An Approach of Applying Machine Learning Model in Flight Delay Prediction- A Comparative Analysis

Flight delays have become a major issue in the aviation industry, impacting operational efficiency and customer satisfaction. This study proposes a CatBoostClassifier-based approach combined with Feature Engineering, Bayesian Optimization, and Random Over Sampling techniques to improve the accuracy of flight delay predictions. Based on model evaluation results, the use of Feature Engineering and Bayesian Optimization enhances performance compared to the baseline CatBoost model. The CatBoost+FE+Bayes combination achieves an accuracy of 83.32%, higher than the unmodified CatBoost model, which only reaches 82.95%. However, applying the Random Over Sampling technique in the CatBoost+FE+Bayes+ROS combination decreases model performance, reducing accuracy to 81.44%. Regarding other metrics, the CatBoost+FE+Bayes model demonstrates the highest F1-score of 0.62, indicating a balance between precision and recall. Additionally, the Area Under Curve (AUC) analysis reveals that CatBoost+FE+Bayes has the highest AUC value of 0.7793, followed by CatBoost+FE at 0.7768, and the unmodified CatBoost model at 0.7643. Meanwhile, the application of ROS leads to a decrease in AUC value to 0.6787. These findings suggest that utilizing Feature Engineering and Bayesian Optimization significantly enhances flight delay predictions. However, resampling techniques such as ROS do not always positively impact the tested model and can even degrade classification performance. The objective of this research is to develop a more accurate flight delay prediction model through the application of appropriate optimization techniques. The resulting model is expected to improve prediction quality and benefit the aviation industry by optimizing operational efficiency and minimizing the negative impact of delays on passengers.

Delays in flights and other airline operations have significant consequences in quality of service, operational costs, and customer satisfaction. Therefore, it is important to predict the occurrence of delays and take necessary actions accordingly. In this study, we addressed the flight delay prediction problem from a supervised machine learning perspective. Using a real-world airline operations dataset provided by a leading airline company, we identified optimum dataset features for optimum prediction accuracy. In addition, we trained and tested 11 machine learning models on the datasets that we created from the original dataset via feature selection and transformation. CART and KNN showed consistently good performance in almost all cases achieving 0.816 and 0.807 F-Scores respectively. Similarly, GBM, XGB, and LGBM showed very good performance in most of the cases, achieving F-Scores around 0.810.

Nowadays, the civil aviation industry has a high precision demand of flight delay prediction. To make full use of the characteristics of flight data and meteorological data, two flight delay prediction models using deep convolution neural network based on fusion of meteorological data are proposed in this paper. One is DCNN (Dual-channel Convolutional Neural Network), which refers to the ResNet network structure. The other is SE-DenseNet (Squeeze and Excitation-Densely Connected Convolutional Network), combining the advantages of DenseNet and SENet. Firstly, flight data and meteorological data are fused in the model. Then, both DCNN and SE-DenseNet models are used to extract feature automatically based on the fused flight data set. Finally, the softmax classifier is adopted to predict the flight delay level. For proposed DCNN model, both straight channel and convolution channel are designed to guarantee the lossless transmission of the feature matrix and enhance the patency of the deep network. For proposed SE-DenseNet model, a SE module is added after the convolution layer of each DenseNet block, which can not only enhance the transmission of deep information but also achieve feature recalibration in the feature extraction process. The research results indicate that after considering characteristics of meteorological information, the accuracy of the model can be improved 1% compared with only considering the flight information. The two deep convolutional neural networks proposed in this paper, DCNN and SE-DenseNet, can both effectively improve the prediction accuracies, reaching to 92.1% and 93.19%, respectively.

The purpose of this paper is to combine the cloud model method with the Artificial neural network to predict and evaluate flight delay date. In this paper, the flight delay data of the United States in recent 15 years were collected, involving nine airlines and seven delay causes. Then, the flight delay prediction model is obtained by combining neural network and cloud model theory. 36 sets of data are extracted to verify the accuracy of the prediction model. Finally, the delay rate is predicted and the prediction data is evaluated by cloud model. The results show that the amount of data to be processed is reduced to 20 % after combining the cloud model with the neural network. In the model validation, the average expected value deviation of flight delay prediction model is 23.1 %. In the analysis and evaluation of the prediction results, the delay cause 6 is taken as an example, with the highest delay rate of 7.03 % in December. The delay risk assessment results for all months were general. The method provided in this paper can predict flight delays and provide theoretical support for the delay prevention of airlines.

