Airport congestion monitoring

Abstract

The invention discloses airport congestion monitoring. An apparatus for airport congestion monitoring includes one or more processors configured to obtain historical data corresponding to historical usage metrics for a particular airport from one or more global data sources associated with aircraft traffic. The one or more processors are configured to process the historical usage metrics to generate a distribution model associated with usage of the particular airport. The one or more processors are configured to obtain data corresponding to a current usage metric for a particular airport from one or more global data sources. The one or more processors are further configured to determine a degree of airport congestion for the particular airport based on the distribution model and a current usage metric for the particular airport.

Description

Technical Field

[0001] The present disclosure generally relates to monitoring airport congestion. Background Art

[0002] Air traffic networks are highly dependent on airport arrival and departure processes, which are associated with capacity constraints and delay propagation. In order to minimize delays in air traffic networks and produce an improved balance between demand and capacity balance, it is important to accurately assess and predict potential congestion at airports.

[0003] Traditionally, congestion at airports has been measured by comparing scheduled times with the actual times of flights departing or arriving at the airport. For example, a traditional metric used to calculate congestion is the average departure delay over a time period—for example, the average of the differences between the scheduled departure time and the actual departure time for each flight. However, in addition to not being easily accessible outside of each specific airport, flight schedule information is often inaccurate and can change significantly over time.

[0004] Another traditional approach that airports may use is to calculate congestion based on passenger flows and available resources, such as ground personnel and tower air traffic controllers. This approach works well to generate customized congestion calculations for a specific airport, but because the input data (e.g., passenger flows and resource availability) is not globally available and the models used may be airport-specific, the practicality of these techniques is largely limited to local calculations at each specific airport.

[0005] An improved system for predicting potential airport congestion that does not rely on schedule information or specific data available only at each specific airport would enable enhanced operations and efficiencies of the air traffic network. Summary of the Invention

[0006] One aspect of the subject matter disclosed in detail below is an apparatus comprising one or more processors configured to obtain historical data corresponding to historical usage metrics for a particular airport from one or more global data sources associated with aircraft traffic. The one or more processors are configured to process the historical usage metrics to generate a distribution model associated with usage at the particular airport. The one or more processors are configured to obtain data corresponding to current usage metrics for the particular airport from the one or more global data sources. The one or more processors are further configured to determine a level of airport congestion at the particular airport based on the distribution model and the current usage metrics for the particular airport.

[0007] Another aspect of the subject matter disclosed in detail below is a method comprising obtaining, at one or more processors, historical data from one or more global data sources associated with aircraft traffic, the historical data corresponding to historical usage metrics for a particular airport. The method comprises processing, at the one or more processors, the historical usage metrics to generate a distribution model associated with usage at the particular airport. The method comprises obtaining, at the one or more processors, data corresponding to current usage metrics for the particular airport from the one or more global data sources. The method further comprises determining a level of airport congestion for the particular airport based on the distribution model and the current usage metrics for the particular airport.

[0008] Another aspect of the subject matter disclosed in detail below is a non-transitory computer-readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to obtain historical data corresponding to historical usage metrics for a particular airport from one or more global data sources associated with aircraft traffic. The instructions, when executed by the one or more processors, cause the one or more processors to process the historical usage metrics to generate a distribution model associated with usage at the particular airport. The instructions, when executed by the one or more processors, cause the one or more processors to obtain data corresponding to current usage metrics for the particular airport from the one or more global data sources. The instructions, when executed by the one or more processors, further cause the one or more processors to determine a level of airport congestion at the particular airport based on the distribution model and the current usage metrics for the particular airport.

[0009] The features, functions, and advantages described herein can be achieved independently in various implementations or may be combined in yet other implementations further details of which can be found with reference to the following description and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 is a diagram illustrating a system for monitoring airport congestion according to some embodiments of the present disclosure.

[0011] Figure 2 According to some embodiments of the present disclosure Figure 1 Diagram of the components of a system.

[0012] Figure 3 According to some embodiments of the present disclosure, Figure 1 A diagram of the operations performed by the system.

[0013] Figure 4 According to some embodiments of the present disclosure, Figure 1 A diagram of the operations performed by the system.

[0014] Figure 5 According to some embodiments of the present disclosure, Figure 1 Illustration of the probability distribution generated by the system.

[0015] Figure 6 Is shown using Figure 1 A flow chart of an embodiment of a method of a system for monitoring airport congestion.

[0016] Figure 7 is a block diagram of a computing environment including a computing device configured to support aspects of computer-implemented methods and computer-executable program instructions (or code) according to the present disclosure. DETAILED DESCRIPTION

[0017] Aspects disclosed herein provide systems and methods for monitoring airport congestion. Conventional techniques for monitoring airport congestion often rely on schedule information and / or other data, such as passenger flow and resource availability, that may be inaccurate and difficult to access outside of each specific airport, thereby making it difficult for air traffic management to predict potential airport congestion for air traffic between multiple airports.

[0018] The present disclosure addresses the problem of using airport data, which is often inaccurate or difficult to access, to predict potential airport congestion by introducing techniques for using globally available data to calculate congestion at any airport in the world where such data is available. According to the disclosed techniques, airport congestion is calculated based on information that can be extracted from three different types of globally available data: surveillance information (e.g., position reports), Airport Map Database (AMDB) data, and weather reports.

[0019] Airport traffic information can be calculated in real time from such globally available data and used to determine the level of congestion at each airport of interest. Examples of traffic information that can be used include, for a specific time interval and at a specific airport, the number of taxi operations for arriving aircraft, the number of taxi operations for departing aircraft, the number of aircraft that have taken off, the number of aircraft that have landed, the number of aircraft on approach, the number of aircraft moving on the ground, and the number of aircraft waiting. These traffic counts can be determined using a sliding window to measure the occurrence of various time intervals. In addition, weather information can be used to distinguish different types of weather conditions (such as different visibility conditions) at the airport during each time interval. This information can be grouped by airport and hour of the day to obtain a historical data distribution of the total operations that occurred at a given airport at that hour. The historical data distribution can be further refined based on the different types of weather conditions at the given airport where the operations occurred.

[0020] In order to reduce the storage requirements, transmission bandwidth, and complexity associated with large sets of raw historical data, a distribution model generator such as a kernel density estimator (KDE) is used to obtain a probability density function of the raw data that describes the distribution of each historical data. One of the benefits of using KDE to represent the distribution of historical data is that KDE can be used with both univariate and multivariate distributions, and KDE models can be used to obtain statistics from the distribution with relatively low computational complexity.

[0021] Once a KDE model is generated based on historical data for a specific airport, time of day, and weather conditions, one or more percentiles can be calculated, such as the 95th and 99th percentiles for each distribution. These percentiles can be used to define an operational region associated with the congestion state of each airport at each time of day and weather conditions.

[0022] Systems employing the disclosed technology thus use data-driven statistical methods to determine or predict congestion at a particular airport at a specific time based on a comparison of current traffic operations and weather conditions with a historical data distribution determined for that airport. For example, the system can determine the airport's current congestion status based on the airport's current traffic operations and weather conditions (e.g., based on a KDE probability density function above or below the 95th and / or 99th percentiles). According to an embodiment, when the operating conditions reach the 95th percentile, the system generates a warning message for that airport to inform customers that the airport is becoming congested and delays are possible. Similarly, when the operating conditions reach the 99th percentile, another message can be generated to report a fully congested state. When the operating conditions fall back below the 95th percentile, another message can be generated to announce that the airport is no longer congested.

[0023] Thus, the disclosed systems and methods provide an accurate and global calculation of airport congestion by using publicly available data sources instead of incomplete data sets or data that is specific to individual airports and not globally available, thereby providing a holistic overview of the state of airport congestion worldwide. Consequently, the use of the disclosed systems and methods enables more accurate flight planning.

[0024] Specific embodiments are illustrated in the accompanying drawings and the following description. All drawings are covered by the present solution, which has common features across the various drawings. The drawings include multiple embodiments of possible different types of systems, devices, and operations in conjunction with the present solution. It should be understood that those skilled in the art will be able to design various arrangements that, although not explicitly described or shown herein, embody the principles described herein and are included within the scope of the claims that follow this description. In addition, any embodiments described herein are intended to aid in understanding the principles of the present disclosure and are to be construed as not limiting. Therefore, the present disclosure is not limited to the specific embodiments or examples described below, but is defined by the claims and their equivalents.

[0025] Specific embodiments are described herein with reference to the accompanying drawings. In the description, common features are indicated by common reference numerals throughout the drawings. In some of the drawings, multiple embodiments of a particular type of feature are used. Although the features are physically and / or logically different, the same reference numeral is used for each, and different instances are distinguished by adding a letter to the reference numeral. When features are referred to herein as a group or type (e.g., when a particular one of the features is not mentioned), the reference numeral is used without a distinguishing letter. However, when a particular feature of a plurality of features of the same type is referred to herein, the reference numeral is used with a distinguishing letter. For example, with reference to Figure 1 , a plurality of usage metric generators are shown and associated with reference numerals 130A and 130B. When referring to a specific one of these usage metric generators (such as usage metric generator 130A), the distinguishing letter "A" is used. However, when referring to any one of these usage metric generators or these usage metric generators as a group, the reference numeral 130 is used without the distinguishing letter.

[0026] As used herein, various terms are used for the purpose of describing particular examples and are not intended to be limiting. For example, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. Further, some features described herein may be singular or plural. For illustration, Figure 7 Depicts a system comprising one or more processors ( Figure 7 720), indicating that the device may include a single processor 720 or may include multiple processors 720. For ease of reference herein, such features are often introduced as "one or more" features and are then referred to in the singular unless aspects related to multiple features are being described.

