João Paulo Sena-Souza

João Paulo Sena-Souza

Auto-generated profile, based on publicly available information

João Paulo Sena-Souza

Department of Geosciences, State University of Montes Claros, Melo, Monte Carlos 39580-000, Brazil

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
31 August 2020 in Ecosphere
Verified
Journal Article
Open access
PDF file
JSJoão Paulo Sena‐Souza
João Paulo Sena‐Souza
BHBenjamin Z. Houlton
Benjamin Z. Houlton
LMLuiz Antonio Martinelli
Luiz Antonio Martinelli
Gabriela NardotoGabriela Nardoto
Gabriela Nardoto
Soil nitrogen isotope composition (δ15N) is an essential tool for investigating ecosystem nitrogen balances, plant–microbe interactions, ecological niches, animal migration, food origins, and forensics. The advancement of these applications is limited by a lack of robust geospatial models that are capable of capturing variation in soil δ15N (i.e., isotopic landscapes or isoscapes). Due to the complexity of the nitrogen cycle and general scarcity of isotopic information, previous approaches have reconstructed regional to global soil δ15N patterns via highly uncertain linear regression models. Here, we develop a new machine learning approach to ascertain a finer‐scale understanding of geographic differences in soil δ15N, using the South American continent as a test case. We use a robust training set spanning 278 geographic locations across the continent, spanning all major biomes. We tested three different machine learning methods: cubist, random forest (RF), and stochastic gradient boosting (GBM). 10‐fold cross‐validation revealed that the RF method outperformed both the cubist and GBM approaches. Variable importance analysis of the RF framework pointed to biome type as the most crucial auxiliary variable, followed by soil organic carbon content, in determining the model performance. We thereby created a biogeographic boundary map, which predicted an expected multiscale spatial pattern of soil δ15N with a high degree of confidence, performing substantially better than all previous approaches for the continent of South America. Therefore, the RF machine learning framework showed to be a great opportunity to explore a broad array of ecological, biogeochemical, and forensic issues through the lens of soil δ15N.

29 November 2022 in Sociedade & Natureza
Verified
Journal Article
Open access
PDF file
Lucas SilvaLucas Silva
Lucas Silva
CSClaudionor Silva
Claudionor Silva
CSCristiano Marcelo Pereira de Souza
Cristiano Marcelo Pereira de Souza
Édson Luis BolfeÉdson Luis Bolfe
Édson Luis Bolfe
JSJoão Paulo Sena Souza
João Paulo Sena Souza
MARCOS ESDRAS LEITEMARCOS ESDRAS LEITE
MARCOS ESDRAS LEITE
Brazil has the most populous and biodiverse semi-arid region in the world (Brazilian Semi-arid - SAB). However, in recent decades, clusters of desertification have emerged, a problem that could intensify from climate change. The objective of this study was to elaborate on the spatial distribution of areas susceptible to climatic desertification in the SAB, considering future climate change scenarios. Understanding this dynamic is essential for SAB's agri-environmental management. Aridity indices and proposition of climate classes for current condition (1970-2000) and future scenarios (2061-2080) of the Intergovernmental Panel on Climate Change (IPCC) were prepared, considering scenarios from Shared Socioeconomic Pathways: Optimistic (SSP 126) and pessimists (SSP 585). The results indicate that by the end of the century, the climate in the SAB should become significantly drier (Kruskal-Wallis = p-value < 0.05), with an intensification of the aridity index in SSP 585. In the scenarios, the expansion of more arid areas over humid climates could reach 56,500 km² (10%) in SSP 126 and 140,400 km² (24%) in SSP 585. Consequently, areas with high (622,400 km² to 706,300 km²) and very high (622,400 km² to 706,300 km²) are expected to expand. 4,400 to 21,700 km²) susceptibility to climate desertification in the SAB, respectively in scenarios SSPs 126 and 585. Confirming these projections would imply socioeconomic and ecological risks in the SAB.

16 July 2020 in npj Science of Food
Verified
Journal Article
Open access
PDF file
Gabriela NardotoGabriela Nardoto
Gabriela Nardoto
JSJoão Paulo Sena-Souza
João Paulo Sena-Souza
TKTiago Borges Kisaka
Tiago Borges Kisaka
FCFabio Jose Costa
Fabio Jose Costa
PDPaulo Duarte-Neto
Paulo Duarte-Neto
LMLuiz Antonio Martinelli
Luiz Antonio Martinelli
High δ13C in human tissues in Brazil indicate high consumption of C4-based sources due to the consumption of highly processed food and animal protein. The significant positive correlation between the human developed index (HDI) developed by the United Nations Development Program, and fingernail δ13C at the county level proved to be useful as a new proxy in tracking human nutrition. Regions with higher HDI are those with higher consumption of highly processed food.

