Washington Luiz Félix Correia Filho
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Washington Luiz Félix Correia Filho has a total of 161 co-authors. Here are the top co-authors by number of shared publications:
- José Francisco de Oliveira-Júnior
Federal University of Alagoas
25 shared publications - Dimas de Barros Santiago
Universidade Federal de Campina Grande
22 shared publications - Carlos Antonio da Silva Junior
Department of Geography, Universidade do Estado de Mato Grosso (UNEMAT), Campus de Sinop, Sinop 78550-000, Brazil
14 shared publications - Givanildo de Gois
Institute of Atmospheric Sciences, Federal University of Alagoas, Maceió 57072-900, Brazil
14 shared publications José Francisco de Oliveira-Júnior
9 shared publicationsDimas de Barros Santiago
8 shared publications
Latest Publications
- 6 October 2026
- Published by Springer Nature
- p. 301-315
Assessment of Vegetation Health Index in South America Using AVHRR and VIIRS Sensors
- 6 October 2026
- Published by Springer Nature
- p. 301-315
Assessment of Vegetation Health Index in South America Using AVHRR and VIIRS Sensors
- 19 July 2026
- Published by Sociedade Brasileira de Computação
- p. 360-363
Plataforma para Consulta de Dados sobre Internações Hospitalares por Doenças Respiratórias, Poluição e Clima
Fatores ambientais, como variabilidade climática e poluição atmosférica, estão associados à ocorrência e ao agravamento de doenças respiratórias, representando um importante desafio para a saúde pública. Este trabalho apresenta o desenvolvimento de uma plataforma Web para análise integrada de dados climáticos diários e registros de internações hospitalares por doenças do trato respiratório, em aproximadamente 700 municípios brasileiros, abrangendo o período de 2000 a 2023. O sistema integra dados de diferentes bases públicas e oferece visualizações interativas que permitem explorar padrões temporais e possíveis relações entre variáveis ambientais e indicadores de saúde, além de possibilitar a exportação dos dados para análises complementares.
- 19 July 2026
- Published by Sociedade Brasileira de Computação
- p. 360-363
Plataforma para Consulta de Dados sobre Internações Hospitalares por Doenças Respiratórias, Poluição e Clima
Fatores ambientais, como variabilidade climática e poluição atmosférica, estão associados à ocorrência e ao agravamento de doenças respiratórias, representando um importante desafio para a saúde pública. Este trabalho apresenta o desenvolvimento de uma plataforma Web para análise integrada de dados climáticos diários e registros de internações hospitalares por doenças do trato respiratório, em aproximadamente 700 municípios brasileiros, abrangendo o período de 2000 a 2023. O sistema integra dados de diferentes bases públicas e oferece visualizações interativas que permitem explorar padrões temporais e possíveis relações entre variáveis ambientais e indicadores de saúde, além de possibilitar a exportação dos dados para análises complementares.
- Open Access
- 9 June 2026
- Published by MDPI AG in Atmosphere
- Vol. 17 (6) , 593
Impacts of Biomass Burning, Urbanization, and Regional Environmental Conditions on Air Quality in Medium-Sized Cities in Brazil
Introduction: International studies have demonstrated a positive impact on air quality associated with the presence of green areas in urban conglomerates. However, in Brazil, studies addressing the impacts of urban green areas on air quality are still incipient and are predominantly focused on large urban centers. The objective of this study was to investigate the relationship between urban green areas, surface temperature (LST), and air quality across 15 medium-sized Brazilian cities. Methods: Concentrations of particulate matter fractions (PM1, PM2.5, and PM10) were monitored from January 2023 to May 2024 using second data from low-cost sensors. The NDVI and both daytime and nighttime LST profiles were extracted via Google Earth Engine within a 1 km buffer zone surrounding each station via the Sentinel-2 and MODIS 11A1 satellite data, respectively. Spatial–temporal co-variation patterns were explored using principal component analysis (PCA). To model these dynamics while controlling for spatial dependencies, a multi-criteria framework compared linear models (simple linear regression (LM) and linear mixed (LMM)) and generalized models (generalized additive (GAM) and generalized additive mixed (GAMM)). Results: The results revealed a positive relationship between NDVI and PM2.5 and PM10 fractions in specific regions, while surface temperatures showed a direct association with finer particles (PM1 and PM2.5). The regression coefficient showed the significant association of PM2.5 with NDVI and nighttime LST (β = 1.330; IC 95%: [0.397; 2.270]; p = 0.005). The GAMM was the best-fitting model for all particle fractions, demonstrating that incorporating monitoring stations as random intercepts successfully controls for unmeasured local heterogeneity, while penalized splines accurately capture non-linear environmental factors. Conclusions: Although many studies have shown that green areas in temperate regions typically act as consistent sinks for particulate matter, our study revealed localized and seasonal responses in tropical urban landscapes. It should be noted that our study is conducted on a national scale and that the use of low-cost sensors and remote sensing does not allow us to distinguish between the localized microclimatic benefits of vegetation and the long-range transport of regional pollutants.
