Robust and Explainable Semi-Supervised Deep Learning Model for Anomaly Detection in Aviation
Explore the source record for details and available documents.
Milad Memarzadeh↗
Engineering topics
Milad Memarzadeh
Publications and source records attributed to Milad Memarzadeh.
Unsupervised Anomaly Detection in High-Dimensional Flight Data Using Convolutional Variational Auto-Encoder
The modern National Airspace System (NAS) is an extremely safe system. The industry has experienced a steady decrease in fatalities over the years. This can be contributed to both improved flight critical systems with redundant hardware and software protections as well as an increased focus on active monitoring and response to real time and historically identified vulnerabilities by implementing more resilient procedures and protocols. The main practice for identifying vulnerabilities in operations leverages domain expertise using knowledge about how the system should behave with the expected tolerances to known safety margins. This approach works well when the system has a well-defined operating condition. However, the operations in the NAS can be highly complex with various nuances that render it difficult to clearly pre-define all known safety vulnerabilities. With the advancement of data science and machine learning techniques, the potential to automatically identify emerging vulnerabilities in the observed operations has become more practical in recent years. The state-of-the-art anomaly detection approaches in aerospace data usually rely on supervised or semi-supervised learning. However, in many real-world problems such as flight safety creating labels for the data requires huge amount of efforts and is largely expensive. As a result, in this article, we develop a Convolutional Variational Auto-Encoder (CVAE), an unsupervised learning approach for anomaly detection in high-dimensional heterogeneous time-series data. We validate performance of CVAE compared to the state-of-the-art supervised learning approach (as an upper bound) as well as an supervised clustering based on K-Means (as a lower bound) on Yahoo!'s benchmark time series anomaly detection data. Finally, we showcase performance of CVAE on a case study of identifying anomalies in the first 60 seconds of commercial flights' take-offs using Flight Operational Quality Assurance (FOQA) data.
Milad Memarzadeh↗
Multi-Class Anomaly Detection in Flight Data using Semi-Supervised Explainable Deep Learning Model
Identifying precursor for safety incidents in aviation data is a crucial task, yet extremely challenging. The main approach, in practice, leverages domain expertise to define expected tolerances in system’s behavior and alarm exceedance from such safety margins. However, this approach is incapable of identifying unknown risk and vulnerabilities. Machine learning has been long studied and deployed to identify precursors for such anomalies, with the great challenge of the need for sufficient labelled set of data to achieve a reliable and accurate performance. In this article, we develop an explainable deep semi-supervised model for anomaly detection in aviation, building upon recent advancements in the machine learning literature. The proposed model combines feature engineering and classification in the feature space, while leveraging all available data (labelled and unlabeled). Validating on two case studies of anomaly detection in take-off and landing phases of commercial aircraft, we show that our model is able to outperform state-of-the-art supervised anomaly detection model and reach significantly high accuracy and low false alarm with minimum amount of available labelled data.
Anomaly Detection↗
Runway Configuration Management with Offline Reinforcement Learning
Runway configuration management (RCM) is a challenging task, and it affects the efficiency of the National Airspace System (NAS) and airport surface operations significantly. Each airport, depending on the geometry, capacity, local climate patterns, etc. has multiple configurations for the runway usage for arriving and departing flights. Many factors such as the incoming/outgoing traffic load, wind direction and speed, convective weather, cloud ceiling and other environmental factors might affect the choice of a runway configuration at any point in time. However, other factors such as safety measures and regulations, noise abatement, capacity of each configuration, and preference of the air traffic controllers (ATCs) can also play a significant role in selecting the configuration. A sub-optimal selection of the runway configuration, or delay in making configuration changes might result in significant increase in taxi times for aircraft on the surface of the airport, fuel and energy use of the aircraft, and maintenance costs. It can also lead to safety concerns, such as an aircraft performing one or more go-arounds before being able to land. All these factors make RCM an extremely important and challenging decision-making process for the ATCs. The current state of practice sets the runway configuration by the ATCs based on relevant information available at the time including weather, traffic, noise abatement, safety bounds, etc. This makes the decision-making process subjective based on the accuracy of the available information and the bias in human decision making. Unfortunately, this approach yields poor results (e.g., significant delays) if the predicted outcomes are uncertain and their relative impact is not well understood. This is especially evident when the uncertainty increases the size of possible predicted outcomes (combinatorial explosion in possible scenarios) that cannot be handled by human reasoning. On the other hand, an automated approach based on machine intelligence can make use of historical data and search through all (or significant amount of) possible scenarios under uncertainty and make well-informed decisions.