19 June 2023 in Sociedade & Natureza
Verified
Journal Article
Open access
Lucas SilvaLucas Silva
Lucas Silva
CSClaudionor Silva
Claudionor Silva
CSCristiano Marcelo Pereira de Souza
Cristiano Marcelo Pereira de Souza
Édson Luis BolfeÉdson Luis Bolfe
Édson Luis Bolfe
JSJoão Paulo Sena Souza
João Paulo Sena Souza
MARCOS ESDRAS LEITEMARCOS ESDRAS LEITE
MARCOS ESDRAS LEITE
Brazil has the most populous and biodiverse semi-arid region in the world (Brazilian Semi-arid - SAB). However, in recent decades, clusters of desertification have emerged, a problem that could intensify from climate change. The objective of this study was to elaborate on the spatial distribution of areas susceptible to climatic desertification in the SAB, considering future climate change scenarios. Understanding this dynamic is essential for SAB's agri-environmental management. Aridity indices and proposition of climate classes for current condition (1970-2000) and future scenarios (2061-2080) of the Intergovernmental Panel on Climate Change (IPCC) were prepared, considering scenarios from Shared Socioeconomic Pathways: Optimistic (SSP 126) and pessimists (SSP 585). The results indicate that by the end of the century, the climate in the SAB should become significantly drier (Kruskal-Wallis = p-value < 0.05), with an intensification of the aridity index in SSP 585. In the scenarios, the expansion of more arid areas over humid climates could reach 56,500 km² (10%) in SSP 126 and 140,400 km² (24%) in SSP 585. Consequently, areas with high (622,400 km² to 706,300 km²) and very high (622,400 km² to 706,300 km²) are expected to expand. 4,400 to 21,700 km²) susceptibility to climate desertification in the SAB, respectively in scenarios SSPs 126 and 585. Confirming these projections would imply socioeconomic and ecological risks in the SAB.

1 December 2021 in Journal of Environmental Management
Verified
Journal Article
Closed access
GNGlauber das Neves
Glauber das Neves
JSJoão Paulo Sena-Souza
João Paulo Sena-Souza
FSFabio Luis de Souza Santos
Fabio Luis de Souza Santos
ESEDSON SANO
EDSON SANO
Gabriela NardotoGabriela Nardoto
Gabriela Nardoto
AJAntonio Felipe Couto Junior
Antonio Felipe Couto Junior

3 April 2023 in Revista Brasileira de Geografia Física
Verified
Journal Article
Open access
PDF file
Lucas SilvaLucas Silva
Lucas Silva
CSCristiano Marcelo Pereira de Souza
Cristiano Marcelo Pereira de Souza
CSClaudionor Silva
Claudionor Silva
RFRoberto Filgueiras
Roberto Filgueiras
JSJoão Paulo Sena-Souza
João Paulo Sena-Souza
MARCOS ESDRAS LEITEMARCOS ESDRAS LEITE
MARCOS ESDRAS LEITE
Brazil has the world's most populous semi-arid region and climate change represents significant ecological and socioeconomic challenges for this area. To better understand the impact of these changes, it is crucial to analyze the dynamics of climate variables and evapotranspiration (ETo), a critical climate variable. This study aimed to model ETo rates considering climate change scenarios in the Brazilian Semi-arid region (BSR). The modeling was based on tests of five machine learning algorithms: Bayesian Regularized Neural Networks (BRNN), Cubist, Earth, Linear Regression (LM), and Random Forest (RF). A dataset with 20 covariates was used to represent the current scenario. In the future prediction, covariates from two shared socio-economic pathways were used (SSPs 126 and 585). The best statistical performance was achieved by Cubist (R² = 0.98 and RMSE = 0.08 mm day-¹ in the holdout-test). The current daily average ETo is 4.77 mm day-¹, while in future scenarios, it can increase by 3.56% in SSP 126 and 15.51% in SSP 585. ETo rates are expected to expand territorially; ranges from > 0.60 mm day-¹ should increase 8% in SSP 126 and 40% in SSP 585. The applied model suggests that ETo may increase in future scenarios in the BSR, which could affect biodiversity levels and intensify social conflicts.Keywords: Machine Learning; Spatial Prediction; Cubist; Semi-arid Zone; Climate changes. Mapeamento dos Efeitos das Mudanças Climáticas na Evapotranspiração de Referência em Cenários Futuros no Semiárido Brasileiro - América do Sul RESUMOO Brasil possui a região semiárida mais populosa do mundo e as mudanças climáticas impõem desafios ecológicos e socioeconômicos significativos para esta área. Para entender melhor o impacto dessas mudanças, é crucial analisar a dinâmica das variáveis climáticas e a evapotranspiração (ETo), uma importante variável do clima. Este estudo teve como objetivo modelar taxas de ETo considerando cenários de mudanças climáticas no Semiárido Brasileiro (BSR). A modelagem foi baseada em testes de cinco algoritmos de aprendizado de máquina: Bayesian Regularized Neural Networks (BRNN), Cubist, Earth, Linear Regression (LM) e Random Forest (RF). Um conjunto de dados com 20 covariáveis foi usado para representar o cenário atual. Na predição futura, foram usadas covariáveis de dados dos Caminhos Socioeconômicos Compartilhados (SSPs 126 e 585). Na modelagem, o melhor desempenho estatístico foi com modelo Cubist (R² = 0,98 e RMSE = 0,08 mm dia-¹ no holdout-test). A média diária atual de ETo é de 4,77 mm dia-¹, enquanto em cenários futuros a média pode aumentar 3,56% no SSP 126 e 15,51% no SSP 585. As taxas de ETo devem se expandir territorialmente; intervalos de > 0,60 mm dia-¹ devem expandir 8% no SSP 126 e 40% no SSP 585. O modelo aplicado sugere que a ETo pode aumentar em cenários futuros na BSR, o que pode afetar os níveis de biodiversidade e intensificar os conflitos sociais.Palavras-Chave: Aprendizado de máquina; Predição espacial; Cubist; Zona Semiárida; Mudanças climáticas.