Technology is evolving in a rapid pace with its numerous discoveries, and nowadays, the rate is more than ever before. Data Analytics has become a knowledge and a tool which significantly contributing relentlessly to majority of the discoveries since this can fetch insights to reduce man-machine interactions. Prediction is an integral part of data analytics that provides meaningful information from historical data to support decisions. Machine learning and deep learning is the core of any predictive analytics where both have their own strengths and weakness. Aviation industry around the world are facing severe problems by the flight delays caused by several factors. In order to achieve its target to provide a hassle-free journey, Aviation Industry is continuously researching to reduce flight delays. This research will focus mainly to predict airlines flight delays by analyzing flight data, especially, for the domestic Airlines those moves around the United States of America. Data science methodology has been implemented in order to fetch the end prediction. In order to transform the high dimension data into a low dimension Principal component analysis is used. Deep learning algorithms, widely popular and state-of-the-art prediction technology, are implemented in the prediction modeling phase. By empirical observation, the research can come to a conclusion that by following the data science methodology better performance could be unlocked to help the aviation industry.

Accurate flight delay prediction contains great reference value for airline business and passenger travel. Recent studies have been concentrated on applying machine learning methods to predict the probability of flight delay. Most of the previous prediction methods are built for a single air route or airport. This paper explores a broader spectrum of factors that may potentially affect the flight delay and proposes a gradient boosting decision tree (GBDT) based models for generalized flight delay prediction. To build a dataset for the proposed model, automatic dependent surveillance-broadcast (ADS-B) messages are received, pre-processed, and integrated with other information such as weather condition of airport, flight schedule, and airport information. Since the delay prediction results can be given with higher resolution, the designed prediction tasks contain four different classification tasks. Experimental results show that the proposed GBDT-based model can obtain higher prediction accuracy (87.72% for the binary classification) when handling our limited dataset.

By predicting flight delays, economic losses caused by delay situations can be effectively prevented and reduced. A classification algorithm for flight delay prediction based on unbalanced data is proposed to solve the problem of unbalanced number of delayed and non-delayed samples in the process of flight delay prediction. Firstly, a multi-classification model based on the CycleMLP algorithm is proposed for flight delay prediction. Secondly, the CycleMLP algorithm is improved by using the Focal Loss modified cross-entropy loss function to build the final classification model for flight delay prediction. And the experimental results show that the improved model has better prediction results for delayed flights, with a 5.54% increase in average macro precision and 1.86% increase in accuracy. Finally, the flight delay prediction results are published in the mobile APP application system to provide corresponding advice to passengers and airport departments.

COVID-19 is highly infectious and causes acute respiratory disease. Machine learning (ML) and deep learning (DL) models are vital in detecting disease from computerized chest tomography (CT) scans. The DL models outperformed the ML models. For COVID-19 detection from CT scan images, DL models are used as end-to-end models. Thus, the performance of the model is evaluated for the quality of the extracted feature and classification accuracy. There are four contributions included in this work. First, this research is motivated by studying the quality of the extracted feature from the DL by feeding these extracted to an ML model. In other words, we proposed comparing the end-to-end DL model performance against the approach of using DL for feature extraction and ML for the classification of COVID-19 CT scan images. Second, we proposed studying the effect of fusing extracted features from image descriptors, e.g., Scale-Invariant Feature Transform (SIFT), with extracted features from DL models. Third, we proposed a new Convolutional Neural Network (CNN) to be trained from scratch and then compared to the deep transfer learning on the same classification problem. Finally, we studied the performance gap between classic ML models against ensemble learning models. The proposed framework is evaluated using a CT dataset, where the obtained results are evaluated using five different metrics The obtained results revealed that using the proposed CNN model is better than using the well-known DL model for the purpose of feature extraction. Moreover, using a DL model for feature extraction and an ML model for the classification task achieved better results in comparison to using an end-to-end DL model for detecting COVID-19 CT scan images. Of note, the accuracy rate of the former method improved by using ensemble learning models instead of the classic ML models. The proposed method achieved the best accuracy rate of 99.39%.

