Décio Alves

Décio Alves


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
13 October 2023 in Computers
Verified
Journal Article
Open access
PDF file
DADécio Alves
Décio Alves
Fabio MendonçaFabio Mendonça
Fabio Mendonça
Sheikh Shanawaz MostafaSheikh Shanawaz Mostafa
Sheikh Shanawaz Mostafa
Morgado DiasMorgado Dias
Morgado Dias
Wind forecasting, which is essential for numerous services and safety, has significantly improved in accuracy due to machine learning advancements. This study reviews 23 articles from 1983 to 2023 on machine learning for wind speed and direction nowcasting. The wind prediction ranged from 1 min to 1 week, with more articles at lower temporal resolutions. Most works employed neural networks, focusing recently on deep learning models. Among the reported performance metrics, the most prevalent were mean absolute error, mean squared error, and mean absolute percentage error. Considering these metrics, the mean performance of the examined works was 0.56 m/s, 1.10 m/s, and 6.72%, respectively. The results underscore the novel effectiveness of machine learning in predicting wind conditions using high-resolution time data and demonstrated that deep learning models surpassed traditional methods, improving the accuracy of wind speed and direction forecasts. Moreover, it was found that the inclusion of non-wind weather variables does not benefit the model’s overall performance. Further studies are recommended to predict both wind speed and direction using diverse spatial data points, and high-resolution data are recommended along with the usage of deep learning models.

1 October 2024 in Environmental Research Communications
Verified
Journal Article
Open access
DADécio Alves
Décio Alves
FMFábio Mendonça
Fábio Mendonça
SMSheikh Shanawaz Mostafa
Sheikh Shanawaz Mostafa
FMFernando Morgado-Dias
Fernando Morgado-Dias
This study examines the application of machine learning to enhance wind nowcasting by using a Kolmogorov-Arnold Network model to improve predictions from the Global Forecast System at Madeira International Airport, a site affected by complex terrain. The research addresses the limitations of traditional numerical weather prediction models, which often fail to accurately forecast localized wind patterns. Using the Kolmogorov-Arnold Network model led to a substantial reduction in wind speed and direction forecast errors, with a performance that reached a 48.5% improvement to the Global Forecast System 3 h nowcast, considering the mean squared error. A key outcome of this study comes from the model’s ability to generate mathematical formulas that provide insights into the physical and mathematical dynamics influencing local wind patterns and improve the transparency, explainability, and interpretability of the employed machine learning models for atmosphere modeling.

12 September 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
DADécio Alves
Décio Alves
Fabio MendonçaFabio Mendonça
Fabio Mendonça
Sheikh Shanawaz MostafaSheikh Shanawaz Mostafa
Sheikh Shanawaz Mostafa
Morgado DiasMorgado Dias
Morgado Dias
Wind factors significantly influence air travel, and extreme conditions can cause operational disruptions. Machine learning approaches are emerging as a valuable tool for predicting wind patterns. This research, using Madeira International Airport as a case study, delves into the effectiveness of feature creation and selection for wind nowcasting, focusing on predicting wind speed, direction, and gusts. Data from four sensors provided 56 features to forecast wind conditions over intervals of 2, 10, and 20 min. Five feature selection techniques were analyzed, namely mRMR, PCA, RFECV, GA, and XGBoost. The results indicate that combining new wind features with optimized feature selection can boost prediction accuracy and computational efficiency. A strong spatial correlation was observed among sensors at different locations, suggesting that the spatial-temporal context enhances predictions. The best accuracy for wind speed forecasts yielded a mean absolute percentage error of 0.35%, 0.53%, and 0.63% for the three time intervals, respectively. Wind gust errors were 0.24%, 0.33%, and 0.38%, respectively, while wind direction predictions remained challenging with errors above 100% for all intervals.