Milad Memarzadeh↗
Quantum-Compatible Variational Segmentation for Image-to-Image Wildfire Detection Using Satellite Data
Wildfire occurrences have been increasing for the past decade, leaving devastating traces across the world. In the recent efforts, remote sensing and airborne missions have been utilized to better understand and manage wildfires. This has resulted in an exponential increase in volume of remote sensing data, which has pushed the need for intelligent automation of data extraction for wildfire studies. Machine learning offers accurate automation in detecting such natural anomalies and enable decision-makers to take actions in a timely manner. Recent advances in machine learning algorithms, namely probabilistic generative methods, allow researchers and decisionmakers to step beyond detection and study “what-if” scenarios for wildfire occurrences. Additionally, they offer better imitations to the stochastic behavior of nature, and wildfire events. However, optimizing the performance of these probabilistic generative models is a computationally expensive process, specially using digital computers. On the other hand, quantum computers have recently shown a promise to reduce computationally costly training of such models and provide performance improvements. There is a body of research investigating the potential for improved machine learning methods in which key operations are performed on a quantum computer. In this study, we propose a probabilistic image-toimage segmentation approach combining a very well-known segmentation method, U-NET, with a Conditional Variational Auto-Encoder (CVAE) to not only detect wildfires but also describe the stochasticity of the phenomenon and be capable of running “what-if” scenarios. Our proposed model is compatible with training on quantum computers, which results in a quantum-assisted image-to-image segmentation approach and can be used to benchmark the potential benefit of quantum computing over the classical one.
quantum↗
Airport Runway Configuration Management with Offline Model-free Reinforcement Learning
Runway configuration management (RCM) deals with the optimal selection of runways to operate on (for arrivals and departures) based on traffic, surface wind speed, wind direction and other environmental variables. RCM is one of the most challenging tasks in air traffic management, as it relies on operational and environmental variables (e.g., weather forecast) that are highly uncertain and complex to model. In this paper, an innovative and automated approach is deployed using offline model-free reinforcement learning to provide decision-support for RCM. The proposed technology processes historical data about variables of interest, decisions made regarding RCM, and their subsequent outcome, to identify a policy that would encourage good decisions and avoid the poor ones. The policy search is guided by an appropriately chosen weighted utility function (e.g., based on minimizing delays and go-arounds). Finally, the performance of the proposed tool is validated using Charlotte Douglas International Airport as the case study, which shows that the proposed method is superior to other conventional rule-based approaches.
Milad Memarzadeh↗
Airport Runway Configuration Management with Offline Model-free Reinforcement Learning
Runway configuration management (RCM) deals with the optimal selection of runways to operate on (for arrivals and departures) based on traffic, surface wind speed, wind direction and other environmental variables. RCM is one of the most challenging tasks in air traffic management, as it relies on operational and environmental variables (e.g., weather forecast) that are highly uncertain and complex to model. In this paper, an innovative and automated approach is deployed using offline model-free reinforcement learning to provide decision-support for RCM. The proposed technology processes historical data about variables of interest, decisions made regarding RCM, and their subsequent outcome, to identify a policy that would encourage good decisions and avoid the poor ones. The policy search is guided by an appropriately chosen weighted utility function (e.g., based on minimizing delays and go-arounds). Finally, the performance of the proposed tool is validated using Charlotte Douglas International Airport as the case study, which shows that the proposed method is superior to other conventional rule-based approaches.
