Forecasting Flight Delays with a Multilayered Memory Fusion Network

One of the biggest worldwide sectors is aviation, hence delays in flight services not only perturb customers but also result in large losses for airlines. Forecasting these delays is still difficult because of the erratic character of elements like climate. Accurate projections are challenging even using accepted analytical methods. This work employs sophisticated deep learning methods to enhance the forecast of aircraft delays—more especially, those resulting from weather-related causes.We investigate their effect on aircraft delays using datasets from both the United States and India, including meteorological fluctuations. Built on a Multilayered Memory Fusion Network, the model captures intricate temporal patterns in the data by merging Bidirectional LSTM (Bi-LSTM) and Long Short-Term Memory (LSTM). This network generates more accurate forecasts and is meant to effectively manage several factors. For the United States dataset, the proposed network attained a Mean Absolute Error (MAE) score of 72.41 and Root Mean Square Error (RMSE) scores of 118.87 and 11.83 and 21.82 for India respectively. Our deep learning methodology clearly predicts flight delays as these performance measures are far better than those attained by conventional machine learning techniques, including linear regression. By using these cutting-edge algorithms, the research provides a more accurate way to forecast flight delays, hence perhaps lowering passenger discontent and airline financial losses.