[0027] The terms "comprise," "comprises," and "comprising" are used interchangeably with "include," "includes," or "including." Additionally, the term "wherein" is used interchangeably with the term "wherein." As used herein, "exemplary" indicates an embodiment, implementation, and / or aspect and should not be construed as limiting or indicating a preference or preferred implementation. As used herein, ordinal terms (e.g., "first," "second," "third," etc.) used to modify an element (such as a structure, component, operation, etc.) do not, by themselves, indicate any priority or order of the element relative to another element, but merely distinguish the element from another element having the same name (but with respect to the use of the ordinal term). As used herein, the term "set" refers to a grouping of one or more elements, and the term "plurality" refers to a plurality of elements.

[0028] As used herein, "obtain," "generate," "compute," "use," "select," "access," and "determine" are interchangeable unless the context indicates otherwise. For example, "obtaining," "generating," "computing," or "determining" a parameter (or signal) may refer to actively generating, calculating, or determining a parameter (or signal) or may refer to using, selecting, or accessing an already generated parameter (or signal), such as by another component or device. As used herein, a device "configured to" perform an operation includes dedicated circuitry, hardware, or other components that enable the operation to be performed by the device. As an example, a general-purpose processor is programmed with instructions to produce a dedicated processor configured to perform the specific operation, wherein the instructions, when executed by the processor, cause the processor to perform the specific operation. A device may be configured to perform multiple operations. A device configured to perform an operation does not necessarily preclude the device from being configured to perform other operations.

[0029] As used herein, “coupled” may include “communicatively coupled,” “electrically coupled,” or “physically coupled,” and may also (or alternatively) include any combination thereof. Two devices (or components) may be directly coupled or indirectly coupled (e.g., communicatively coupled, electrically coupled, or physically coupled) via one or more other devices, components, wiring, buses, networks (e.g., wired networks, wireless networks, or combinations thereof). Two electrically coupled devices (or components) may be included in the same device or different devices and may be connected via electronics, one or more connectors, or inductive coupling, as illustrative, non-limiting examples. In some implementations, two devices (or components) coupled in a communicative manner (e.g., in electrical communication) may, for example, send and receive electrical signals (digital or analog) directly or indirectly via one or more wiring, buses, networks, or the like. As used herein, “directly coupled” is used to describe two devices that are coupled (e.g., communicatively coupled, electrically coupled, or physically coupled) without an intervening component.

[0030] refer to Figure 1 , shows a system 100 including components associated with monitoring airport congestion. System 100 includes a first subsystem 102 and a second subsystem 104 coupled to one or more global data sources 120. Global data sources 120 include one or more global data sources associated with aircraft traffic. For example, global data sources 120 may include an airport map database that provides map data regarding runways, taxiways, etc. at various airports, an aircraft tracking data source that provides positional data (e.g., radar surveillance data) for aircraft near the airport, and a weather data source that provides current weather data, weather forecasts, or both for the airport.

[0031] First subsystem 102 is configured to obtain historical data 122 corresponding to historical usage metrics 132A for a particular airport from global data source 120 and generate distribution model 142 associated with usage of the particular airport. First subsystem 102 includes usage metrics generator 130A coupled to distribution model generator 140.

[0032] The usage metric generator 130A is configured to process the historical data 122 to obtain historical usage metrics 132A for a particular airport. Figure 2 As further described, the historical usage metrics 132A may include taxi-in data, taxi-out data, departure data, arrival data, approach data, ground movement data, weather data, aircraft holding data, or any combination thereof. Figure 2-Figure 3As described, global data source(s) 120 may include an airport map database and an aircraft tracking data source, and usage metric generator 130A may process data from the airport map database and from the aircraft tracking data source to determine, for a particular airport in a particular time interval, a count of aircraft that have landed, a count of aircraft that have taken off, a count of taxi operations for arriving aircraft, a count of taxi operations for departing aircraft, a count of aircraft moving on the ground, a count of aircraft on approach that have not landed at the particular airport during the particular time interval, and a count of aircraft waiting at the particular airport during the particular time interval. Such historical usage metrics 132A may be generated for overlapping time intervals using a sliding window to improve the accuracy of congestion estimates, as described with reference to FIG. Figure 3 Further described.

[0033] The distribution model generator 140 is configured to process the historical usage metrics 132A to generate a distribution model 142 associated with the historical usage of a particular airport. The distribution model 142 corresponds to the kernel density estimator (KDE) model 141. Figure 5 As described in more detail, the probability density estimate associated with KDE model 141 approximates the distribution (e.g., histogram) of historical usage metrics 132A and enables determination of the current level of congestion at an airport relative to the airport's historical usage using relatively low-complexity statistical calculations. Furthermore, using KDE model 141 to estimate the current level of congestion consumes less processing resources, memory, and bandwidth than using the raw data of historical usage metrics 132A.

[0034] Although the above description of the operation of using the metric generator 130A and the distribution model generator 140 is for a single airport and a single time interval, it should be understood that the first subsystem 102 can process historical data corresponding to multiple time intervals and multiple airports to generate one or more sets of distribution models for each time interval for each airport. For illustration, in some implementations, the distribution model generator 140 is configured to generate, for each of the multiple airports, multiple distribution models 142 based on time of day and further based on weather conditions, as shown in FIG. Figure 5 Further described.

[0035] The second subsystem 104 is configured to determine an airport congestion level 162 associated with a particular airport based on the distribution model 142 for the particular airport and current data 144 corresponding to the current usage metric 132B for the particular airport. The second subsystem 104 includes a usage metric generator 130B, an airport congestion evaluator 160, and a congestion reliever 170.

[0036] Usage metrics generator 130B is configured to process current data 144 to obtain current usage metrics 132B. For example, as illustrative, non-limiting examples, current data 144 may include data related to aircraft positions and weather conditions at a particular airport within a recent time period (such as the previous hour, half an hour, or ten minutes), and usage metrics generator 130B may process current data 144 to generate current usage metrics 132B for the recent time period. Current usage metrics 132B include usage metrics corresponding to historical usage metrics 132A to enable comparison of current usage of the airport with historical usage of the airport. In the illustrative embodiment, current usage metrics 132B include one or more of taxi-in data, taxi-out data, departure data, arrival data, approach data, ground movement data, weather data, or aircraft holding data, as previously described with respect to historical usage metrics 132A.

[0037] Airport congestion evaluator 160 is configured to receive distribution model 142 and a current usage metric 132B for a particular airport and determine a degree of airport congestion 162 for the particular airport based on distribution model 142 and the current usage metric 132B. For example, in some implementations, distribution model 142 includes data describing a probability density function that indicates, for each value of a count of aircraft operations (e.g., the sum of aircraft arrivals and departures) during a particular time period, a relative probability associated with that count of aircraft operations based on historical counts of aircraft operations at the particular airport during the particular time period. Airport congestion evaluator 160 may generate a current count of aircraft operations based on current usage metric 132B and determine a percentile associated with the current count, for example, by calculating or approximating the integral of a probability distribution estimate over a range from zero to the current count. Airport congestion evaluator 160 may compare the determined percentile to one or more thresholds (e.g., a first threshold corresponding to the 95th percentile and / or a second threshold corresponding to the 99th percentile) to determine degree of airport congestion 162.

[0038] In other implementations, distribution model 142 does not include data describing a probability density function, but instead includes data mapping one or more operation counts to one or more congestion levels. For example, distribution model generator 140 may determine which operation counts correspond to the 95th percentile and the 99th percentile, and distribution model generator 142 may provide the determined counts as distribution model 142. To illustrate, distribution model 142 may indicate that a count of 52 operations corresponds to the 95th percentile and a count of 63 operations corresponds to the 99th percentile. In this implementation, airport congestion evaluator 160 compares the current count of operations with the values ​​indicated in distribution model 142 to determine airport congestion level 162.

[0039] The congestion reliever 170 is configured to selectively initiate the execution of a mitigation action based on the value of the airport congestion level 162. For example, in response to the airport congestion level 162 indicating that a threshold usage level has been exceeded, the congestion reliever 170 performs a mitigation action. To illustrate, the congestion reliever 170 may generate a congestion warning 172, generate a congestion alert 174, update one or more flight arrival or departure forecasts 176 at a particular airport based on congestion at the particular airport, reallocate one or more resources 178 at the particular airport, adjust a flight plan 180 of an aircraft en route to the particular airport to improve the aircraft's fuel efficiency, reroute an aircraft to avoid the airspace of the particular airport, or any combination thereof.

[0040] In an example, the congestion reliever 170 may generate a congestion warning 172 in response to the airport congestion level 162 exceeding a first threshold percentile of the distribution model 142. After the airport congestion level 162 has further increased to exceed a second threshold percentile of the distribution model 142 that is greater than the first threshold percentile, the congestion reliever 170 may generate a congestion alert 174. When the airport congestion level 162 drops below the second threshold percentile, the second subsystem 104 (e.g., the congestion reliever 170) may generate a notification that the airport congestion level 162 has dropped from an alert level to a warning level. When the airport congestion level 162 drops below the first threshold percentile, the second subsystem 104 (e.g., the congestion reliever 170) may generate a notification that the airport congestion level 162 is no longer at a warning level.