Milad Memarzadeh↗
Quantum-Assisted Variational Segmentation for Image-to-Image Wildfire Detection Using Satellite Data
The quantum computing community has been searching for suitable applications to demonstrate the potential of near-term quantum devices. Quantum machine learning is a potential candidate, particularly using models that cannot be efficiently simulated with classical computers [1, 2]. This work focuses on a transition phase of quantum computers where the quantum machine learning model is still simulable classically but projected not to be simulable as the size of the model grows. Ultimately quantum computers may have advantages for high-dimensional real-world problems. Due to the limited number of qubits in current noisy intermediate-scale quantum (NISQ) devices, the direct application of quantum computers in high dimensional data is not feasible. To remedy this problem, an encoder-decoder architecture can be utilized. The encoder model would transform the high-dimensional data into a compact representation, to a level that small quantum computers can be used today (or in the near future), and the decoder would take the quantum processed outputs back to the high-dimensional space. Addressing the two challenges of quantum machine learning, this work investigates a hybrid supervised generative model with a quantum Ising Born machine embedded as the latent distribution. The model contains four main parts (Figure 1.a.): (1) a U-NET architecture responsible for learning segmentation flow, (2) a Prior network responsible for learning an encoded latent distribution of the input data, (3) a Born machine which represents the latent distribution, and (4) a Posterior network in charge of learning the joint encoded latent distribution of inputs and target data. The initial model, proposed by [3], is optimized by (1) maximizing the overlap of the prior and posterior latent distributions, and (2) minimizing the segmentation loss. The proposed model is designed to be investigated in a simulation environment applied to the real-world application of wildfire segmentation. Specifically, the model is designed to solve the patchy wildfire segmentations of Moderate Resolution Imaging Spectroradiometer (MODIS) by taking the MODIS observations and using Visible Infrared Imaging Radiometer Suite’s (VIIRS) consistent wildfire product as the target. The model solves patchy wildfire segmentations and provides insight into the epistemic errors sourced from model variation. The model utilizes the Born machine as a QUBO solver to represent the latent space as a Bernoulli distribution. The proposed configuration allows the variational segmentation model to leverage the true quantum probabilistic nature and derive a more expressive latent configuration, increasing the model performance in describing wildfire segmentations. The quantum probabilistic information of the Born machine is directly incorporated in the Kullback-Leibler divergence loss in the prior and posterior distributions, forcing the Bernoulli latent distribution to maximize the overlap of input and joint input-target distributions. The proposed model is then trained and compared with a baseline only consisting of direct Bernoulli latent distribution with no Born machine representing the latent space. The models are evaluated based on the segmentation metrics, such as precision, recall, intersect of union, with uncertainty boundaries accounting for the stochastic nature of the model. Our findings show that even in low latent-dimensional space (due to the limit in computational power of the classical quantum simulator), we are able to effectively capture the latent representation and hence the model performs better than the baseline. The findings are a projection for scaling the model into higher dimensional latent space with the Born machine surpassing the baseline performance. Figure 1. Sub-figure (a) demonstrates the architecture for the training phase. The model consists of a Prior and Posterior network that encode inputs and joint input-target data into compact representations, respectively. The Born machine represents the latent distribution, and the U-NET branch learns the segmentation patterns of the data. The stochasticity is introduced to the U-NET through its last layer to create meaningful but stochastic segmentations. Sub-figure (b) represents the inference phase where the model takes the stochastic behavior from the prior network and injects that into the U-NET. Each attempt of inference will generate different but similar segmentations from the same distribution of the wildfire event. REFERENCES [1] Coyle, B., Mills, D., Danos, V., & Kashefi, E. (2020). The Born supremacy: quantum advantage and training of an Ising Born machine. npj Quantum Information, 6(1), 1-11. [2] Liu, J. G., & Wang, L. (2018). Differentiable learning of quantum circuit born machines. Physical Review A, 98(6), 062324. [3] Kohl, S., Romera-Paredes, B., Meyer, C., De Fauw, J., Ledsam, J. R., Maier-Hein, K., ... & Ronneberger, O. (2018). A probabilistic u-net for segmentation of ambiguous images. Advances in neural information processing systems, 31.
