Articles | Volume 23, issue 3
https://doi.org/10.5194/bg-23-881-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/bg-23-881-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| Highlight paper
| 
02 Feb 2026
Research article | Highlight paper |
| 02 Feb 2026
| 02 Feb 2026
Machine-learning models of δ13C and δ15N isoscapes in Amazonian wood
Isabela M. Souza-Silva
CORRESPONDING AUTHOR
Center for Nuclear Energy in Agriculture, University of São Paulo, Av. Centenário 303, Piracicaba, SP 13416-000, Brazil
Department of Earth and Environmental Sciences, University of Ottawa, 25 Templeton St., Ottawa, ON K1N 6N5, Canada
Luiz A. Martinelli
Center for Nuclear Energy in Agriculture, University of São Paulo, Av. Centenário 303, Piracicaba, SP 13416-000, Brazil
Brent Holmes
Department of Earth and Environmental Sciences, University of Ottawa, 25 Templeton St., Ottawa, ON K1N 6N5, Canada
Ana C. G. Batista
Center for Nuclear Energy in Agriculture, University of São Paulo, Av. Centenário 303, Piracicaba, SP 13416-000, Brazil
Maria G. S. Araújo
Center for Nuclear Energy in Agriculture, University of São Paulo, Av. Centenário 303, Piracicaba, SP 13416-000, Brazil
Anna L. Garção
Center for Nuclear Energy in Agriculture, University of São Paulo, Av. Centenário 303, Piracicaba, SP 13416-000, Brazil
Stéphane Ponton
SILVA UMR 1434, INRAE, Université de Lorraine, AgroParisTech, F-54280 Champenoux, France
Peter Groenendijk
Department of Plant Biology, Institute of Biology, University of Campinas, Campinas, SP, Brazil
Giuliano M. Locosselli
Center for Nuclear Energy in Agriculture, University of São Paulo, Av. Centenário 303, Piracicaba, SP 13416-000, Brazil
Daigard R. Ortega-Rodriguez
Department of Forest Sciences, Luiz de Queiroz College of Agriculture, University of São Paulo, Av. Pádua Dias 11, Piracicaba, SP 13418-900, Brazil
Deoclecio J. Amorim
Center for Nuclear Energy in Agriculture, University of São Paulo, Av. Centenário 303, Piracicaba, SP 13416-000, Brazil
Fábio J. V. Costa
National Institute of Criminalistics, Federal Police, Setor Policial Sul, Lote 7, Asa Sul, Brasília, DF 70610-902, Brazil
Gabriela B. Nardoto
Department of Ecology, Institute of Biological Sciences, University of Brasília, Campus Universitário Darcy Ribeiro Bloco E, Brasília, DF 70910-900, Brazil
Alexandre T. Brunello
Center for Nuclear Energy in Agriculture, University of São Paulo, Av. Centenário 303, Piracicaba, SP 13416-000, Brazil
Vladimir Eliodoro Costa
Stable Isotopes Center, São Paulo State University (UNESP), Prof. Dr. Antônio Celso Wagner Zanin Street 250, Rubião Junior, Botucatu, SP 18618-689, Brazil
Gabriel Assis-Pereira
Research and Development Department, Monte Verde Carbon, Itajubá, Minas Gerais, Brazil
Mario Tomazello-Filho
Department of Forest Sciences, Luiz de Queiroz College of Agriculture, University of São Paulo, Av. Pádua Dias 11, Piracicaba, SP 13418-900, Brazil
Niro Higuchi
National Institute for Amazon Research, Av. André Araújo 2936, Petrópolis, Manaus, AM 69067-375, Brazil
Ana C. Barbosa
Department of Forest Sciences, University of Lavras, P.O. Box 3037, Lavras, MG 37200-000, Brazil
João Paulo Sena-Souza
Department of Geosciences, State University of Montes Claros (Unimontes), Professor Darcy Ribeiro Campus, Montes Claros, MG 39401-089, Brazil
Clément P. Bataille
CORRESPONDING AUTHOR
Department of Earth and Environmental Sciences, University of Ottawa, 25 Templeton St., Ottawa, ON K1N 6N5, Canada
Department of Forestry and Natural Resources, Purdue University, West Lafayette, IN 47907, USA
Data sets
Research compendium for 'Machine-learning models of δ¹³C and δ¹⁵N isoscapes in Amazonian wood'. I. M. Souza-Silva and C. Bataille https://doi.org/10.17605/OSF.IO/U5RWS
Co-editor-in-chief
The study by Souza-Silva and co-workers presents a comprehensive dataset and a foundational approach for assessing the legitimacy of logged wood in the Amazon basin—a topic of global relevance and high societal impact. Building on this dataset and further developing these methods will be critical for safeguarding the Amazon’s ecologically vital yet fragile forests into the future.
The study by Souza-Silva and co-workers presents a comprehensive dataset and a foundational...
Short summary
Illegal logging is a major environmental concern in the Amazon. We tested whether the isotopic composition of carbon (δ13C) and nitrogen (δ15N) in wood can support timber traceability. Using machine-learning models, we generated basin-wide isoscapes showing that both isotopes capture consistent environmental gradients, providing a scientific basis to improve provenance verification and guide enforcement efforts.
Illegal logging is a major environmental concern in the Amazon. We tested whether the isotopic...
Altmetrics
Final-revised paper
Preprint