Williane Gabriele Souza Pereira

Williane Gabriele Souza Pereira

Auto-generated profile, based on publicly available information

Williane Gabriele Souza Pereira

UFPA

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
15 April 2025 in IEEE Access
Verified
Journal Article
Open access
JDJean A. C. Dias
Jean A. C. Dias
PGPedro H. Do V. Guimarães
Pedro H. Do V. Guimarães
WPWilliane G. S. Pereira
Williane G. S. Pereira
LTLeonardo De O. Tamasauskas
Leonardo De O. Tamasauskas
MGMarivan S. Gomes
Marivan S. Gomes
MSMarcos Seruffo
Marcos Seruffo
This study presents a hybrid model, STL-ARIMA-ES-LSTM, developed to improve the accuracy of Gross Primary Productivity (GPP) forecasts in the Amazon region. The model combines seasonal and trend decomposition using Loess (STL) with statistical methods (ARIMA and Exponential Smoothing - ES) and a machine learning technique (Long Short-Term Memory - LSTM). Applied to data from the PE-QFR site, the hybrid model outperformed LSTM alone, with lower prediction error and higher correlation with real data, ensuring a more accurate representation of GPP variability. In addition, the results show the effectiveness of STL decomposition to isolate trend, seasonality and residual components, allowing for more accurate and robust modeling. The study reinforces the potential of hybrid approaches to capture complex environmental dynamics and contributes to a deeper understanding of the carbon cycle, offering promising tools for environmental monitoring and climate change mitigation strategies in the Amazon.

9 October 2024
Verified
Conference Paper
Open access
PDF file
DLDanilo Teixeira Lima
Danilo Teixeira Lima
FMFlávio Rafael Trindade Moura
Flávio Rafael Trindade Moura
WPWilliane Gabriele Souza Pereira
Williane Gabriele Souza Pereira
RZRodrigo Oliveira Zacarias
Rodrigo Oliveira Zacarias
RSRodrigo Pereira dos Santos
Rodrigo Pereira dos Santos
MSMarcos Seruffo
Marcos Seruffo
Este artigo explora como a UX-Tracking, uma ferramenta de captura multimodal, pode auxiliar nos desafios emergentes da Interação Humano-Dados (IHD) no Brasil. Um estudo de caso foi realizado no site do XXIII Simpósio Brasileiro sobre Fatores Humanos em Sistemas Computacionais com cinco universitários, que realizaram tarefas baseadas nas heurísticas de Nielsen, enquanto suas interações eram monitoradas. A UX-Tracking capturou dados como uso do mouse, rastreamento ocular, digitação e comandos de voz, permitindo uma análise detalhada das áreas de interesse e pontos críticos. As visualizações geradas facilitaram a compreensão dos dados, complementando a avaliação de usabilidade com a System Usability Scale (SUS).

20 July 2025
Verified
Conference Paper
Open access
PDF file
JDJean Dias
Jean Dias
WPWilliane G. S. Pereira
Williane G. S. Pereira
Waldemiro José Assis Gomes NegreirosWaldemiro José Assis Gomes Negreiros
Waldemiro José Assis Gomes Negreiros
PGPedro Henrique do Vale Guimarães
Pedro Henrique do Vale Guimarães
ACAlan B. S. Corrêa
Alan B. S. Corrêa
MSMarcos C. da R. Seruffo
Marcos C. da R. Seruffo
To enhance the processing of multispectral images under adverse conditions, such as the presence of clouds, this study compared the neural networks U-Net, DeepLabV3+, and SegFormer using images from the Sentinel-2 satellite, evaluating their performance through metrics such as Intersection over Union (IoU) and Dice coefficient. The results indicate that SegFormer achieved the highest accuracy in cloud detection but with a longer inference time, while U-Net demonstrated a balance between accuracy and efficiency, and DeepLabV3+ stood out for its shorter processing time but lower performance. The study highlights the relevance of neural networks in remote sensing and indicates the need for model optimization.

19 July 2026
Verified
Conference Paper
Open access
PDF file
WPWilliane G. S. Pereira
Williane G. S. Pereira
GMGabriel V. de Melo
Gabriel V. de Melo
Waldemiro José Assis Gomes NegreirosWaldemiro José Assis Gomes Negreiros
Waldemiro José Assis Gomes Negreiros
FCFernando A. R. Costa
Fernando A. R. Costa
LTLeonardo De O. Tamasauskas
Leonardo De O. Tamasauskas
MSMarcos Seruffo
Marcos Seruffo
Accelerated urbanization has expanded urban heat islands, necessitating the precise monitoring of Land Surface Temperature (LST). This study spatially predicts LST in Butantã (SP) for 2018 and 2021 using a high-resolution multiscale approach. To capture the relationships between urban morphology and LST, XGBoost and LightGBM models were compared, with XGBoost demonstrating superior predictive performance (R2 of 0.890 and 0.848). Applying the SHapley Additive exPlanations (SHAP) method to the winning model ensured explainability, revealing the dominance of impervious surfaces in warming, the strong mitigating potential of water bodies and vegetation, and the heat retention induced by topography in valleys.

19 July 2026
Verified
Conference Paper
Open access
PDF file
LTLeonardo de O. Tamasauskas
Leonardo de O. Tamasauskas
Waldemiro José Assis Gomes NegreirosWaldemiro José Assis Gomes Negreiros
Waldemiro José Assis Gomes Negreiros
PGPedro H. Do V. Guimarães
Pedro H. Do V. Guimarães
WPWilliane G. S. Pereira
Williane G. S. Pereira
JDJean A. C. Dias
Jean A. C. Dias
MSMarcos Seruffo
Marcos Seruffo
This study evaluates fusion strategies between ERA5-Land orbital data and INMET surface observations to estimate daily air temperature in Belém, using data from 1994 to 2024. Different Random Forest models were compared, along with SARIMAX, LSTM, and stacking (SARIMAX and RF). The RF model with multivariate fusion achieved the best performance (RMSE = 0.5157 °C; R2 = 0.708; Skill = 6.19%), reducing bias relative to the orbital baseline, while chronological validation confirmed the temporal stability of RF-based models. The results indicate that, under low equatorial thermal variability, tree-based models are the most robust for satellite–surface fusion and thermal downscaling.