quantum machine learning↗
Image-to-Image Wildfire Detection via Quantum-Compatible Variational Segmentation from Remotely-sensed Data
Over the last decade, the incidence of wildfires has surged, causing widespread destruction globally. To better comprehend and manage these incidents, remote sensing and aerial missions have been implemented in recent efforts. However, this has resulted in an exponential rise in the amount of remote sensing data utilization, leading to a need for intelligent automation of data extraction in wildfire studies. Machine learning provides an accurate automated approach for detecting these natural anomalies and facilitates decision-makers to take prompt actions. To make insightful decisions in wildfire management, it is imperative to move beyond simple detection and explore the potential of probabilistic generative machine learning for creating "what-if" scenarios for various wildfire conditions. Such models offer improved representation of the stochastic nature of wildfire events. However, the optimization of these models can be computationally expensive, especially when using classical computers. Quantum computers have recently emerged as a promising solution to reduce the computational cost of training such models and improve their performance. In this study, we aim to utilize quantum-compatible machine learning techniques to implement our probabilistic generative approach. To that end, we propose a supervised probabilistic variational model consisting of a U-NET-based image-to-image component along with encoder and decoder networks which work as a variational autoencoder (VAE) component. Additionally, we explore the type of latent distribution type in the VAE component and implement different means for modeling the prior distribution. We further investigate the quantum-compatible versions of the model compared to the classical counterpart and benchmark potential benefits of quantum compatibility over the classical model.
quantum machine learning↗
Predicting Airport Runway Configurations for Decision-Support Using Supervised Learning
One of the most challenging tasks for air traffic controllers is runway configuration management (RCM). It deals with the optimal selection of runways to operate on (for arrivals and departures) based on traffic, surface wind speed, wind direction, other environmental variables, noise constraints, and several other airport-specific factors. It affects the efficiency of the National Airspace System (NAS) and both surface and airspace operations can benefit from better understanding future runway configurations. In this paper, we present a comprehensive implementation of predictive models for runway configuration estimation from large volumes of historical data. Specifically, operational data from two full years (2018 and 2019) is collected, analyzed, and fused together to build the data product used in this work. The data set differs from prior work in the field in terms of its scope, resolution, and variety of factors collected and considered. Meteorological data is collected from two different sources – current weather conditions from METAR (Meteorological Terminal Aviation Routine Weather Report) and forecast weather conditions from Localized Aviation MOS Program (LAMP). Operational data from the Federal Aviation Administration (FAA) Aviation System Performance Metrics (ASPM) related to scheduled and actual number of arrivals and departures, average taxi times, etc. are collected. NASA’s Sherlock Data Warehouse is used to identify critical information such as go-arounds, and other events that might impact RCM decision-making. All data is collected and aggregated over 15-minute intervals throughout the two years. This provides a resolution like the timescales that might be necessary for runway configuration management decision-making. A variety of supervised learning algorithms are tested including Support Vector Machine, Random Forest, Gradient Boosting, etc. including tuning of the model hyperparameters. The modeling process is applied and presented on two representative U.S. airports – Charlotte Douglas International Airport (KCLT) and Denver International Airport (KDEN). The two airports present different levels of complexity in terms of the total number of configurations used and provide a balanced perspective on the generalizability of the developed approach to other airports in the NAS. Initial results are promising (F1 score of 0.91 at KCLT and 0.83 at KDEN) for data in the test set. The final paper will contain a comprehensive comparison between different models and model building strategies as well as further refined results. Most important predictors for each airport will be identified along with a discussion and recommendations on adapting the framework to other scenarios.