- 9 June 2026
- Published by MDPI AG in Atmosphere
- Vol. 17 (6) , 593
Open AccessImpacts of Biomass Burning, Urbanization, and Regional Environmental Conditions on Air Quality in Medium-Sized Cities in Brazil
Introduction: International studies have demonstrated a positive impact on air quality associated with the presence of green areas in urban conglomerates. However, in Brazil, studies addressing the impacts of urban green areas on air quality are still incipient and are predominantly focused on large urban centers. The objective of this study was to investigate the relationship between urban green areas, surface temperature (LST), and air quality across 15 medium-sized Brazilian cities. Methods: Concentrations of particulate matter fractions (PM1, PM2.5, and PM10) were monitored from January 2023 to May 2024 using second data from low-cost sensors. The NDVI and both daytime and nighttime LST profiles were extracted via Google Earth Engine within a 1 km buffer zone surrounding each station via the Sentinel-2 and MODIS 11A1 satellite data, respectively. Spatial–temporal co-variation patterns were explored using principal component analysis (PCA). To model these dynamics while controlling for spatial dependencies, a multi-criteria framework compared linear models (simple linear regression (LM) and linear mixed (LMM)) and generalized models (generalized additive (GAM) and generalized additive mixed (GAMM)). Results: The results revealed a positive relationship between NDVI and PM2.5 and PM10 fractions in specific regions, while surface temperatures showed a direct association with finer particles (PM1 and PM2.5). The regression coefficient showed the significant association of PM2.5 with NDVI and nighttime LST (β = 1.330; IC 95%: [0.397; 2.270]; p = 0.005). The GAMM was the best-fitting model for all particle fractions, demonstrating that incorporating monitoring stations as random intercepts successfully controls for unmeasured local heterogeneity, while penalized splines accurately capture non-linear environmental factors. Conclusions: Although many studies have shown that green areas in temperate regions typically act as consistent sinks for particulate matter, our study revealed localized and seasonal responses in tropical urban landscapes. It should be noted that our study is conducted on a national scale and that the use of low-cost sensors and remote sensing does not allow us to distinguish between the localized microclimatic benefits of vegetation and the long-range transport of regional pollutants.
- Open Access
- 28 April 2026
- Published by MDPI AG in International Journal of Environmental Research and Public Health
- Vol. 23 (5) , 569
Evaluation of Eco-Environmental Quality in the Maceió Metropolitan Region, Alagoas, Brazil
The Maceió Metropolitan Region (MMR) has undergone significant changes due to public policies that promote urban growth. This has intensified environmental impacts, adversely affecting local communities. The Remote Sensing Ecological Index (RSEI), a remote sensing-based metric, was used to evaluate ecosystem quality. The study assessed annual ecosystem quality in the MMR, Alagoas, using RSEI values from MODIS data spanning 2000 to March 2024/2025. To ensure data quality and reliable results, all MODIS data underwent rigorous quality control, including the exclusion of pixels affected by cloud cover, shadows, and missing values. Only data points meeting established MODIS quality assurance standards were used. Annual RSEI values varied considerably, from 0.449 in 2005 to 0.636 in 2014. Most areas in the MMR are classified as moderate quality (0.4 < RSEI < 0.6), particularly in central and eastern sectors. The lowest-quality regions (0 < RSEI < 0.4) are concentrated in the east—including Maceió, the hub city—and the west, largely due to high population density. The Sen-Slope Estimator and trend analysis revealed significant trends in the hub city, with positive trends in the northeast. Urban expansion has led to the loss of native vegetation, including sugarcane fields and remnants of the Atlantic Forest. The Pettitt test identified a structural change in 2018, likely linked to environmental violations related to the Braskem petrochemical industry and salt extraction in Maceió.