[0041] During operation, the first subsystem 102 may operate as a backend system configured to periodically (e.g., daily, weekly, or at some other interval) or occasionally update multiple distribution models (e.g., including distribution model 142) associated with each airport for which congestion monitoring is performed based on updated historical data. The first subsystem 102 may have relatively significant processing power compared to the second subsystem 104, which may operate as a client system, such as an electronic flight bag (EFP) that a pilot can access in the cockpit to receive real-time or near-real-time updates on estimated airport congestion. The first subsystem 102 generates an updated set of distribution models for various airports, time periods, and weather conditions, and may provide one or more distribution models 142 to the second subsystem 104. In some embodiments, one or more distribution models 142 are provided to the second subsystem 104 on a scheduled or on-demand basis. To illustrate, when an aircraft is scheduled to arrive at one or more specific airports within one or more specific time ranges, the distribution models 142 associated with the specific airports and time ranges may be provided to the second subsystem 104. In other embodiments, the entire set or a partial set of distribution models 142 may be provided to the second subsystem 104 , such as the entire set of distribution models 142 for all airports and all time periods being monitored for congestion.

[0042] The second subsystem 104 may periodically or occasionally access the global data source(s) 120 to generate real-time updates of airport congestion levels 162 for one or more destination airports associated with one or more scheduled flights. For example, the second subsystem 104 may be used by one or more airlines or one or more operations control centers (OCCs) to implement system-wide monitoring and congestion relief, by individual pilots to perform individual airport monitoring and congestion relief for individual flights entering or departing a particular airport, or any combination thereof.

[0043] In some embodiments, airport personnel and / or the air traffic management system may take proactive measures to reduce or mitigate potential congestion or the potential effects of congestion at the airport by issuing a congestion warning 172. As an example, additional personnel may be notified and deployed to the scene to help alleviate the congestion.

[0044] In some embodiments, by issuing a congestion alert 174, airport personnel and / or the air traffic management system can take remedial measures to reduce or alleviate the congestion at the airport. As an example, additional personnel can be deployed to the scene to help alleviate the congestion.

[0045] By performing mitigating actions including updating one or more flight arrival or departure forecasts (e.g., updating flight forecast 176), schedule adjustments can be made to reflect expected delays due to increased airport congestion, and the adjusted flight forecasts can be propagated to the schedules of arriving and departing flights at the airport to provide a highly accurate flight operating schedule for use by airport personnel, crews, and passengers.

[0046] By performing mitigation actions that include reallocating one or more resources at a particular airport (e.g., resource reallocation 178), resources such as gate assignments, flight crews, ground personnel, and other resources associated with aircraft turnarounds can be reallocated to reduce inefficiencies that are expected to occur due to delays caused by airport congestion. For example, when airport congestion is expected to delay the arrival of a particular aircraft (which in turn will result in an expected delay in the departure of the particular aircraft on a subsequent flight), resource allocation can include performing a tail swap in which a different aircraft is assigned to the subsequent flight to reduce or eliminate the triggered expected delay for the flight.

[0047] By performing mitigation actions, including adjusting the aircraft's flight plan for a particular airport (e.g., adjusting flight plan 180) to improve the aircraft's fuel efficiency, the aircraft's efficiency can be improved. For example, when estimated congestion at an arrival airport is expected to cause the aircraft to fly in a holding pattern upon arrival at the airport, the flight plan can be adjusted to reduce the aircraft's speed, which can improve the aircraft's fuel efficiency for the remainder of the flight and reduce the amount of time the aircraft is held compared to following the original flight plan.

[0048] While the first subsystem 102 and the second subsystem 104 can be implemented in separate devices, components associated with the first subsystem 102 and the second subsystem 104 can optionally be included in a single device. For example, the single device can include one or more processors that include (or are otherwise configured to perform operations associated with) a single usage metric generator 130 for generating historical usage metrics 132A and current usage metrics 132B, a distribution model generator 140, an airport congestion evaluator 160, and a congestion reliever 170. Alternatively, one or more of the components (such as the congestion reliever 170) can be implemented in another subsystem (such as a scheduling or resource management subsystem that communicates with the airport congestion evaluator 160 to receive an indication of the airport congestion level 162).

[0049] Although the usage metric generator 130A, the usage metric generator 130B, the distribution model generator 140, the airport congestion evaluator 160, and the congestion reliever 170 are shown as distinct components, alternatively, the functionality of two or more of the usage metric generator 130A, the usage metric generator 130B, the distribution model generator 140, the airport congestion evaluator 160, and the congestion reliever 170 may be combined into a single component.

[0050] While the above examples describe congested areas associated with thresholds corresponding to the 95th and 99th percentiles, such examples are provided for illustrative purposes and should not be considered limiting. For example, the first threshold may correspond to the 85th percentile, the 90th percentile, or any other percentile determined to be useful for warning of potential airport congestion. The second threshold may correspond to the 96th percentile, the 98th percentile, or any other percentile determined to be useful for warning of airport congestion. Alternatively, as another embodiment, a single threshold may be used, or three or more thresholds may be used, instead of the two thresholds in the above examples.

[0051] Figure 2 Is depicted can be included in Figure 1 1 is a diagram of an example of components 200 in system 100 , including global data source 120 and usage metric generator 130 .

[0052] Global data sources 120 include an airport map database 214, an aircraft tracking data source 216, and a weather data source 218. Airport map database 214 may include or correspond to one or more AMDBs 204, which store data associated with one or more airports being monitored for congestion by system 100. For illustration, AMDB 204 may include a dataset representing the spatial layout of an airport using features (e.g., runways, taxiways, parking stands) that can be described as points, lines, polygons, etc., as well as other information such as surface type. In an example, AMDB 204 includes data in a format consistent with a geographic information system (GIS).

[0053] Aircraft tracking data source 216 may include or correspond to a source or collection of position reports 206. For illustration, aircraft tracking data source 216 may include an internet-based service that provides real-time commercial aircraft flight tracking information, origin and destination, flight number, aircraft type, position, altitude, heading, and speed from one or more aggregated sources, such as a FLIGHTRADAR24-type service (FLIGHTRADAR24 is a trademark of Flightradar24 AB of Stockholm, Sweden).

[0054] Weather data source 218 may include or correspond to a set of current weather reports 208. For example, weather reports 208 may correspond to a weather terminal aviation routine weather report (METAR) type report from an airport, from a weather observation station, from one or more sources, or any combination thereof. Alternatively or additionally, weather reports 208 may correspond to a terminal airport forecast (TAF) type forecast report.

[0055] The usage metric generator 130 may correspond to Figure 1 a usage metric generator 130A of the first subsystem 102, Figure 1 The usage metric generator 130B of the second subsystem 104 or a combination thereof. The usage metric generator 130 outputs a set of usage metrics 132, such as Figure 1 The historical usage metrics 132A or the current usage metrics 132B.

[0056] The usage metrics generator 130 is configured to process data 224 from the airport map database 214, data 226 from the aircraft tracking data source 216, and data 228 from the weather data source 218 to generate usage metrics 132. For example, the usage metrics generator 130 is configured to determine, for a particular airport and for a particular time interval, a count of aircraft that have landed, a count of aircraft that have taken off, a count of taxi operations for arriving aircraft, a count of taxi operations for departing aircraft, a count of aircraft moving on the ground, a count of aircraft approaching, and a count of aircraft holding. In an embodiment, the usage metrics generator 130 is configured to determine weather conditions during a particular time interval at the particular airport. The usage metrics generator 130 includes a taxi engine 240, a ground movement engine 244, an approach engine 246, a holding engine 248, and a weather engine 250.

[0057] Taxi engine 240 is configured to process data 224 from airport map database 214 and data 226 from aircraft tracking data source 216 to generate a number of usage metrics 132, including taxi-in data 260, taxi-out data 262, departure data 264, and arrival data 266. For example, taxi engine 240 may compare the positions and travel paths of individual aircraft in the vicinity of a particular airport with the runways and taxiways of the particular airport, as indicated by the airport map in data 224 from airport map database 214, to identify when each individual aircraft landed, took off, taxied in (e.g., traveled from a landing runway to an arrival gate during the time interval), taxied out (e.g., traveled from a departure gate to a departure (takeoff) runway), and / or made other ground movements during a particular time period.

[0058] Taxi engine 240 can determine, for a specific time period, an average (e.g., mean) taxi-in time, an average taxi-out time, a count of aircraft that have landed, a count of aircraft that have taken off, a count of aircraft that have taxied in, a count of aircraft that have taxied out, and a total count of all aircraft taxiing or otherwise moving on the ground during the specific time period. The average taxi-in time (or count of aircraft that have taxied in) is output as taxi-in data 260, and the average taxi-out time (or count of aircraft that have taxied out) is output as taxi-out data 262. The count of aircraft that have taken off is output as departure data 264, and the count of aircraft that have landed is output as arrival data 266. Taxi engine 240 is also configured to provide taxi data 242 to ground movement engine 244.

[0059] Ground movement engine 244 is configured to process taxi data 242 to determine ground movement data 268 to be included in usage metrics 132. For example, taxi data 242 may include an indication of all aircraft movements detected in an airport map during a particular time interval. Based on taxi data 242, ground movement engine 244 calculates all aircraft movements detected moving and / or taxiing at a particular airport and outputs a total count of all aircraft participating in the ground movement as ground movement data 268.

[0060] Approach engine 246 is configured to process data 226 from aircraft tracking data source 216 to generate approach data 270 for inclusion in usage metrics 132. For example, approach engine 246 may determine a count of aircraft that have not landed during a particular time interval but are expected to land at a particular airport and are within a threshold distance (such as less than or equal to 100 nautical miles) from the particular airport.