Tejas G Puranik↗
Predicting Airport Runway Configurations for Decision-Support Using Supervised Learning
One of the most challenging tasks for air traffic controllers is runway configuration management (RCM). It deals with the optimal selection of runways to operate on (for arrivals and departures) based on current and forecast of traffic, surface wind speed, wind direction, other environmental variables, noise constraints, and several other airport-specific factors. In this paper, a methodology using supervised learning is developed to build a predictive model for RCM decision-support from large volumes of historical data. Data from two full years (2018 and 2019) related to current and forecast weather, demand/capacity, etc. is collected, analyzed, and fused together. A variety of supervised learning algorithms are tested for predicting runway configuration and hyperparameter tuning is carried out to select the best performing model. The validation process involves two airports of low (Charlotte Douglas International Airport, CLT) and high (Denver International Airport, DEN) complexity of configuration decision-making. The results show significant promise for the two airports with test accuracy of 93% (CLT) and 73% (DEN). The methodology is scalable and generalizable to other airports across the U.S. National Airspace System.
air traffic management↗
Anomaly Detection in Flight Operational Data Using Deep Learning
In this session, we demonstrate two recently developed deep learning models for anomaly detection in flight operational data by the Data Sciences Group at NASA Ames Research Center. The first model is Convolutional Variational Auto-Encoder (CVAE) [1], which is an unsupervised deep encoder-decoder model, designed specifically for finding anomalies in heterogeneous multivariate time series data. We will demonstrate its application to finding anomalies in streaming data from NASA’s Digital Information Platform’s Fuser source. CVAE identifies data instances that are not representative of expected nominal behavior as anomalous. Since it is an unsupervised approach, the flagged anomalies will need to be reviewed by the subject matter experts (SMEs) for validation and labeling and is designed to assist with vulnerability discovery within Safety Monitoring System programs. The second model is Robust and Explainable Semi-supervised Anomaly Detection (RESAD) model [2], which builds on CVAE to allow learning from both minimally labeled data (previously reviewed by the SMEs) as well as majority unlabeled data. RESAD takes advantage of graph theoretic techniques to propagate the labels from the labeled data to the unlabeled data based on a pre-defined similarity metric and structures the learned feature space from flight time-series so that data of the same class would cluster tightly together. This model characteristic is enabled by training with an augmented loss function and allows learning of a more informative feature space for down-stream tasks such as search and active learning. We demonstrate RESAD using data from the NASA DASHlink project [3].
anomaly detection↗
Predicting Airport Runway Configuration for Decision-Support Using Supervised Learning
One of the most challenging tasks for air traffic controllers is runway configuration management (RCM). It deals with the optimal selection of runways to operate on (for arrivals and departures) based on current and forecast of traffic, surface wind speed, wind direction, other environmental variables, noise constraints, and several other airport-specific factors. In this paper, a methodology using supervised learning is developed to build a predictive model for RCM decision-support from large volumes of historical data. Data from two full years (2018 and 2019) related to current and forecast weather, demand/capacity, etc. is collected, analyzed, and fused together. A variety of supervised learning algorithms are tested for predicting runway configuration and hyperparameter tuning is carried out to select the best performing model. The validation process involves two airports of low (Charlotte Douglas International Airport, CLT) and high (Denver International Airport, DEN) complexity of configuration decision-making. The results show significant promise for the two airports with test accuracy of 93% (CLT) and 73% (DEN). The methodology is scalable and generalizable to other airports across the U.S. National Airspace System.
