Rafael Lucas Figueiredo de Souza

Rafael Lucas Figueiredo de Souza

Auto-generated profile, based on publicly available information

Rafael Lucas Figueiredo de Souza

Instituto Tecnológico Vale – ITV, Belém, Pará, 66055-090, Brazil

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2025 in Environmental Research Communications
Verified
Journal Article
Open access
Emily Ane DionizioEmily Ane Dionizio
Emily Ane Dionizio
TGTereza Giannini
Tereza Giannini
MGMarkus Gastauer
Markus Gastauer
Rafael Gomes Barbosa-SilvaRafael Gomes Barbosa-Silva
Rafael Gomes Barbosa-Silva
RSRafael Lucas Figueiredo de Souza
Rafael Lucas Figueiredo de Souza
RCRosane Cavalcante
Rosane Cavalcante
Protected areas worldwide have been recognized as crucial entities in preserving and conserving forest ecosystem services. These areas play an important role in mitigating climate change due to their carbon stocks. In this study, we characterized the aboveground carbon stocks (AGC) across different forest types for the Protected Area Carajás National Forest in the Eastern Amazon, based on data from 387 forest inventory plots and two distinct AGC maps from remote sensing and LiDAR (Light Detection and Ranging) data fusion—GEDI and EBA. The estimates of AGC from field data showed higher amounts of AGC in the open forest formations (187.20 ± 46.83 MgC ha−1), followed by dense (105.90 ± 42.56 ha−1 MgC ha−1) and transitional forests (48.86 ± 31.72 MgC ha−1) with lower amounts under seasonal forests (38.65 ± 9.48 MgC ha−1) and secondary forest areas (>23 MgCha−1). However, the dense, seasonal, and transitional forests exhibited higher carbon density than the open and secondary areas in both AGC maps analyzed. We emphasize the significant importance of monitoring open and seasonal forest areas, due to the gap in field data for these forest types in Amazonia. Here, we underscore the importance of more standardized forest field data and better plot distribution in non-disturbed areas to reduce the uncertainty of AGC estimates and improve the estimation of greenhouse gas emissions from deforestation and forest fires.

1 January 2023 in Scientia Agricola
Verified
Journal Article
Open access
TSThaine Teixeira Silva
Thaine Teixeira Silva
RLRobson Borges De Lima
Robson Borges De Lima
RSRafael Lucas Figueiredo de Souza
Rafael Lucas Figueiredo de Souza
PMPeter W. Moonlight
Peter W. Moonlight
DCDomingos Cardoso
Domingos Cardoso
OPOliver L. Phillips
Oliver L. Phillips

3 January 2024 in FLORESTA
Verified
Journal Article
Open access
ASAnthoinny Vittória Dos Santos Silva
Anthoinny Vittória Dos Santos Silva
RSRafael Lucas Figueiredo de Souza
Rafael Lucas Figueiredo de Souza
RSRenan Mendes Santos
Renan Mendes Santos
RLRobson Borges De Lima
Robson Borges De Lima
JAJadson De Abreu
Jadson De Abreu
The present study aimed to evaluate the performance of artificial neural networks (ANNs), support vector machines (SVM), and fixed and mixed models to estimate the volume of individual trees in an Amazonian estuary floodplain forest. The forest inventory was conducted in an area located in the district of Itatupã - Gurupá, Pará, Brazil. The Schumacher and Hall linear model was used in its fixed and mixed form to estimate the volume. A total of 240 ANNs and 32 SVM configurations were trained, with 4 variations of the input variables: diameter at breast height (D), commercial height (hm), diameter classes (CCD), commercial height classes (CChm),) and species (SP), with the volume (V) being the output variable. The ANNs were trained in the Neuro 4.0.6 software program, and the analyses of the fixed and mixed regression models and SVM were performed in the R software program. The AIC (Akaike’s Information Criterion) and BIC (Bayesian Information Criterion) information criteria were used for the regression models, while the following were used for comparisons of all models: correlation coefficient (rYŶ), bias, root mean squared error (RMSE), and residual distribution analysis. The best statistical metrics were obtained by the ANN of the RPROP- algorithm with D+hm+CCD+CChm inputs, with eight neurons in the hidden layer and hyperbolic tangent activation function, with 0.9827 of rYŶ RMSE of 0.2439, bias of 0.0080 and residual graphic distribution tending to homogeneity.