[0061] The holding engine 248 is configured to process the data 226 from the aircraft tracking data source 216 to generate the aircraft holding data 272 to be included in the usage metrics 132. For example, the holding engine 248 may determine a count of aircraft that were in a holding mode at a particular airport during a particular time period and may output the count of aircraft that were in a holding mode as the aircraft holding data 272.

[0062] Weather engine 250 is configured to process data 228 from weather data source 218 to generate weather data 274 to be included in usage metrics 132. For example, weather engine 250 may decode and select fields from METAR and / or TAF reports for a particular airport and a particular time interval to gather information such as temperature, dew point, wind direction, wind speed, visibility, gusts, one or more other types of weather information, or a combination thereof. One or more weather categories may be determined from the weather information and output as weather data 274. In an illustrative, non-limiting implementation, weather data 274 includes an indication of a visibility category from the following categories: visual (e.g., visibility greater than 9,656 meters), marginal visual (e.g., visibility within a range of 4,828 to 9,656 meters), instrument (e.g., visibility within a range of 1,609 to 4,828 meters), and low instrument (e.g., visibility less than 1,609 meters).

[0063] Although the usage metrics generator 130 is illustrated as including the taxi engine 240, the ground movement engine 244, the approach engine 246, the hold engine 248, and the weather engine 250, the usage metrics generator 130 may optionally omit one or more of the taxi engine 240, the ground movement engine 244, the approach engine 246, the hold engine 248, and the weather engine 250. For example, the functionality associated with two or more of the taxi engine 240, the ground movement engine 244, the approach engine 246, the hold engine 248, or the weather engine 250 may be combined into a single component. In another embodiment, the usage metrics 132 may omit one or more values ​​of the data 260-274, and the components used to generate the data omitted from the usage metrics 132 may also be omitted from the usage metrics generator 130.

[0064] Figure 3 Describes the Figure 1 1. An embodiment of operation 300 performed by system 100 of FIG. Operation 300 includes using metric generator 130 to generate one or more counts of a transportation operation using a sliding window, the one or more counts may correspond to historical usage metrics 132A or current usage metrics 132B.

[0065] As shown, the usage metric generator 130 generates a first set of traffic counts 320 using a first sliding window (W1) 310, a second set of traffic counts 322 using a second sliding window (W2) 312, a third set of traffic counts 324 using a third sliding window (W3) 314, and a fourth set of traffic counts 326 using a fourth sliding window (W4) 316. Each of the sliding windows 310-316 is illustrated as spanning a respective 10-minute time interval along the timeline 302, and the sliding windows 310-316 partially overlap with each other.

[0066] For example, to determine a first set of traffic counts 320, usage metric generator 130 processes data 224 from airport map database 214 and data 226 from aircraft tracking data source 216 to determine, for a particular airport during a particular time interval 340, a count of aircraft that have landed (landing count 366), a count of aircraft that have taken off (takeoff count 364), a count of taxi operations for arriving aircraft (taxi-in count 360), a count of taxi operations for departing aircraft (taxi-out count 362), and a count of aircraft moving on the ground 368. Usage metric generator 130 also determines, based on data 226 from aircraft tracking data source 216, a count of approaching aircraft 370 that have not landed at the particular airport during the particular time interval 340 and a count of aircraft that are in a holding pattern 372 at the particular airport during the particular time interval 340. As shown, particular time interval 340 is a 10-minute interval from 12:00 to 12:10.

[0067] To determine the second set of traffic counts 322, the data 224 from the airport map database 214 and the data 226 from the aircraft tracking data source 216 are processed using the metric generator 130 to determine values ​​for the counts 360-372 for a second time interval associated with the second sliding window 312. The second time interval is a 10-minute interval from 12:05 to 12:15, which overlaps with the second half of the time interval 340. Similarly, the data 224, 226 are processed using the metric generator 130 to determine values ​​for the counts 360-372 for a third time interval associated with the third sliding window 314 (corresponding to a 10-minute interval from 12:10 to 12:20), and to determine values ​​for the counts 360-372 for a fourth time interval associated with the fourth sliding window 316 (corresponding to a 10-minute interval from 12:15 to 12:25).

[0068] One benefit provided by using overlapping sliding windows is the granularity of the start time (e.g. Figure 3 The 5 minute increments shown) can be smaller than the length of the sliding window (e.g., 10 minute time intervals). Reducing the granularity of the start time can provide enhanced accuracy of real-time congestion monitoring, while having a longer time interval can eliminate variability associated with a low number of events per time period.

[0069] although Figure 3 Each of the traffic counts 320-326 is depicted as being calculated for 10 minute intervals with 5 minute increments, but in other examples any other time interval length (e.g., 15 minutes, 30 minutes, 1 hour, etc.), any other starting increment (e.g., 10 minutes, 15 minutes, 20 minutes, etc.), or combinations thereof may be used.

[0070] The same sliding windows 310-316 can be used to generate both the historical usage metrics 132A and the current usage metrics 132B. However, alternatively, a different sliding window can be used to generate the historical usage metrics 132A than to generate the current usage metrics 132B. For example, a sliding window having a length of one hour can be used to generate the historical usage metrics 132A, while a sliding window having a length of 15 minutes can be used to generate the current usage metrics 132B. In such an embodiment, adjustments can be made due to differences in traffic counts detected in the historical usage metrics 132A, which use a longer time period, compared to traffic counts detected in the current usage metrics 132B, which use a shorter time period, such as by multiplying the current usage metrics 132B by a factor of 4 in this example.

[0071] although Figure 3 Four sliding windows 310-316 are depicted spanning the time period from 12:00 to 12:25, but it should be understood that this arrangement of overlapping sliding windows, and the corresponding generation of traffic counts associated with these sliding windows, can be extended to cover the entire 24 hour period.

[0072] While the use of sliding windows, as described above, can provide benefits in terms of enhanced accuracy due to relatively small increments and in terms of smoothing of traffic counts due to relatively large time intervals, in other implementations, traffic counts 320-326 can be generated based on non-overlapping time intervals associated with non-overlapping sliding windows. Such implementations can reduce the amount of computing resources and storage associated with the generation and storage of traffic counts compared to using overlapping windows.

[0073] Figure 4 Describes the Figure 1 system 100 (such as, for example, Figure 1 An example of operations 400 performed by the airport congestion evaluator 160 ).

[0074] exist Figure 4 , usage metrics 132 (e.g., current usage metrics 132B) are each categorized as arrival metrics 402, departure metrics 404, or both. Arrival metrics 402 include taxi-in data 260, arrival data 266, ground movement data 268, approach data 270, aircraft holding data 272, and weather data 274. Departure metrics 404 include taxi-out data 262, departure data 264, ground movement data 268, and weather data 274.

[0075] In some implementations, the arrival metrics 402 are used to determine an arrival congestion index 410, and the departure metrics 404 are used to determine a departure congestion index 420. For example, the arrival congestion index 410 can be determined by summing a count of aircraft taxiing in (from the taxi-in data 260), a count of aircraft landing (from the arrival data 266), a count of aircraft performing ground movement associated with traveling from the arrival runway to the arrival gate (from the ground movement data 268), a count of aircraft on approach (from the approach data 270), and a count of aircraft in a holding pattern (from the aircraft holding data 272) within a particular time period. The sum can be normalized (e.g., set to a value from 0 to 1) based on historical usage metrics 132A associated with the same time period, the same airport, and the same weather conditions indicated by the weather data 274 to generate the arrival congestion index 410.

[0076] Similarly, the departure congestion index 420 can be determined by summing a count of aircraft that taxied (from the taxi-out data 262), a count of aircraft that departed (from the departure data 264), and a count of aircraft that performed ground movement associated with traveling from the departure gate to the takeoff runway (from the arrival ground movement data 268) during a particular time period. This sum can be normalized (e.g., set to a value from 0 to 1) based on historical usage metrics 132A associated with the same time period, the same airport, and the same weather conditions indicated by the weather data 274 to generate the departure congestion index 420. The arrival congestion index 410 and the departure congestion index 420 can be processed to determine the airport congestion index 462, such as by subtracting the departure congestion index 420 from the arrival congestion index 410, determining a ratio of the arrival congestion index 410 to the departure congestion index 420 (e.g., dividing the arrival congestion index 410 by the departure congestion index 420), one or more other operations, or any combination thereof.

[0077] In other implementations, one or more of the arrival metric 402 and the departure metric 404 are used to determine the airport congestion index 462 without generating the arrival congestion index 410 and the departure congestion index 420. In a first embodiment, the arrival count indicated by the arrival data 266 and the departure count indicated by the departure data 264 can be added together to generate a total of arrivals and departures for a particular time period. The total of arrivals and departures can be used to determine the airport congestion index 462. In a second embodiment, the airport congestion index 462 can be determined based on the sum of the arrival count indicated by the arrival data 266 and the departure count indicated by the departure data 264, as well as one or more of the following: a count of taxiing aircraft as indicated by the taxi-in data 260, a count of taxiing aircraft as indicated by the taxi-out data 262, a count of aircraft moving on the ground as indicated by the ground movement data 268, a count of approaches as indicated by the approach data 270, or a count of aircraft in a holding mode as indicated by the aircraft holding data 272.