25 June 2024 in Pure and Applied Geophysics
Verified
Journal Article
Open access
PDF file
DADécio Alves
Décio Alves
FMFábio Mendonça
Fábio Mendonça
SMSheikh Shanawaz Mostafa
Sheikh Shanawaz Mostafa
FMFernando Morgado-Dias
Fernando Morgado-Dias
In aviation, accurate wind prediction is crucial, especially during takeoff and landing at complex sites like Gran Canaria Airport. This study evaluated five Deep Learning models: Long Short-Term Memory (LSTM), Vanilla Recurrent Neural Network (vRNN), One-Dimensional Convolutional Neural Network (1dCNN), Convolutional Neural Network Long Short-Term Memory (CNN-LSTM), and Gated Recurrent Unit (GRU) for forecasting wind speed and direction. The LSTM model demonstrated the highest precision, particularly for extended forecasting periods, achieving a mean absolute error (MAE) of 1.23 m/s and a circular MAE (cMAE) of 15.80° for wind speed and direction, respectively, aligning with World Meteorological Organization standards for Terminal Aerodrome Forecasts (TAF). While the GRU and CNN-LSTM also showed promising results, and the 1dCNN excelled in wind direction forecasting over shorter intervals, the vRNN lagged in performance. Additionally, the autoregressive integrated moving average model underperformed relative to the DL models, underscoring the potential of DL, particularly LSTM, in enhancing TAF accuracy at airports with intricate wind patterns. This study not only confirms the superiority of DL over traditional methods but also highlights the promise of integrating artificial intelligence into TAF automation.

1 January 2025 in Weather and Forecasting
Verified
Journal Article
Closed access
PDF file
DADécio Alves
Décio Alves
FMFábio Mendonça
Fábio Mendonça
SMSheikh Shanawaz Mostafa
Sheikh Shanawaz Mostafa
FMFernando Morgado-Dias
Fernando Morgado-Dias
This work introduces a deep learning architecture tailored for accurate wind speed and direction forecasting for airports using a grid-based input. Moving beyond the limitations of conventional forecasting methods, which struggle with rapid and localized atmospheric changes and demand substantial computational power, this study positions a machine learning approach as a superior alternative for wind nowcasting. By employing a comprehensive dataset covering 75 years, the proposed model distinguishes itself by achieving a mean absolute error of 1.26 m s−1 for wind speed and 16.18° for wind direction in the examined location, Madeira International Airport area. The model’s robustness was further validated using transfer learning across 10 global airport areas, each with diverse atmospheric conditions, resulting in consistent accuracy. Additionally, a precision forecast focused specifically on the runway was conducted, and its performance was found to be consistent with the broader spatial area forecasts. These results underscore the potential of machine learning in wind prediction for aviation, highlighting a promising pathway for future advancements in weather forecasting technology. Significance Statement: This study introduces a machine learning model that demonstrates the potential for improving spatial grid and runway wind forecasts in aviation. The model achieves a mean absolute error of 1.26 m s−1 for wind speed and 16.18° for wind direction within a region measuring 10° in both latitude and longitude. It also reduces computational demands and enhances processing speed, generating 6-h ahead forecasts in just 6 s.

1 June 2025 in Environmental Research Communications
Verified
Journal Article
Open access
PDF file
DADécio Alves
Décio Alves
Margarida Belo-PereiraMargarida Belo-Pereira
Margarida Belo-Pereira
FMFábio Mendonça
Fábio Mendonça
FMFernando Morgado-Dias
Fernando Morgado-Dias
Low visibility conditions caused by phenomena such as fog, heavy rain, or snowfall impose major operational and safety challenges at airports. Conventional numerical weather prediction models, although improved over time, still struggle to forecast low visibility accurately due to scale mismatches and uncertainties in physical parameterizations, among other factors. This review synthesizes findings on data-driven solutions, including machine learning and deep learning, that harness large datasets to reveal hidden patterns, offering better performance and adaptability. Ensemble methods and the integration of multiple data sources further enhance accuracy, particularly for short lead times. Several methods achieve correlation coefficients above 0.90 and root mean square error below 1 km, yet generalization and integration into real-time airport operations remain underexplored. Future work should focus on transferability across diverse climates, integration with advanced operational tools, and bridging gaps between model complexity and user interpretability. The next generation of hybrid forecasting frameworks has the potential to enhance safety, limit economic losses, and improve resilience in airport operations.