<![CDATA[Maximum wind speed is an important indicator for assessing wind energy potential; however, it is dynamic, nonlinear, and affected by interactions among meteorological parameters. This study compares Multi-Layer Perceptron (MLP), Bidirectional Long Short-Term Memory (BiLSTM), and Gated Recurrent Unit (GRU) models for maximum wind speed prediction in Bogor. The dataset comprises 3,653 daily observations from the BMKG Citeko Meteorological Station during 2011–2020, including minimum, maximum, and average temperature, relative humidity, rainfall, sunshine duration, prevailing wind direction, and average wind speed. Preprocessing involved data cleaning, missing-value imputation, Min-Max Scaling, and chronological splitting into training, validation, and testing subsets. The three models were trained using equivalent configurations and evaluated using MAE, RMSE, MAPE, and R². MLP achieved the lowest MAE of 0.0796 and MAPE of 33.11%, whereas BiLSTM and GRU achieved the lowest RMSE of 0.1025 and the highest R² of 0.2215. GRU was selected as the preferred model because it matched BiLSTM performance with a simpler architecture and lower computational complexity. Nevertheless, the limited R² indicates that additional atmospheric predictors, higher temporal resolution, and further model optimization are required to improve prediction of extreme wind events]]>
Copyrights © 2026