- 28 April 2026
- Published by MDPI AG in International Journal of Environmental Research and Public Health
- Vol. 23 (5) , 569
Open AccessEvaluation of Eco-Environmental Quality in the Maceió Metropolitan Region, Alagoas, Brazil
The Maceió Metropolitan Region (MMR) has undergone significant changes due to public policies that promote urban growth. This has intensified environmental impacts, adversely affecting local communities. The Remote Sensing Ecological Index (RSEI), a remote sensing-based metric, was used to evaluate ecosystem quality. The study assessed annual ecosystem quality in the MMR, Alagoas, using RSEI values from MODIS data spanning 2000 to March 2024/2025. To ensure data quality and reliable results, all MODIS data underwent rigorous quality control, including the exclusion of pixels affected by cloud cover, shadows, and missing values. Only data points meeting established MODIS quality assurance standards were used. Annual RSEI values varied considerably, from 0.449 in 2005 to 0.636 in 2014. Most areas in the MMR are classified as moderate quality (0.4 < RSEI < 0.6), particularly in central and eastern sectors. The lowest-quality regions (0 < RSEI < 0.4) are concentrated in the east—including Maceió, the hub city—and the west, largely due to high population density. The Sen-Slope Estimator and trend analysis revealed significant trends in the hub city, with positive trends in the northeast. Urban expansion has led to the loss of native vegetation, including sugarcane fields and remnants of the Atlantic Forest. The Pettitt test identified a structural change in 2018, likely linked to environmental violations related to the Braskem petrochemical industry and salt extraction in Maceió.
- Open Access
- 1 January 2026
- Published by FapUNIFESP (SciELO) in Ciencia & Saude Coletiva
- Vol. 31 (5) , e23522025
Use of artificial intelligence and environmental data to estimate respiratory hospitalizations in support of SUS management
This study developed a predictive model of hospital admissions due to respiratory diseases using environmental and meteorological data from São Paulo (2017-2022). It analyzed hospitalizations classified under ICD-10 codes J00-J99. Weekly public data on air pollutants (PM2.5, PM10, O3, NO2, SO2, CO) and climate variables (temperature, humidity, precipitation, among others) were used. The methodology included feature engineering (lags, moving averages, interactions, trend, seasonality), Lasso regression for variable selection, and application of the CatBoost algorithm optimized via GridSearchCV. The model showed strong performance (R²≈0.895), with good accuracy in estimating healthcare demand. The Shapley Additive Explanations (SHAP) technique ensured model explainability, identifying the most influential predictors of respiratory admissions. The results highlight the potential of AI as a strategic Digital Health tool, especially for early outbreak detection and resource allocation within Brazil’s Unified Health System (SUS).
- 1 January 2026
- Published by FapUNIFESP (SciELO) in Ciencia & Saude Coletiva
- Vol. 31 (5) , e23522025
Open AccessUse of artificial intelligence and environmental data to estimate respiratory hospitalizations in support of SUS management
This study developed a predictive model of hospital admissions due to respiratory diseases using environmental and meteorological data from São Paulo (2017-2022). It analyzed hospitalizations classified under ICD-10 codes J00-J99. Weekly public data on air pollutants (PM2.5, PM10, O3, NO2, SO2, CO) and climate variables (temperature, humidity, precipitation, among others) were used. The methodology included feature engineering (lags, moving averages, interactions, trend, seasonality), Lasso regression for variable selection, and application of the CatBoost algorithm optimized via GridSearchCV. The model showed strong performance (R²≈0.895), with good accuracy in estimating healthcare demand. The Shapley Additive Explanations (SHAP) technique ensured model explainability, identifying the most influential predictors of respiratory admissions. The results highlight the potential of AI as a strategic Digital Health tool, especially for early outbreak detection and resource allocation within Brazil’s Unified Health System (SUS).