[0078] In the first and second embodiments described above, the usage metric 132 is used to generate a unidimensional value (i.e., a count), and the airport congestion evaluator 160 can determine the airport congestion index 462 by determining a percentile associated with the count based on a univariate probability density function corresponding to the distribution model 142 (such as the univariate KDE model 141). Alternatively, in a third embodiment, the usage metric 132 is used to generate a multidimensional value. For example, the first dimension may correspond to the sum of the arrival count indicated by the arrival data 266 and the departure count indicated by the departure data 264; the second dimension may correspond to the sum of the count of taxiing-in aircraft indicated by the taxi-in data 260, the count of taxiing-out aircraft indicated by the taxi-out data 262, the count of aircraft moving on the ground indicated by the ground movement data 268, and the count of aircraft undergoing ground operations indicated by the ground operations data 468; and the third dimension may correspond to the sum of the count of aircraft in approach or holding mode, as indicated by the approach data 270 and the aircraft holding data 272, respectively. The airport congestion evaluator 160 may determine the airport congestion index 462 by determining percentiles associated with the multidimensional values ​​according to a multivariate probability density function corresponding to the distribution model 142 , such as the multivariate KDE model 141 .

[0079] Figure 5 Describes the Figure 15. An embodiment 500 of probability distributions generated by the system 100 of FIG. 5. For example, the distribution model generator 140 may generate a plurality of distribution models 560 for each of a plurality of airports, including a plurality of distribution models 560A for airport "A," a plurality of distribution models 560B for airport "B," and a plurality of distribution models 560C for airport "C." The plurality of distribution models 560 are each based on a corresponding time 520 (e.g., a time of day). To illustrate, a first set of probability distributions 560A for airport A corresponds to a probability density function for each of a plurality of times 520 (e.g., 09:00 Coordinated Universal Time (UTC), 12:00 UTC, etc.). Each of the plurality of times 520 corresponds to a probability density function corresponding to Figure 3 The time interval associated with the corresponding sliding window of is used to determine the traffic count associated with the time interval. In the embodiment 500, a one-hour time interval is used and only 10 hourly distribution models are shown; however, it should be understood that other time intervals can be used in other examples, such as using Figure 3 A collection of distribution models are generated for 10-minute time intervals and 5-minute increments associated with the sliding windows 310-316, and a distribution model may be generated for each increment over the entire 24-hour period.

[0080] The first set of probability distributions 560A is further based on weather conditions 522. For illustration, five probability density functions are shown for 09:00 UTC and are labeled based on visibility conditions, including "all" (e.g., all visibility conditions combined), "visual," "marginal," "instrument," and "low." Visual, marginal, instrument, and low visibility conditions can correspond to the visibility categories previously described as included in weather data 274, such as visual (e.g., visibility greater than 9,656 meters), marginal visual (e.g., visibility within a range of 4,828 and 9,656 meters), instrument (e.g., visibility within a range of 1,609 and 4,828 meters), and low instrument (e.g., visibility less than 1,609 meters).

[0081] Example distribution 502 graphically illustrates a KDE model 560 (e.g., a probability density function) fitted to a histogram 504. Histogram 504 represents the distribution of historical counts of hourly operations occurring at Airport A during the previous day at an associated time 520 (e.g., 09:00 UTC) under all visibility conditions. In some implementations, KDE model 560 applies more weight to more recent historical data than to older historical data, modeling more recent hourly operation counts as more likely to occur than more recent hourly operation counts. The dashed vertical line represents a first KDE threshold percentile 508, such as the 95th percentile, and the solid vertical line represents a second KDE threshold percentile 510, such as the 99th percentile. The total count of hourly operations occurring at Airport A during the associated time 520 (e.g., 09:00 UTC) during the previous day under all visibility conditions, detected in the historical data and represented in histogram 504, is depicted as operation count 512. It should be understood that the embodiment distribution 502 is depicted in graphical form for purposes of explanation; in general, the probability distribution 560 may be stored as a data set, data structure, or other format for efficient computer-based access and processing, and need not be accessible in graphical form. However, in some implementations, such as Figure 1 A system such as system 100 may include or be coupled to a display device that provides a graphical indication of the current count of operations per hour and (e.g., overlaid on) a graphical representation of one or more of probability distributions 560 to provide visual information about the current amount of congestion at a particular airport in relation to historical distributions.

[0082] Figure 1 Airport congestion evaluator 160 can determine airport congestion level 162 by comparing the count of operations associated with current usage metric 132B to historical counts of hourly operations (horizontal axis values) associated with threshold percentiles 508 and 510. In embodiment 502, first threshold percentile 508 corresponds to 37 hourly operations, and second threshold percentile 510 corresponds to 54 hourly operations. In the context of embodiment 502, the "hourly operations" value represents the sum of arrivals and departures that occurred at the airport during the one-hour interval from 09:00 UTC to 10:00 UTC, and the height of each bar of histogram 504 indicates the number of times a particular number of hourly operations occurred in the historical data. However, in other embodiments, each "hourly operation" may instead represent the sum of one or more additional arrival and / or departure operations (e.g., arrivals, taxi-ins, approaches, holds, departures, taxi-outs, etc.) that occurred at the airport during the one-hour interval from 09:00 UTC to 10:00 UTC.

[0083] Figure 1 The airport congestion evaluator 160 can determine the airport congestion level 162 as a numerical value, such as a KDE percentile associated with the current count of operations per hour associated with the current usage metric. Alternatively or additionally, when the current count of operations per hour is to the left of the dashed line indicating the first threshold percentile 508 (e.g., less than 37 operations per hour), Figure 1 The airport congestion evaluator 160 may determine the airport congestion level 162 as a congestion category, such as “not congested,” when the current count of operations per hour is between the dashed line indicating the first threshold percentile 508 and the solid line indicating the second threshold percentile 510 (e.g., 37 to 53 operations per hour). Figure 1 The airport congestion evaluator 160 may determine the airport congestion level 162 as a “warning” category, or when the current count of operations per hour is to the right of the solid line indicating the second threshold percentile 510 (e.g., 53 or more operations per hour). Figure 1 The airport congestion evaluator 160 may determine the airport congestion level 162 as being in the “congested” category. The congestion mitigater 170 may generate a congestion warning 172 in response to the airport congestion level 162 exceeding the first threshold percentile 508 of the distribution model 142 and may generate a congestion alert 174 in response to the airport congestion level 162 exceeding the second threshold percentile 510 of the distribution model 142.

[0084] Although distribution model 560 is described as univariate (e.g., a single count of operations), it should be understood that in other examples, distribution model 560 can be multivariate (e.g., a multivariate KDE model) corresponding to a multidimensional histogram. In such an embodiment, instead of a curve representing an underlying one-dimensional histogram (e.g., histogram 504), each distribution model in distribution model 560 defines a surface that approximates the underlying multidimensional histogram.

[0085] Figure 6 is a flow chart illustrating a method 600 of monitoring airport congestion. In a specific implementation, the method 600 is performed by the usage metric generator(s) 130, the distribution model generator 140, the airport congestion evaluator 160, the congestion mitigater 170, or a combination thereof.

[0086] Method 600 includes, at block 602, obtaining, at one or more processors, historical data from one or more global data sources associated with aircraft traffic. The historical data corresponds to historical usage metrics for a particular airport. For example, usage metric generator 130A receives historical data 122 from global data source 120 and generates historical usage metrics 132A based on historical data 122. In an embodiment, the one or more global data sources include an airport map database, an aircraft tracking data source, and a weather data source, such as, respectively. Figure 2The airport map database 214, the aircraft tracking data source 216 and the weather data source 218 are provided.

[0087] The method 600 includes processing the historical usage metrics at one or more processors to generate a distribution model associated with usage of a particular airport at block 604. For example, the distribution model generator 140 processes the historical usage metrics 132A to generate the distribution model 142.

[0088] Method 600 includes obtaining, at one or more processors, data corresponding to a current usage metric for a particular airport from one or more global data sources at block 606. For example, usage metric generator 130B receives current data 144 from global data source 120 and processes current data 144 to generate current usage metric 132B.

[0089] The method 600 includes determining an airport congestion level for a particular airport based on the distribution model and the current usage metric for the particular airport at block 608. For example, the airport congestion evaluator 160 determines the airport congestion level 162 based on the distribution model 142 and the current usage metric 132B.

[0090] The method 600 optionally includes one or more actions that may be performed by the congestion reliever 170 in response to the airport congestion level 162 corresponding to a KDE percentile exceeding a threshold percentile of congestion conditions, such as a reference Figure 5 For illustration, method 600 optionally includes generating an alert at block 610, such as Figure 1 Congestion alert 174; At block 612, reallocate one or more resources at a particular airport, such as Figure 1 At block 614, one or more flight arrival or departure forecasts (such as Figure 1 and / or adjusting the aircraft's flight plan to a particular airport at block 616 to improve the aircraft's fuel efficiency, such as Figure 1 Adjustment of flight plan 180.

[0091] Method 600 thus enables the use of globally available public data to determine the amount of congestion at a particular airport. Thus, as an illustrative, non-limiting example, method 600 enables mitigation actions to be taken to reduce the impact of congestion at individual airports, individual flights, fleets of aircraft operated by one or more airlines, or air traffic management systems.

[0092] Figure 7is a block diagram of a computing environment 700 including a computing device 710 configured to support various aspects of computer-implemented methods and computer-executable program instructions (or code) according to the present disclosure. For example, the computing device 710 or a portion thereof is configured to execute instructions to initiate, execute, or control a reference Figures 1-6 In some implementations, the computing device 710 corresponds to the first subsystem 102 , the second subsystem 104 , or a combination of the first subsystem 102 and the second subsystem 104 .

