This folder is made available as part of the following research paper in Expert Systems with Applications.

Title: Prediction of Flight Delay using Deep Operator Network with Gradient-mayfly Optimisation Algorithm
Authors: Desmond B. Bisandu and Irene Moulitsas

Citation: Desmond B. Bisandu; Irene Moulitsas. Prediction of Flight Delay using Deep Operator Network with Gradient-mayfly Optimisation Algorithm. Expert Systems with Applications 247(2024),123306. https://doi.org/10.1016/j.eswa.2024.123306

Abtract:
Accurate flight delay prediction is fundamental to establishing an efficient airline business. It is considered one of the most critical intelligent aviation systems components. Recently, flight delay has been a significant cause that deprives airlines of good performance. Hence, airlines must accurately forecast flight delays and comprehend their sources to have excellent passenger experiences, increase income and minimise unwanted revenue loss. In this paper, we developed a novel approach that is an optimisation-driven deep learning model for predicting flight delays by extending a state-of-the-art method, DeepONet. We utilise the Box-Cox transformation for data conversion with a minimal error rate. Also, we employed a deep residual network for the feature fusion before training our model. Furthermore, this research uses flight on-time data for flight delay prediction. To validate our proposed model, we conducted a numerical study using the US Bureau of Transportation of Statistics. Also, we predict the flight delay by selecting the optimum weights using the novel DeepONet with the Gradient Mayfly Optimisation Algorithm (GMOA). Our experiment results show that the proposed GMOA-based DeepONet outperformed the existing methods with a Root Mean Square Error of 0.0765, Mean Square Error of 0.0058, Mean Absolute Error of 0.0049 and Mean Absolute Percent Error of 0.0043, respectively. These results also show the importance of optimisation algorithms in deciding the optimal weight to improve the model performance. The efficacy of our proposed approach in predicting flight delays with minimal errors well define from all the evaluation metrics. Also, utilising the prediction outcome of our robust model to release information about the delayed flight in advance from the aviation decision systems can effectively alleviate the passengers’ nervousness.


We perform our experiment on a Personal Computer (PC) with an Intel (R) Core (TM) i7-9700 CPU with a processor speed of 3.00 GHz and 32 GHz RAM. We developed our algorithm with Python programming using TensorFlow Core-2.4.1, TensorFlow GPU-2.4.1, NumPy-1.19.1, pandas-0.25.3, sci-kit learn-0.23.2, Scipy1.5.2, PySimpleGUI-4.29.0 and Matplolib-3.3.1 libraries.


## Contents of this repository
Data: 
This folder contains:
- Datasets called Jan_2021_ontime.csv and Nov_2021_ontime.csv which were used to obtain the results presented in the journal paper.

Source code:
This folder contains two files having the instruction on how to run the code and list of libraries reuquirement; and folders for each of the ML models as named exactly as contained in the paper which implements the proposed Deep Operator Network with Gradient-mayfly Optimisation Algorithm and all the algorithms presented and validated in the journal paper.


Output:
This folder contains:
- Figures called Figure_1_MAE.png, Figure_1_MAPE.png, Figure_1_RMSE.png, Figure_1_MSE.png, Figure_2_MAE.png,Figure_2_MAPE.png, Figure_2_RMSE.png, Figure_2_MSE.png which shows results from the models based on different train/test ratios, The models are: (A)DBN, (B) Gradient Boosting Classifier, (C) Information Gain-SVM, (D) Multi-Agent Approach, (E) DeepLSTM, (F) SSDCA-based Deep LSTM, (G) DeepONet and (H) Proposed GMOA-based DeepOnet.- Figures called Figure 6A.jpg and Figure 6B.jpg which show the EEG signals before applying the preprocessing pipeline, and after applying the preprocessing pipeline, respectively.
- Figures called Figure_1_Prediction_Result_Jan_2021.png and Figure_2_Prediction_Result_Nov_2021.png which are the plots of the prediction results from presented in the journal paper.
- 8 csv files called 1 MAE.csv, 1 MAPE.csv, 1 RMSE.csv, 1 MSE.csv, 2 MAE.csv, 2 MAPE.csv, 2 RMSE.csv, 2 MSE.csv, which contains the evaluation results produced by all algorithms presented and validated in the journal paper.
- 2 csv files called Delay Prediction_Jan_2021_ontime_Figure_1 and Delay Prediction_Nov_2021_ontime_Figure_2 which contains the prediction results produced by all algorithms presented and validated in the journal paper.