- Open Access
- 6 November 2025
- Published by Editoriales Iberoamericanos in Revista Políticas Públicas & Cidades
- Vol. 14 (9) , e2705
PREDICTIVE MODELING WITH XGBOOST FOR RESPIRATORY HOSPITALIZATIONS IN SÃO PAULO: PERFORMANCE AND DECISION SUPPORT IN THE PUBLIC HEALTH SYSTEM
This study addresses the rise in respiratory disease hospitalizations associated with air pollution in large urban centers, using São Paulo, 2017 to 2022, as a case study. The objective was to clearly and practically assess the ability of XGBoost to predict daily fluctuations in hospitalizations and to provide operational inputs for public management. We employed a reproducible pipeline with median imputation, stabilization via PowerTransformer, a chronological train and test split at 70 to 30, and hyperparameter tuning with GridSearchCV using TimeSeriesSplit. Interpretability was ensured with SHAP and diagnostics through a correlation matrix. On the test data, the model showed stable performance, R² ≈ 0.65, MAE ≈ 18, RMSE ≈ 22.7, r ≈ 0.81, with errors concentrated around zero. Explanations indicated a dominant contribution of seasonal and temporal markers, month, day of year, and day of week, followed by PM₁₀, PM₂.₅, and NO₂, and the strong correlation between PM₁₀ and PM₂.₅, r = 0.96, confirms redundancy among predictors. We conclude that XGBoost meets the proposed goal by bringing environmental surveillance closer to care management in the Brazilian Unified Health System, SUS, while preserving transparency and practical usefulness. Limitations are acknowledged, and advances are suggested in contextual variables, tail-sensitive loss functions, and benchmarking across algorithms.
- 6 November 2025
- Published by Editoriales Iberoamericanos in Revista Políticas Públicas & Cidades
- Vol. 14 (9) , e2705
Open AccessPREDICTIVE MODELING WITH XGBOOST FOR RESPIRATORY HOSPITALIZATIONS IN SÃO PAULO: PERFORMANCE AND DECISION SUPPORT IN THE PUBLIC HEALTH SYSTEM
This study addresses the rise in respiratory disease hospitalizations associated with air pollution in large urban centers, using São Paulo, 2017 to 2022, as a case study. The objective was to clearly and practically assess the ability of XGBoost to predict daily fluctuations in hospitalizations and to provide operational inputs for public management. We employed a reproducible pipeline with median imputation, stabilization via PowerTransformer, a chronological train and test split at 70 to 30, and hyperparameter tuning with GridSearchCV using TimeSeriesSplit. Interpretability was ensured with SHAP and diagnostics through a correlation matrix. On the test data, the model showed stable performance, R² ≈ 0.65, MAE ≈ 18, RMSE ≈ 22.7, r ≈ 0.81, with errors concentrated around zero. Explanations indicated a dominant contribution of seasonal and temporal markers, month, day of year, and day of week, followed by PM₁₀, PM₂.₅, and NO₂, and the strong correlation between PM₁₀ and PM₂.₅, r = 0.96, confirms redundancy among predictors. We conclude that XGBoost meets the proposed goal by bringing environmental surveillance closer to care management in the Brazilian Unified Health System, SUS, while preserving transparency and practical usefulness. Limitations are acknowledged, and advances are suggested in contextual variables, tail-sensitive loss functions, and benchmarking across algorithms.
- 28 October 2025
- Published by Springer Nature in Remote Sensing in Earth Systems Sciences
- Vol. 9 (1) , 1-13
Active Fire Dynamics in Venezuela
- 28 October 2025
- Published by Springer Nature in Remote Sensing in Earth Systems Sciences
- Vol. 9 (1) , 1-13
Active Fire Dynamics in Venezuela
- 6 December 2024
- Published by Elsevier in Atmospheric Pollution Research
- Vol. 16 (2)
An exploratory study on the association between air pollution and health problems (ICD-10) with an emphasis on respiratory diseases
- 6 December 2024
- Published by Elsevier in Atmospheric Pollution Research
- Vol. 16 (2)
An exploratory study on the association between air pollution and health problems (ICD-10) with an emphasis on respiratory diseases
- 7 September 2024
- Published by Elsevier in Atmospheric Environment
- Vol. 338
Evaluation of the PM2.5 concentrations in South America: Climatological patterns and trend analysis
- 7 September 2024
- Published by Elsevier in Atmospheric Environment
- Vol. 338
Evaluation of the PM2.5 concentrations in South America: Climatological patterns and trend analysis
- 28 August 2024
- Published by Springer Nature
- p. 155-170
Predicting Future Rainfall Scenario in the Brazilian Amazon and Its Socio-Economic Impacts
- 28 August 2024
- Published by Springer Nature
- p. 155-170
Predicting Future Rainfall Scenario in the Brazilian Amazon and Its Socio-Economic Impacts