air traffic management↗
Predicting Air Traffic Management Initiatives Using Supervised Learning
Terminal Traffic Management Initiatives (TMIs) such as Ground Stops (GS) and Ground Delay Programs (GDP) are implemented to manage excess demand or lowered capacity at an airport. Air Traffic Flow Management (TFM) specialists identify situations such as aviation constraints, current and forecasted weather conditions, airport demand and capacity, and initiate TMIs for safe and orderly movement of air traffic. In this paper, we outline supervised learning techniques that can be used to predict and recommend TMIs at an airport based on current weather and airport conditions. Our research involves building classic Machine Learning (ML) models such as Logistic Regression, K-Nearest Neighbor, Random Forest and XGBoost, as well as Long short-term memory (LSTM) networks. We trained the models on 3-year historical data (weather, airport demand, capacity and TMIs) from Newark (EWR) airport which was selected based on its higher TMI implementation rates and varied weather conditions. Although Random Forest and XGBoost algorithms are able to predict if a TMI is needed or not, they have difficulty in predicting specific program type. For this purpose, we found that LSTM time-series forecasting models performed better as they also learn from past TMI program type sequences. This study also lays down the foundation for advanced modeling techniques and architectures to predict TMIs in advance for future periods. The ability to predict TMIs in advance will be highly beneficial to the traffic controllers and managers as this will help them to prepare for and manage TMIs more efficiently.
Manoj Agrawal↗
Optimization of Airport Runway Configuration with Forecast-Augmented Offline Reinforcement Learning
Runway configuration Management (RCM) governs the optimal utilization of runways based on variables such as traffic and meteorological conditions, making it a daunting task in air traffic management due to its dependency on volatile operational and environmental factors. This paper improves upon our previous work [1] on using offline model-free reinforcement learning for creating a Runway Configuration Assistance (RCA) decision-support tool. A novel integration of forecast data from LAMP (Localized Aviation Model Output Statistics Program) and TAF (Terminal Area Forecast) is introduced, enhancing the tool’s accuracy and also its adaptability to quick wind changes. The performance is evaluated using two major US airports, Charlotte Douglas International Airport (CLT) and Denver International Airport (DEN). To counter scalability issues presented by the addition of discrete forecast variables, we transitioned to a continuous state space model, ensuring scalability and inclusion of longer forecast data. The results of our experiments reflect significant improvements in the RCA tool’s prediction accuracy.
Sumanth Nethi↗
Exploring Deep-Rooted Networks: Decision Support for Vulnerability Discovery
Explore the source record for details and available documents.
Anomaly detection↗
Applying Machine Learning Tools for Runway Configuration Decision Support
Determining optimal runway configurations at airports, a responsibility assigned to air traffic controllers, is a challenging task. The decision-making process is intricate and involves consideration of many factors such as prevailing wind condition, convective weather, visibility, cloud ceilings, departure and arrival demand, traffic flow, equipment status, and other airport constraints. In a previous work, we developed a Runway Configuration Assistance tool using an offline reinforcement learning method called conservative Q-learning. In this paper, we evaluate and validate our Runway Configuration Assistance tool as a decision support for air traffic controllers. We validated our tool using three airports with differing levels of complexity: Charlotte Douglas International Airport, Denver International Airport, and Dallas Fort Worth International Airport. We quantified the performance of the Runway Configuration Assistance tool based on (1) agreement with historical air traffic controller decisions and (2) violation of decisions that would be obvious to subject-matter experts. Our tool showed promising results in both performance metrics for the three airports, despite the complexities in the runway configuration decision-making process. We also discuss challenges in using machine learning in general to aid air traffic management and identify deployment considerations for the Runway Configuration Assistance tool.