[0093] Computing device 710 includes one or more processors 720. Processor(s) 720 are configured to communicate with system memory 730, one or more storage devices 750, one or more input / output interfaces 740, one or more communication interfaces 760, or any combination thereof. System memory 730 includes volatile memory devices (e.g., random access memory (RAM) devices), non-volatile memory devices (e.g., read-only memory (ROM) devices, programmable read-only memory, and flash memory), or both. System memory 730 stores an operating system 732, which may include a basic input / output system for booting computing device 710 and a complete operating system that enables computing device 710 to interact with users, other programs, and other devices. System memory 730 also stores system (program) data 738, such as global data 790 from global data source(s) 120 (e.g., historical data 122 and / or current data 144), usage metrics 132, one or more distribution models 792 (e.g., distribution model 142 and / or distribution model 560), airport congestion levels 162, or any combination thereof.

[0094] System memory 730 includes one or more applications 734 (eg, instruction sets) that can be executed by one or more processors 720. As an example, one or more applications 734 include instructions that can be executed by one or more processors 720 to initiate, control, or execute a reference program. Figures 1-6 For illustration, the one or more applications 734 include instructions executable by the one or more processors 720 to initiate, control, or perform one or more operations described with reference to the usage metric generator 130, the distribution model generator 140, the airport congestion evaluator 160, the congestion mitigater 170, or a combination thereof.

[0095] The system memory 730 includes a non-transitory computer-readable medium storing instructions that, when executed by the one or more processors 720, cause the one or more processors 720 to obtain historical data corresponding to historical usage metrics for a particular airport from one or more global data sources associated with aircraft traffic; process the historical usage metrics to generate a distribution model associated with usage of the particular airport; obtain data corresponding to current usage metrics for the particular airport from the one or more global data sources, and determine a level of airport congestion for the particular airport based on the distribution model and the current usage metrics for the particular airport.

[0096] One or more storage devices 750 include non-volatile storage devices, such as magnetic disks, optical disks, or flash memory devices. In particular embodiments, storage devices 750 include both removable and non-removable storage devices. Storage devices 750 are configured to store an operating system, operating system images, applications (e.g., one or more of applications 734), and program data (e.g., program data 738). In certain aspects, system memory 730, storage devices 750, or both comprise tangible computer-readable media. In certain aspects, one or more of storage devices 750 are external to computing device 710.

[0097] One or more input / output interfaces 740 enable computing device 710 to communicate with one or more input / output devices 770 to facilitate user interaction. For example, one or more input / output interfaces 740 may include a display interface, an input interface, or both. For example, input / output interface 740 may be adapted to receive input from a user, receive input from another computing device, or a combination thereof. Input / output interface 740 may conform to one or more standard interface protocols, including a serial interface (e.g., a Universal Serial Bus (USB) interface or an Institute of Electrical and Electronics Engineers (IEEE) interface standard), a parallel interface, a display adapter, an audio adapter, or a custom interface ("IEEE" is a registered trademark of the Institute of Electrical and Electronics Engineers, Piscataway, New Jersey). Input / output devices 770 may include one or more user interface devices and displays, including some combination of buttons, keyboards, pointing devices, displays, speakers, microphones, touch screens, and other devices.

[0098] The one or more processors 720 are configured to communicate with one or more devices (or controllers) 780 via one or more communication interfaces 760. For example, the one or more communication interfaces 760 may include a network interface. The one or more devices 780 may include, for example, a global data source 120, such as Figure 2The airport map database 214, the aircraft tracking data source 216, and the weather data source 218 are provided. In an embodiment, the application 734 may include one of the first subsystem 102 or the second subsystem 104, and the one or more devices 780 may include the other of the first subsystem 102 or the second subsystem 104. In an embodiment, the application 734 may include one of the airport congestion evaluator 160 and the congestion reliever 170, and the one or more devices 780 may include the other of the airport congestion evaluator 160 and the congestion reliever 170.

[0099] In conjunction with the described systems and methods, an apparatus is disclosed that includes means for obtaining historical data from one or more global data sources associated with aircraft traffic, the historical data corresponding to historical usage metrics for a particular airport. The means for obtaining historical data from one or more global data sources corresponds to the system 100, the first subsystem 102, the usage metric generator 130A, the device 710, the input / output device 770, the processor(s) 720, one or more other circuits or devices configured to obtain historical data from one or more global data sources, or a combination thereof.

[0100] The apparatus includes means for processing historical usage metrics to generate a distribution model associated with usage of a particular airport. The means for processing historical usage metrics to generate a distribution model associated with usage of a particular airport corresponds to the system 100, the first subsystem 102, the distribution model generator 140, the means 710, the processor(s) 720, one or more other circuits or means configured to process historical usage metrics to generate a distribution model associated with usage of a particular airport, or a combination thereof.

[0101] The apparatus includes means for obtaining data corresponding to current usage metrics for a particular airport from one or more global data sources. The means for obtaining data corresponding to current usage metrics corresponds to the system 100, the second subsystem 104, the usage metrics generator 130B, the means 710, the processor(s) 720, one or more other circuits or means configured to obtain data corresponding to current usage metrics for a particular airport from one or more global data sources, or a combination thereof.

[0102] The apparatus further includes means for determining a degree of airport congestion for the particular airport based on the distribution model and the current usage metric for the particular airport. The means for determining a degree of airport congestion for the particular airport based on the distribution model and the current usage metric for the particular airport corresponds to the system 100, the second subsystem 104, the airport congestion evaluator 160, the means 710, the processor(s) 720, one or more other circuits or means configured to determine a degree of airport congestion for the particular airport based on the distribution model and the current usage metric for the particular airport, or a combination thereof.

[0103] The non-transitory computer readable medium may store instructions that, when executed by one or more processors, cause the one or more processors to initiate, execute, or control operations to perform some or all of the above functions. For example, the instructions may be executable to implement Figure 1-Figure 7 One or more of the operations or methods. Figure 1-Figure 7 Part or all of one or more of the operations or methods may be implemented by one or more processors (e.g., one or more central processing units (CPUs), one or more graphics processing units (GPUs), one or more neural processing units (NPUs), one or more digital signal processors (DSPs)) that execute instructions, by dedicated hardware circuits, or any combination thereof.

[0104] Certain aspects of the present disclosure are described in the following first set of interrelated embodiments:

[0105] According to embodiment 1, an apparatus includes one or more processors configured to: obtain historical data corresponding to historical usage metrics of a particular airport from one or more global data sources associated with aircraft traffic; process the historical usage metrics to generate a distribution model associated with usage of the particular airport; obtain data corresponding to current usage metrics of the particular airport from one or more global data sources; and determine a level of airport congestion for the particular airport based on the distribution model and the current usage metrics of the particular airport.

[0106] Embodiment 2 includes the apparatus of embodiment 1, wherein the distribution model corresponds to a kernel density estimator (KDE) model.

[0107] Embodiment 3 includes the apparatus of embodiment 1 or embodiment 2, wherein the one or more global data sources include an airport map database, an aircraft tracking data source, and a weather data source.

[0108] Embodiment 4 includes the apparatus of any one of embodiments 1 to 3, wherein the historical usage metrics include one or more of taxi-in data, taxi-out data, departure data, arrival data, approach data, ground movement data, weather data, or aircraft hold data.

[0109] Embodiment 5 includes the apparatus of any one of embodiments 1 to 4, wherein the data corresponding to the current usage metric comprises one or more of: taxi-in data, taxi-out data, departure data, arrival data, approach data, ground movement data, weather data, or aircraft holding data.

[0110] Embodiment 6 includes the apparatus of any one of embodiments 1 to 5, wherein the one or more processors are configured to process data from an airport map database and data from an aircraft tracking data source in one or more global data sources to determine, for a particular airport and at a particular time interval, a count of aircraft that have landed, a count of aircraft that have taken off, a count of taxi operations for arriving aircraft, a count of taxi operations for departing aircraft, and a count of aircraft moving on the ground.

[0111] Embodiment 7 includes the apparatus of embodiment 6, wherein the one or more processors are further configured to determine a count of approaching aircraft that have not landed during a particular time interval at a particular airport based on data from an aircraft tracking data source.

[0112] Embodiment 8 includes the apparatus of embodiment 6 or embodiment 7, wherein the one or more processors are further configured to determine a count of aircraft in a holding mode at a particular airport during a particular time interval based on data from an aircraft tracking data source.

[0113] Embodiment 9 includes the apparatus of any one of embodiments 1 to 8, wherein one or more of the historical usage metric or the current usage metric is generated using a sliding window.

[0114] Embodiment 10 includes the apparatus of any one of embodiments 1 to 9, wherein the one or more processors are further configured to: process the current usage metric to generate a current arrival congestion index and a current departure congestion index; and determine the airport congestion level based on the current arrival congestion index, the current departure congestion index, and the allocation model.

[0115] Embodiment 11 includes the apparatus of any of embodiments 1-10, wherein the one or more processors are configured to generate a plurality of distribution models based on time of day for each of the plurality of airports.

[0116] Example 12 includes the apparatus of Example 11, wherein the plurality of distribution models are further based on weather conditions.

[0117] Embodiment 13 includes the apparatus of embodiment 11 or embodiment 12, wherein the one or more processors are configured to periodically update the plurality of distribution models based on updated historical data.

[0118] Embodiment 14 includes the apparatus of any one of embodiments 1 to 13, wherein the one or more processors are further configured to perform a mitigation action in response to the airport congestion level exceeding a threshold percentile of the distribution model, the mitigation action comprising one or more of: generating an alert; updating one or more flight arrival or departure forecasts at a particular airport based on the congestion at the particular airport; or reallocating one or more resources at the particular airport.

