegally in southeastern Brazil. Charcoals composition and proportion of mineral elements were determined by X-ray fluorescence. The ANNs were trained based on the elemental composition of the charcoal specimens to classify the species and origin of the charcoals (i.e., native forest or Eucalyptus). The ANNs based on mineral element content yielded high percentage of correct classification for charcoal specimens by species (72% accuracy) or origin (97% accuracy) from an independent validation sample set.
URI: https://pubs.acs.org/doi/10.1021/acs.energyfuels.0c01034
http://repositorio.ufla.br/jspui/handle/1/42903
Appears in Collections:DCS - Artigos publicados em periódicos

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.