Frederico Scherr Caldeira Takahashi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Frederico Scherr Caldeira Takahashi has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Leonardo Lima Bergamini
Brazilian Institute of Geography and Statistics
3 shared publications - Díbio Leandro Borges
University of Brasilia
2 shared publications - Adriano Antonio Brito Darosci
Instituto Federal Goiano
1 shared publication Alessandra Luiza Gouveia
Instituto Brasileiro de Geografia e Estatística -IBGE Resumo
1 shared publicationAline Danieli-Silva
Instituto Brasileiro de Geografia e Estatística -IBGE Resumo
1 shared publication- Ana Sofia S. Silvestre
Universidade de Brasília
1 shared publication
Latest Publications
- 28 September 2026
- Published by Springer Nature
- p. 358-373
Multispectral UAV Fusion for Native Tree Species Recognition in the Cerrado
- 28 September 2026
- Published by Springer Nature
- p. 358-373
Multispectral UAV Fusion for Native Tree Species Recognition in the Cerrado
- Open Access
- 30 January 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (3) , 480
Machine Learning-Based Cerrado Land Cover Classification Using PlanetScope Imagery
The Cerrado domain, one of the richest on Earth, is among the most threatened in South America due to human activities, resulting in biodiversity loss, altered fire dynamics, water pollution, and other environmental impacts. Monitoring this domain is crucial for preserving its biodiversity and ecosystem services. This study aimed to apply machine learning techniques to classify the main vegetation formations of the Cerrado within the IBGE Ecological Reserve, a protected area in Brazil, using high-resolution PlanetScope imagery from 2021 to 2024. Three machine learning methods were evaluated: Random Forest (RF), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost). A post-processing process was applied to avoid misclassification of forest in areas of savanna. After performance evaluation, the SVM method achieved the highest classification accuracy (overall accuracy of 97.51%, kappa coefficient of 0.9649) among the evaluated models. This study identified five main classes: grassland (GRA), savanna (SAV), bare soil (BS), samambaião (SAM, representing the superdominant species Pteridium esculentum), and forest (FOR). Over the three-year period (2021–2024), SAV and GRA formations were dominant in the reserve, reflecting the typical physiognomies of the Cerrado. This study successfully delineated areas occupied by the superdominant species P. esculentum, which was concentrated near gallery forests. The generated maps provide valuable insights into the vegetation dynamics within a protected area, aiding in monitoring efforts and suggesting potential new areas for protection in light of imminent anthropogenic threats. This study demonstrates the effectiveness of combining high-resolution satellite imagery with machine learning techniques for detailed vegetation mapping and monitoring in the Cerrado domain.
- 30 January 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (3) , 480
Open AccessMachine Learning-Based Cerrado Land Cover Classification Using PlanetScope Imagery
The Cerrado domain, one of the richest on Earth, is among the most threatened in South America due to human activities, resulting in biodiversity loss, altered fire dynamics, water pollution, and other environmental impacts. Monitoring this domain is crucial for preserving its biodiversity and ecosystem services. This study aimed to apply machine learning techniques to classify the main vegetation formations of the Cerrado within the IBGE Ecological Reserve, a protected area in Brazil, using high-resolution PlanetScope imagery from 2021 to 2024. Three machine learning methods were evaluated: Random Forest (RF), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost). A post-processing process was applied to avoid misclassification of forest in areas of savanna. After performance evaluation, the SVM method achieved the highest classification accuracy (overall accuracy of 97.51%, kappa coefficient of 0.9649) among the evaluated models. This study identified five main classes: grassland (GRA), savanna (SAV), bare soil (BS), samambaião (SAM, representing the superdominant species Pteridium esculentum), and forest (FOR). Over the three-year period (2021–2024), SAV and GRA formations were dominant in the reserve, reflecting the typical physiognomies of the Cerrado. This study successfully delineated areas occupied by the superdominant species P. esculentum, which was concentrated near gallery forests. The generated maps provide valuable insights into the vegetation dynamics within a protected area, aiding in monitoring efforts and suggesting potential new areas for protection in light of imminent anthropogenic threats. This study demonstrates the effectiveness of combining high-resolution satellite imagery with machine learning techniques for detailed vegetation mapping and monitoring in the Cerrado domain.
- Open Access
- 1 September 2021
- Published by FapUNIFESP (SciELO) in Acta Botanica Brasilica
- Vol. 35 (3) , 456-465
Does spatial and seasonal variability in fleshy-fruited trees affect fruit availability? A case study in gallery forests of Central Brazil
- 1 September 2021
- Published by FapUNIFESP (SciELO) in Acta Botanica Brasilica
- Vol. 35 (3) , 456-465
Open AccessDoes spatial and seasonal variability in fleshy-fruited trees affect fruit availability? A case study in gallery forests of Central Brazil
- Open Access
- 2 September 2019
- Published by Fundacao Instituto Brasileiro de Geografia e Estatistica in Revista Brasileira de Geografia
- Vol. 64 (1) , 146-160
Reserva Ecológica do IBGE
Para o desenvolvimento sustentável é necessária ampla base de informações da biodiversidade e processos ecológicos para avaliar os benefícios das atividades humanas e seus custos ambientais. Criada em 1975, a Reserva Ecológica do IBGE é um centro de referência na produção de informações sobre o Cerrado, conciliando a conservação, pesquisa de ambientes preservados e experimentos sobre impactos com projetos de longa duração desenvolvidos em conjunto com parceiros de diversas instituições. Paralelamente, seu programa de pesquisas emprega amostragem ao longo do Cerrado avaliando padrões e descrevendo a biodiversidade regional. Para atender às novas demandas, a Reserva tem voltado seu manejo para novos objetivos de conservação, articulado a participação em redes de pesquisa e preparado ações de ensino e extensão.
- 2 September 2019
- Published by Fundacao Instituto Brasileiro de Geografia e Estatistica in Revista Brasileira de Geografia
- Vol. 64 (1) , 146-160
Open AccessReserva Ecológica do IBGE
Para o desenvolvimento sustentável é necessária ampla base de informações da biodiversidade e processos ecológicos para avaliar os benefícios das atividades humanas e seus custos ambientais. Criada em 1975, a Reserva Ecológica do IBGE é um centro de referência na produção de informações sobre o Cerrado, conciliando a conservação, pesquisa de ambientes preservados e experimentos sobre impactos com projetos de longa duração desenvolvidos em conjunto com parceiros de diversas instituições. Paralelamente, seu programa de pesquisas emprega amostragem ao longo do Cerrado avaliando padrões e descrevendo a biodiversidade regional. Para atender às novas demandas, a Reserva tem voltado seu manejo para novos objetivos de conservação, articulado a participação em redes de pesquisa e preparado ações de ensino e extensão.