[0119] Embodiment 15 includes the apparatus of any one of embodiments 1 to 14, wherein the one or more processors are further configured to adjust a flight plan of an aircraft to a particular airport in response to the airport congestion level exceeding a threshold percentile of the distribution model to improve the fuel efficiency of the aircraft.

[0120] Embodiment 16 includes the apparatus of any one of embodiments 1 to 15, wherein the one or more processors are configured to: generate a congestion warning in response to the airport congestion level exceeding a first threshold percentile of the distribution model; and generate a congestion alert in response to the airport congestion level exceeding a second threshold percentile of the distribution model, wherein the second threshold percentile is greater than the first threshold percentile.

[0121] In embodiment 17, a method includes: obtaining, at one or more processors, historical data from one or more global data sources associated with aircraft traffic, the historical data corresponding to historical usage metrics for a particular airport; processing, at one or more processors, the historical usage metrics to generate a distribution model associated with usage of the particular airport; obtaining, at one or more processors, data corresponding to current usage metrics for the particular airport from one or more global data sources; and determining a level of airport congestion for the particular airport based on the distribution model and the current usage metrics for the particular airport.

[0122] Embodiment 18 includes the method of embodiment 17, wherein the one or more global data sources include an airport map database, an aircraft tracking data source, and a weather data source.

[0123] Example 19 includes the method of Example 17 or Example 18, further comprising performing one or more of the following in response to the airport congestion level exceeding a threshold percentile of the distribution model: generating an alert; updating one or more flight arrival or departure forecasts at the particular airport based on the congestion at the particular airport; reallocating one or more resources at the particular airport; or adjusting the flight plan of an aircraft en route to the particular airport to improve the fuel efficiency of the aircraft.

[0124] Embodiment 20 includes the method of any one of Embodiments 17 to 19, wherein the distribution model corresponds to a kernel density estimator (KDE) model.

[0125] Embodiment 21 includes the method of any one of Embodiments 17 to 20, wherein the one or more global data sources include an airport map database, an aircraft tracking data source, and a weather data source.

[0126] Embodiment 22 includes the method of any one of embodiments 17 to 21, wherein the historical usage metrics include one or more of taxi-in data, taxi-out data, departure data, arrival data, approach data, ground movement data, weather data, or aircraft hold data.

[0127] Embodiment 23 includes the method of any one of embodiments 17 to 22, wherein the data corresponding to the current usage metric includes one or more of: taxi-in data, taxi-out data, departure data, arrival data, approach data, ground movement data, weather data, or aircraft holding data.

[0128] Embodiment 24 includes the method of any one of embodiments 17 to 23, further comprising: processing data from an airport map database and data from an aircraft tracking data source in one or more global data sources to determine, for a particular airport at a particular time interval, a count of aircraft that have landed, a count of aircraft that have taken off, a count of taxi operations for arriving aircraft, a count of taxi operations for departing aircraft, and a count of aircraft moving on the ground.

[0129] Embodiment 25 includes the method of embodiment 24, further comprising determining a count of approaching aircraft that have not landed during a particular time interval at a particular airport based on data from an aircraft tracking data source.

[0130] Embodiment 26 includes the method of embodiment 24 or embodiment 25, further comprising determining a count of aircraft in a holding pattern during a particular time interval at a particular airport based on data from an aircraft tracking data source.

[0131] Embodiment 27 includes the method of any one of embodiments 17 to 26, wherein one or more of the historical usage metrics and the current usage metrics are generated using a sliding window.

[0132] Embodiment 28 includes the method of any one of embodiments 17 to 27, further comprising: processing the current usage metric to generate a current arrival congestion index and a current departure congestion index; and determining the airport congestion level based on the current arrival congestion index, the current departure congestion index, and the allocation model.

[0133] Embodiment 29 includes the method of any one of embodiments 17 to 28, wherein a plurality of distribution models based on time of day are generated for each of the plurality of airports.

[0134] Example 30 includes the method of Example 29, wherein the plurality of distribution models are further based on weather conditions.

[0135] Example 31 includes the method of Example 29 or Example 30, further comprising periodically updating the plurality of distribution models based on updated historical data.

[0136] Embodiment 32 includes the method of any one of embodiments 17 to 31, further comprising: in response to the airport congestion level exceeding a threshold percentile of the distribution model, performing a mitigation action, the mitigation action comprising one or more of: generating an alert; updating one or more flight arrival or departure forecasts at a particular airport based on the congestion at the particular airport; or reallocating one or more resources at the particular airport.

[0137] Embodiment 33 includes the method of any one of embodiments 17 to 32, further comprising: in response to the airport congestion level exceeding a threshold percentile of the distribution model, adjusting a flight plan of an aircraft en route to a particular airport to improve fuel efficiency of the aircraft.

[0138] Embodiment 34 includes the method of any one of embodiments 17 to 33, further comprising: generating a congestion warning in response to the airport congestion level exceeding a first threshold percentile of the distribution model; and generating a congestion alert in response to the airport congestion level exceeding a second threshold percentile of the distribution model, wherein the second threshold percentile is greater than the first threshold percentile.

[0139] Embodiment 35, a non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to: obtain historical data corresponding to historical usage metrics of a particular airport from one or more global data sources associated with aircraft traffic; process the historical usage metrics to generate a distribution model associated with usage of the particular airport; obtain data corresponding to current usage metrics of the particular airport from one or more global data sources; and determine a level of airport congestion for the particular airport based on the distribution model and the current usage metrics of the particular airport.

[0140] Embodiment 36 includes the non-transitory computer-readable medium of embodiment 35, wherein the one or more global data sources include an airport map database, an aircraft tracking data source, and a weather data source.

[0141] Embodiment 37 includes the non-transitory computer-readable medium of embodiment 35 or embodiment 36, wherein the instructions further cause one or more processors to perform one or more of the following in response to the airport congestion level exceeding a threshold percentile of the distribution model: generate an alert; update one or more flight arrival or departure forecasts at a particular airport based on the congestion at the particular airport; reallocate one or more resources at the particular airport; or adjust a flight plan of an aircraft en route to the particular airport to improve the fuel efficiency of the aircraft.

[0142] Embodiment 38 includes the non-transitory computer readable medium of any one of Embodiments 35 to 37, wherein the distribution model corresponds to a kernel density estimator (KDE) model.

[0143] Embodiment 39 includes the non-transitory computer-readable medium of any one of embodiments 35 to 38, wherein the one or more global data sources include an airport map database, an aircraft tracking data source, and a weather data source.

[0144] Embodiment 40 includes the non-transitory computer-readable medium of any one of embodiments 35 to 39, wherein the historical usage metrics include one or more of taxi-in data, taxi-out data, departure data, arrival data, approach data, ground movement data, weather data, or aircraft holding data.

[0145] Embodiment 41 includes the non-transitory computer-readable medium of any one of embodiments 35 to 40, wherein the data corresponding to the current usage metric includes one or more of the following: taxi-in data, taxi-out data, departure data, arrival data, approach data, ground movement data, weather data, or aircraft holding data.

[0146] Embodiment 42 includes the non-transitory computer-readable medium of any one of embodiments 35 to 41, wherein the instructions further cause the one or more processors to process data from an airport map database and data from an aircraft tracking data source in one or more global data sources to determine, for a particular airport and at a particular time interval, a count of aircraft that have landed, a count of aircraft that have taken off, a count of taxi operations for arriving aircraft, a count of taxi operations for departing aircraft, and a count of aircraft moving on the ground.

[0147] Embodiment 43 includes the non-transitory computer-readable medium of embodiment 42, wherein the instructions further cause the one or more processors to determine a count of approaching aircraft that have not landed during a particular time interval at a particular airport based on data from an aircraft tracking data source.

[0148] Embodiment 44 includes the non-transitory computer-readable medium of embodiment 42 or embodiment 43, wherein the instructions further cause the one or more processors to determine a count of aircraft in a holding mode during a particular time interval at a particular airport based on data from an aircraft tracking data source.

[0149] Embodiment 45 includes the non-transitory computer-readable medium of any one of embodiments 35 to 44, wherein one or more of the historical usage metric and the current usage metric are generated using a sliding window.

[0150] Embodiment 46 includes the non-transitory computer-readable medium of any one of embodiments 35 to 45, wherein the instructions further cause the one or more processors to: process the current usage metric to generate a current arrival congestion index and a current departure congestion index; and determine a level of airport congestion based on the current arrival congestion index, the current departure congestion index, and the allocation model.

[0151] Embodiment 47 includes the non-transitory computer-readable medium of any one of embodiments 35 to 46, wherein a plurality of distribution models based on time of day are generated for each of the plurality of airports.

[0152] Embodiment 48 includes the non-transitory computer-readable medium of embodiment 47, wherein the plurality of distribution models are further based on weather conditions.

[0153] Embodiment 49 includes the non-transitory computer-readable medium of embodiment 47 or embodiment 48, wherein the instructions further cause the one or more processors to periodically update the plurality of distribution models based on updated historical data.

[0154] Embodiment 50 includes the non-transitory computer-readable medium of any one of embodiments 35 to 49, wherein the instructions further cause the one or more processors to perform a mitigation action in response to the airport congestion level exceeding a threshold percentile of the distribution model, the mitigation action comprising one or more of: generating an alert; updating one or more flight arrival or departure forecasts at the particular airport based on the congestion at the particular airport; or reallocating one or more resources at the particular airport.