Summary A meticulous interpretation of steady-state or unsteady-state relative permeability (Kr) experimental data is required to determine a complete set of Kr curves. In this work, different machine learning (ML) models were developed to assist in a faster estimation of these curves from steady-state drainage coreflooding experimental runs. These ML algorithms include gradient boosting (GB), random forest (RF), extreme gradient boosting (XGB), and deep neural network (DNN) with a main focus on and comparison of the two latter algorithms (XGB and DNN). Based on existing mathematical models, a leading-edge framework was developed where a large database of Kr and capillary pressure (Pc) curves were generated. This database was used to perform thousands of coreflood simulation runs representing oil-water drainage steady-state experiments. The results obtained from these simulation runs, mainly pressure drop along with other conventional core analysis data, were used to estimate analytical Kr curves based on Darcy’s law. These analytically estimated Kr curves along with the previously generated Pc curves were fed as features into the ML model. The entire data set was split into 80% for training and 20% for testing. The k-fold cross-validation technique was applied to increase the model’s accuracy by splitting 80% of the training data into 10 folds. In this manner, for each of the 10 experiments, nine folds were used for training and the remaining fold was used for model validation. Once the model was trained and validated, it was subjected to blind testing on the remaining 20% of the data set. The ML model learns to capture fluid flow behavior inside the core from the training data set. In terms of applicability of these ML models, two sets of experimental data were needed as input; the first was the analytically estimated Kr curves from the steady-state drainage coreflooding experiments, while the other was the Pc curves estimated from centrifuge or mercury injection capillary pressure (MICP) measurements. The trained/tested model was then able to estimate Kr curves based on the experimental results fed as input. Furthermore, to test the performance of the ML model when only one set of experimental data is available to an end user, a recurrent neural network (RNN) algorithm was trained/tested to predict Kr curves in the absence of Pc curves as an input. The performance of the three developed models (XGB, DNN, and RNN) was assessed using the values of the coefficient of determination (R2) along with the loss calculated during training/validation of the model. The respective crossplots along with comparisons of ground truth vs. artificial intelligence (AI)-predicted curves indicated that the model is capable of making accurate predictions with an error percentage between 0.2% and 0.6% on history-matching experimental data for all three tested ML techniques. This implies that the AI-based model exhibits better efficiency and reliability in determining Kr curves when compared to conventional methods. The developed ML models by no means replace the need to conduct drainage coreflooding or centrifuge experiments but act as an alternative to existing commercial platforms that are used to interpret experimental data to predict Kr curves. The two main advantages of the developed ML models are their capability of predicting Kr curves within a matter of a few minutes as well as with limited intervention from the end user. The results also include a comparison between classical ML approaches, shallow neural networks, and DNNs in terms of accuracy in predicting the final Kr curves. The research presented here is an extension of the state-of-the-art framework proposed by Mathew et al. (2021). However, the two main aspects of the current study are the application of deep learning for the prediction of Kr curves and the application of feature engineering. The latter not only reduces the training/testing time for the ML models but also enables the end user to obtain the final predictions with the least set of experimental data. The various models discussed in this research work currently focus on the prediction of Kr curves for drainage steady-state experiments; however, the work can be extended to capture the imbibition cycle as well.

Metabolic dysfunction-associated steatotic liver disease (MASLD) can progress to metabolic dysfunction-associated steatohepatitis (MASH) and liver fibrosis, contributing to a heavier global health burden. Non-invasive diagnostic tools developed using machine learning (ML) and deep learning (DL), two representative artificial intelligence algorithms, are increasingly being explored for MASH and its related fibrosis assessment. This study aimed to compare the diagnostic performance of different ML and DL models and identify the top-performing models for diagnosing MASH and associated liver fibrosis. A systematic review and meta-analysis were conducted across PubMed, Web of Science, Embase and Cochrane Library from inception to May 18, 2025. Pooled area under the receiver operator characteristic curve (AUROC) values with 95 % confidence interval (CI) were calculated. Accuracy, specificity, sensitivity, positive predictive values, and negative predictive values were also recorded. Of 4,314 studies initially identified, 106 met the inclusion criteria, with 35 studies (ML: n=28; DL: n=7) providing data for analysis. Logistic Regression and Neural Network are the most commonly algorithms applied in ML and DL, respectively. The pooled AUROCs for diagnosing MASH were 0.833 (95 %CI: 0.806-0.860) for ML models and 0.841 (95 %CI: 0.782-0.900) for DL models. Light Gradient Boosting Machine (LightGBM) and ResNet50 were the best-performing models for diagnosing MASH within ML and DL algorithms, respectively, achieving corresponding AUROCs of 0.920 (95 %CI: 0.916-0.924) and 0.960 (95 %CI: 0.951-0.969). For fibrosis diagnosis, ML models had a pooled AUROC of 0.826 (95 %CI: 0.792-0.860), with Categorical Boosting (CatBoost) achieving the highest AUROC of 0.960 (95 %CI: 0.950-0.970). DL models yielded the pooled AUROC of 0.875 (95 %CI: 0.816-0.934) for fibrosis diagnosis. Both ML and DL models demonstrated strong diagnostic performance for MASH and liver fibrosis, with DL achieving marginally higher AUROCs. AI-driven approaches show promise in MASLD management.

