An introduction of a reward-based time-series forecasting model and its application in predicting the dynamic and complicated behavior of the Earth rotation (Delta-T values)

Simultaneous prediction of 10m and 100m wind speeds using a model inspired by brain emotional learning

Predicting wind speed simultaneously at multiple heights, particularly at 10 and 100 metres (m), presents unique challenges due to diverse influences. At lower altitudes, wind speed is significantly affected by surface factors including roughness, vegetation, and man-made structures, causing sharp fluctuations, while at higher altitudes, it is primarily influenced by atmospheric conditions, resulting in smoother flow patterns. Traditional models often require separate systems for each altitude, limiting their efficiency and accuracy. This study introduces the brain emotional learning based on basic and functional memories (BELBFM) model, inspired by adaptive emotional learning mechanisms in the mammalian brain, to predict wind speeds at both altitudes simultaneously. Using ERA5 reanalysis data, BELBFM effectively captures the nonlinear dynamics of wind behavior. Evaluation with data from the Persian Gulf demonstrates BELBFM's high accuracy, enhancing predictive capabilities for applications in renewable energy and structural engineering. This unified model provides a robust and efficient solution for adaptive wind forecasting.