[0155] Embodiment 51 includes the non-transitory computer-readable medium of any one of embodiments 35 to 50, wherein the instructions further cause the one or more processors to adjust a flight plan of an aircraft en route to a particular airport to improve fuel efficiency of the aircraft in response to the airport congestion level exceeding a threshold percentile of a distribution model.

[0156] Embodiment 52 includes the non-transitory computer-readable medium of any one of embodiments 35 to 51, wherein the instructions further cause one or more processors to: generate a congestion warning in response to the airport congestion level exceeding a first threshold percentile of the distribution model; and generate a congestion alert in response to the airport congestion level exceeding a second threshold percentile of the distribution model, wherein the second threshold percentile is greater than the first threshold percentile.

[0157] Embodiment 53, a device comprises: a device for obtaining historical data from one or more global data sources associated with aircraft traffic, the historical data corresponding to historical usage metrics of a particular airport; a device for processing these historical usage metrics to generate a distribution model associated with usage of the particular airport; a device for obtaining data corresponding to current usage metrics of the particular airport from one or more global data sources; and a device for determining a level of airport congestion for the particular airport based on the distribution model and the current usage metrics of the particular airport.

[0158] Embodiment 54 includes the apparatus of embodiment 53, wherein the one or more global data sources include an airport map database, an aircraft tracking data source, and a weather data source.

[0159] Embodiment 55 includes the apparatus of embodiment 53 or embodiment 54, wherein the distribution model corresponds to a kernel density estimator (KDE) model.

[0160] Embodiment 56 includes the apparatus of any one of embodiments 53 to 55, wherein the one or more global data sources include an airport map database, an aircraft tracking data source, and a weather data source.

[0161] Embodiment 57 includes the apparatus of any one of embodiments 53 to 56, wherein the historical usage metrics include one or more of taxi-in data, taxi-out data, departure data, arrival data, approach data, ground movement data, weather data, or aircraft hold data.

[0162] Embodiment 58 includes the apparatus of any one of embodiments 53 to 57, wherein the data corresponding to the current usage metric comprises one or more of taxi-in data, taxi-out data, departure data, arrival data, approach data, ground movement data, weather data, or aircraft holding data.

[0163] Embodiment 59 includes the apparatus of any one of embodiments 53 to 58, wherein one or more of the historical usage metrics and the current usage metrics are generated using a sliding window.

[0164] Embodiment 60 includes the apparatus of any one of embodiments 53 to 59, wherein a plurality of distribution models based on time of day are generated for each of the plurality of airports.

[0165] Example 61 includes the apparatus of Example 60, wherein the plurality of distribution models are further based on weather conditions.

[0166] The illustrations of the embodiments described herein are intended to provide an overall understanding of the structures of different implementations. These illustrations are not intended to serve as a complete description of all elements and features of the devices and systems utilizing the structures or methods described herein. After reviewing the present invention, many other implementations may be apparent to those skilled in the art. Other implementations may be utilized and derived from this disclosure so that structural and logical replacements and changes can be made without departing from the scope of this disclosure. For example, method operations may be performed in an order different from the order shown in the figures or one or more method operations may be omitted. Therefore, this disclosure and the accompanying drawings are considered to be illustrative and not restrictive.

[0167] In addition, although specific embodiments have been shown and described herein, it should be understood that any subsequent arrangement designed to achieve the same or similar results may replace the specific implementations shown. This disclosure is intended to cover any and all subsequent adaptations or variations of different implementations. Combinations of the above implementations, as well as other implementations not specifically described herein, will be apparent to those skilled in the art after reading this description.

[0168] The abstract of the present disclosure is submitted with the understanding that it is not used to interpret or limit the scope or meaning of the claims. In addition, in the foregoing detailed description, different features may be combined together or described in a single implementation for the purpose of streamlining the present disclosure. The above embodiments illustrate but do not limit the present disclosure. It should also be understood that many modifications and variations are possible in accordance with the principles of the present disclosure. As reflected in the following claims, the claimed subject matter may involve fewer features than all the features of any disclosed embodiment. Therefore, the scope of the present disclosure is defined by the appended claims and their equivalents.

Claims

1. A device (710) for monitoring airport congestion, comprising: One or more processors (720) configured to: Obtaining historical data (122) corresponding to a historical usage metric (132A) for a particular airport from one or more global data sources (120) associated with aircraft traffic; processing the historical usage metrics to generate a distribution model associated with usage of the particular airport (142); obtaining data (144) corresponding to a current usage metric (132B) for the particular airport from the one or more global data sources; and An airport congestion level for the particular airport is determined based on the distribution model and the current usage metric for the particular airport (162).

2. The device according to claim 1, wherein: The distribution model corresponds to the kernel density estimator (KDE) model (141).

3. The device according to claim 1, wherein: The one or more global data sources include an airport map database (214), an aircraft tracking data source (216), and a weather data source (218).

4. The device according to claim 1, wherein: The historical usage metrics include one or more of: taxi-in data (260), taxi-out data (262), departure data (264), arrival data (266), approach data (270), ground movement data (268), weather data (274), or aircraft hold data (272).

5. The device according to claim 1, wherein: The data corresponding to the current usage metric includes one or more of taxi-in data, taxi-out data, departure data, arrival data, approach data, ground movement data, weather data, or aircraft holding data.

6. The device according to claim 1, wherein: The one or more processors are configured to process data (224) from an airport map database (214) and data (226) from an aircraft tracking data source (216) of the one or more global data sources to determine, for a particular time interval (340) at the particular airport, a count of aircraft that have landed (366), a count of aircraft that have taken off (364), a count of taxi operations (360) for arriving aircraft, a count of taxi operations (362) for departing aircraft, and a count of aircraft moving on the ground (368).

7. The device according to claim 6, wherein: The one or more processors are further configured to determine a count of approaching aircraft that have not landed during the particular time interval at the particular airport based on the data from the aircraft tracking data source (370).

8. The device according to claim 6, wherein: The one or more processors are further configured to determine a count of aircraft that were in a holding mode at the particular airport during the particular time interval based on the data from the aircraft tracking data source ( 372 ).

9. The device according to claim 1, wherein: One or more of the historical usage metric and the current usage metric are generated using a sliding window (310).

10. The device according to claim 1, wherein: The one or more processors are further configured to: processing the current usage metric to generate a current arrival congestion index (410) and a current departure congestion index (420); and The airport congestion level is determined based on the current arrival congestion index, the current departure congestion index, and the distribution model.

11. The device according to claim 1, wherein: The one or more processors are configured to generate a plurality of distribution models (560) based on time of day (510) for each of a plurality of airports.

12. The device according to claim 11, wherein The plurality of distribution models are also based on weather conditions (522).

13. The device according to claim 11, wherein: The one or more processors are configured to periodically update the plurality of distribution models based on updated historical data.

14. The device according to claim 1, wherein: The one or more processors are further configured to perform a mitigation action in response to the airport congestion level exceeding a threshold percentile of the distribution model (510), the mitigation action comprising one or more of the following: GenerateAlert(174); updating one or more flight arrival or departure forecasts at the particular airport based on congestion at the particular airport (176); or One or more resources are reallocated at the particular airport (178).

15. The device according to claim 1, wherein: The one or more processors are further configured to, in response to the airport congestion level exceeding a threshold percentile of the distribution model, adjust a flight plan (180) of an aircraft en route to the particular airport to improve fuel efficiency of the aircraft.

16. The device according to claim 1, wherein The one or more processors are configured to: generating a congestion warning (172) in response to the airport congestion level exceeding a first threshold percentile (508) of the distribution model; and A congestion alert (174) is generated in response to the airport congestion level exceeding a second threshold percentile (510) of the distribution model, wherein the second threshold percentile is greater than the first threshold percentile.

17. A method (600) for airport congestion monitoring, comprising: obtaining ( 602 ), at one or more processors ( 720 ), historical data ( 122 ) from one or more global data sources ( 120 ) associated with aircraft traffic, the historical data corresponding to historical usage metrics ( 132A) for a particular airport; processing (604) the historical usage metrics at the one or more processors to generate a distribution model (142) associated with usage of the particular airport; obtaining (606) at the one or more processors from the one or more global data sources data (144) corresponding to a current usage metric (132B) for the particular airport; and An airport congestion level (162) for the particular airport is determined (608) based on the distribution model and the current usage metric for the particular airport.

18. The method according to claim 17, wherein: The one or more global data sources include an airport map database (214), an aircraft tracking data source (216), and a weather data source (218).

19. The method of claim 17, further comprising, in response to the airport congestion level exceeding a threshold percentile of the distribution model, performing one or more of the following: Generate (610) alert (174); updating (614) one or more flight arrival or departure forecasts (176) at the particular airport based on congestion at the particular airport; reallocating (612) one or more resources (178) at the particular airport; or A flight plan (180) of an aircraft en route to the particular airport is adjusted (616) to improve fuel efficiency of the aircraft.

20. A non-transitory computer readable medium (730) storing instructions (736) that, when executed by one or more processors (720), cause the one or more processors to: Obtaining historical data (122) corresponding to a historical usage metric (132A) for a particular airport from one or more global data sources (120) associated with aircraft traffic; processing the historical usage metrics to generate a distribution model associated with usage of the particular airport (142); obtaining data (144) corresponding to a current usage metric (132B) for the particular airport from the one or more global data sources; and An airport congestion level for the particular airport is determined based on the distribution model and the current usage metric for the particular airport (162).

Images