Flight delays are unavoidable, and they have a substantial financial impact on airlines. Airlines demand an accurate flight delay estimate since the data may be used to improve customer satisfaction and profitability. Many research have been conducted on flight delay modeling and prediction, with the majority of them attempting to predict the delay by extracting important qualities and variables. Due to the large volume of data, dependencies, and large number of parameters, most of the offered solutions are insufficiently accurate. This research presents a Deep Learning-based approach for anticipating aircraft delays (DL).DL is a relatively recent method for tackling issues with a high level of complexity and a large number of data. Besides, DL can extricate key highlights from information naturally. In expansion, since most flight delay information is boisterous, a technique based on stack denoising autoencoder is created and included within the proposed model. Furthermore, the Levenberg-Marquart calculation is utilized to decide weight and inclination fitting values, and the yield is at that point tuned to convey exceptionally precise comes about. Two more structures are created to investigate the effect of the stack denoising autoencoder and the LM method on the model structure.

Social media platforms provide valuable insights into mental health trends by capturing user-generated discussions on conditions such as depression, anxiety, and suicidal ideation. Machine learning (ML) and deep learning (DL) models have been increasingly applied to classify mental health conditions from textual data, but selecting the most effective model involves trade-offs in accuracy, interpretability, and computational efficiency. This study evaluates multiple ML models, including logistic regression, random forest, and LightGBM, alongside DL architectures such as ALBERT and Gated Recurrent Units (GRUs), for both binary and multi-class classification of mental health conditions. Our findings indicate that ML and DL models achieve comparable classification performance on medium-sized datasets, with ML models offering greater interpretability through variable importance scores, while DL models are more robust to complex linguistic patterns. Additionally, ML models require explicit feature engineering, whereas DL models learn hierarchical representations directly from text. Logistic regression provides the advantage of capturing both positive and negative associations between features and mental health conditions, whereas tree-based models prioritize decision-making power through split-based feature selection. This study offers empirical insights into the advantages and limitations of different modeling approaches and provides recommendations for selecting appropriate methods based on dataset size, interpretability needs, and computational constraints.

Data is one of the most important limiting factors of deep machine learning (ML) model in drilling applications. Though a big size of historical data can be available, high-quality cleaned and labeled data is usually limited. In this case study, we show that with limited labeled data, physics-based data augmentation combined with unsupervised learning significantly improves both stability and accuracy in bit wear ML model. It provides a pathway to overcome labeled data shortage and field data quality limitations. Labeled bit wear data is usually limited because only the final bit dull state can be labeled using dull photos for the entire drilling distance. To overcome this difficulty, an encoder-decoder unsupervised ML framework based on Bi-directional LSTM architecture is first applied to the data of entire drilling distance to extract and maximize data learnings. Then, a physics-based wear estimator is implemented in the learned latent space to augment labeled wear dataset, guided by true wear labels and offset-well data. Weighting factor in loss function is applied to optimize augmented and true datasets in final supervised learning step. The proposed real-time bit wear model is built on a combination of physics-based data augmentation and unsupervised data learning method. The model is applied on multiple field bit runs. Results show that by implementing the unsupervised data learnings only, the prediction accuracy is improved by 30% compared to the baseline ML model. By combining physics-based augmentation, the accuracy is further improved by 10%. More importantly, adding physics-based data augmentation significantly reduces prediction variance and unphysical wear outputs, therefore improving prediction stability by more than 30%. It should be noted that the prediction stability of AI/ML model is crucial in real-time application and decision making. The results show physics-based data augmentation not only increases the size of label dataset and prevents model overfitting, but also applies physics-based guidance to the ML model effectively. It is learned weighting factor plays a crucial role in balancing loss contributions from true wear labels and physics-based labels. While low weighting factor of physics-based labels diminishes the augmented data, high weighting factor disrespects the true wear labels leading to a high prediction bias. Overall, the bit wear model study shows physic-based data augmentation combined with unsupervised data learning can effectively improve model accuracy, stability, and overcome labeled data shortage difficulty. The proposed paper shows a case study for the bit wear ML model using a combination of physics-based data augmentation and unsupervised data learning. While labeled data is one of the major challenges of ML models in many drilling applications, this study provides a pathway to improve both accuracy and stability of deep ML models with limited labeled data.

The usage of big data analytics is booming today, with its ability to be used to draw useful insights from past data research. Its uses in the aviation industry have a wide array of applications ranging from predicting flight delays to detecting faults in airplane parts. In this paper, we conducted exploratory data analysis on flight dataset to draw inferences on arrival and departure delays and to identify relationships between flight timings and delays. Using the flight delay data, we identified which flight is mostly prone to delays. The arrived upon conclusions are useful for selecting flights in the future.

A comparison of physical-based and machine learning modeling for soil salt dynamics in crop fields