Runway Configuration Management↗
A Machine Learning Approach to Improve Air Traffic Management Initiatives
Collaborating closely with commercial air carriers and related organizations, the Federal Aviation Administration(FAA) regulates air traffic and ensures the safety and efficiency of air operations. Air traffic controllers make strategic decisions, such as delaying, rerouting, or canceling flights, partly based on guidance provided by the FAA’s Air TrafficControl System Command Center (ATCSCC). The guidance includes, among other things, control measures known asTraffic Management Initiatives (TMIs) designed to enhance safety and improve operational efficiency. TMIs play a crucial role in managing the demand and capacity within the U.S. National Airspace System (NAS). Two major TMIs that are routinely used (primarily to mitigate the adverse effects of bad weather) are Ground Delay Programs (GDPs) andGround Stops (GSs). In a GDP, flights destined for airports facing thunderstorm activity experience delays at their origin airports. This proactive approach minimizes the risk of routing aircraft through hazardous weather conditions and also replaces (fuel burning) airborne delays with ground delays. In a GS, a temporary restriction is imposed on the departure or arrival of aircraft at a specific airport or within a designated airspace. Although other TMIs (e.g., miles-in-trail) are also implemented as part of (air) traffic flow management in the NAS, the focus of this work is on GDPs and GSs. Since TMIs, by design, lead to flight delays or cancellations, it is crucial to put in place the right set of parameters(e.g., scope and duration of the GDP). For example, when the end time of a GDP extends beyond what is necessary, it imposes unnecessary delays on departing flights. This situation could occur as a result of inaccurate prediction of the(required) duration of the GDP based on the weather forecast. On the other hand, if a GDP ends prematurely before the underlying capacity constraints are resolved at the destination airport, it may result in airborne holding. The delicate balance lies in matching the termination of the GDP precisely with the resolution of capacity constraints, avoiding both the imposition of unnecessary ground delays and the need for airborne holding due to premature program termination.Failing to specify the right parameters for TMIs also leads to flight delays, creating a significant obstacle in managing the increasing traffic volumes causing increased work load for the controllers. To address this issue, we propose the integration of Machine Learning (ML) models in the traffic flow management(TFM) pipeline. In current operations, decisions are made by human experts based on extensive training, historical patterns, available traffic and weather data. Since we have an abundance of data from past events that tell us the likely impact of various TMIs, by ingesting historical data, properly trained ML models can offer valuable insights and aid human decision-making. With the FAA increasingly exploring advanced analytics, ML emerges as a focal point for enhancing TFM within the National Airspace System (NAS). As a first step, this study aims to provide traffic controllers with decision-making support for the issuance and adjustment of TMIs. Data analytics and machine learning have been previously employed to address some of the challenges associated with TMIs. Numerous studies have concentrated on various facets of TMI issuance, exploring factors influencing TMI parameters, including arrival rate, airport capacity, and delay prediction. For example, using weather forecasts, several statistical methods were used to produce probabilistic capacity profiles which in conjunction with deterministic models provided insights into the GDP planning process [1–4]. The downside of using deterministic models is that they rely on fixed inputs and predetermined rules, which lack the ability to account for the inherent uncertainty and variability present in real-world scenarios. In a separate series of studies, researchers aimed to predict the occurrences of GDPs and GSs. The majority of these studies utilized various supervised learning methods, including Decision Trees, Naive Bayes, Support VectorMachines, and Random Forests to analyze the influence of weather conditions and arrival demand on TMI incidents[5–8]. However, these studies primarily focused on predicting the incidence of TMIs without explicitly addressing the scope of TMIs, including their duration and their geographical coverage. Furthermore, the emphasis of these studies was largely on GDPs, given their higher frequency and longer duration when compared to GSs. A limited number of studies focused on predicting the parameters of TMIs, specifically addressing their duration and extent. In one such study focusing on optimizing the TMI parameters at San Francisco International Airport (SFO),the authors utilized a probabilistic forecast of fog [9]. They simulated various capacity scenarios based on the (fog)burn-off forecasts, selecting GDP parameters that minimized airborne and overall ground delays. However, this approach exclusively emphasizes stratus (fog) burn-off as the primary determinant of GDP and GS, neglecting other influential factors like severe weather events, runway closures, lower capacity than traffic demand, and other important variables. Given the complexity of predicting the TMI and determining its scope, we seek a more holistic approach. We aim to consider all significant factors that could impact TMIs and their parameters. What sets this research apart is the fusion of all data sources relevant to the issuance and adjustment of TMIs and it represents the first comprehensive attempt to optimize TMIs in this manner. Since this comprehensive solution involves various aspects, we break down the problem into smaller components and input all parameters into a unified model called the “TMI Adjuster”. Figure 1 shows the overall framework and the list of datasets used in each model. The objective of the TMI Adjuster module is to deliver reliable, consistent and expedited recommendations for the progression, adjustment, and termination of TMIs. The ML solution entails developing a pipeline capable of predicting the necessity of a TMI (e.g., GS or GDP) along with its various parameters. For example, in the case of a GS, this includes the scope of the GS either in terms of distance from the destination airport or based on pre-defined airspace sectors. Here, scope refers to those regions and departing airports that are subject to the GS. In this paper, we concentrate on the issuance of GSs in the three major airports in the New York area — LaGuardia(LGA), John F. Kennedy International (JFK), and Newark Liberty International (EWR). We fuse traffic, weather and other relevant aviation data from years 2017 to 2019 to train and validate the ML models. In particular, we use the following datasets: •Terminal Aerodrome Forecast (TAF): meteorological forecasts specific to each airport, issued four times a day, covering predefined time periods. •TMI data: includes all GSs and GDPs along with their respective parameters. •Aviation System Performance Metrics (ASPM): includes traffic related data such as aircraft delays, arrival, and departure rates. •Notices to Airmen (NOTAMs): utilized to extract runway closure data and manage interdependencies between terminals in close proximity. •Flight cancellation data •Airspace Flow Programs (AFP): includes information on flight airborne holdings caused by TMIs. The data preprocessing entails transforming ASPM, TMI, AFP, NOTAMs, and weather data into an hourly format and consolidating all datasets by merging them based on date and time as the primary key. The TMI Adjuster framework comprises two parallel models: one dedicated to GS and a second model focused on GDP. As previously mentioned, our specific focus is on the GS model as a multi-classification problem. In this framework, each data point of the GS model input summarizes ten hours of data. Specifically, the data loader for the GS model generates the input and output of the model as follows: at a given time step, the input includes the actual traffic, weather, and TMI data from the two-hour window before the time step, alongside the weather forecast and scheduled traffic for the next 8 hours starting from the time step. Based on this information, the output of the GS model for each time interval consists of three dimensions. The first dimension represents a binary decision on whether there should be a GS in place for the next hour or not. The second dimension is related to the scope of the GS in the United States, and the third dimension is related to the scope of the GS in Canada (i.e., to determine if the GS impacts airports in Canada).One of the challenges with TMI modeling is the sparsity of TMI events, particularly regarding its scope. To address this challenge in the scope of the GS model output, we implement grouping. The GS scope for the US region is defined based on a list of centers that should be included when the GS is in place. With 20 centers in the US, we utilized historical data to group them into 4 categories. In particular, we summarized our historical data in a graph format where nodes represent centers, and link weights are defined based on the co-occurrence of centers in the scope parameter ofTMIs. By identified strongly connected components in this graph, we were able to partition the centers into four groups. We consider two model structures for the GS Model. Firstly, a hierarchical classification model [10], where the human decision-making for a GS is of hierarchical nature. The decision-maker first decides whether there is a need fora GS, and if the answer is yes, determines the scope. A hierarchical classification model organizes the problem into a class hierarchy, typically a tree or a Directed Acyclic Graph (DAG) structure, and considers the dependency of the decision in the previous step to the next component [10]. Here, we employ the local classifier per level approach, which involves training one multi-class classifier for each level of the class hierarchy. The second structure is the independent structure. In this setting, as the name suggests, we do not consider the dependency of the decisions in the different dimensions of the output of the model. Instead, for each dimension, we train a multi-class classifier independently. Table 1 summarizes GS model statistics for training, validation and testing. The table documents the effect of limiting data to the time steps when there was actually a TMI in place or when a TMI had just terminated. This resulted in a more balanced distribution of the GS class(GS positive class)versus “No GS”(GS negative class), which might help the training process. While JFK and LGA follow very similar distributions, with 40% and 42% GS positive class respectively, EWR has proportionally fewer GS incidents at 28%. Our subsequent phase involves evaluating the performance of both hierarchical structure and independent structure using different state-of-the-art multi-class classifier models such as Random Forest, Decision Trees, K-nearest Neighbors, and Logistic Regression and forecast the duration and scope of the GSs.
Farzan Masrour Shalmani↗