For the purposes of this paper, the National Airspace System (NAS) encompasses the operations of all aircraft which are subject to air traffic control procedures. The NAS is a highly complex dynamic system that is sensitive to aeronautical decision-making and risk management skills. In order to ensure a healthy system with safe flights a systematic approach to anomaly detection is very important when evaluating a given set of circumstances and for determination of the best possible course of action. Given the fact that the NAS is a vast and loosely integrated network of systems, it requires improved safety assurance capabilities to maintain an extremely low accident rate under increasingly dense operating conditions. Data mining based tools and techniques are required to support and aid operators’ (such as pilots, management, or policy makers) overall decision-making capacity. Within the NAS, the ability to analyze fleetwide aircraft data autonomously is still considered a significantly challenging task. For our purposes a fleet is defined as a group of aircraft sharing generally compatible parameter lists. Here, in this effort, we aim at developing a system level analysis scheme. In this paper we address the capability for detection of fleetwide anomalies as they occur, which itself is an important initiative toward the safety of the real-world flight operations. The flight data recorders archive millions of data points with valuable information on flights everyday. The operational parameters consist of both continuous and discrete (binary & categorical) data from several critical subsystems and numerous complex procedures. In this paper, we discuss a system level anomaly detection approach based on the theory of kernel learning to detect potential safety anomalies in a very large data base of commercial aircraft. We also demonstrate that the proposed approach uncovers some operationally significant events due to environmental, mechanical, and human factors issues in high dimensional, multivariate Flight Operations Quality Assurance (FOQA) data. We present the results of our detection algorithms on real FOQA data from a regional carrier.

This dataset gives information on the number of United States general aviation safety data. It gives information on the accident rates, seriously injured incidences, fatality rates and accidents with fatality rates on flight hours.

This statistic depicts the number aircraft accidents worldwide in 2020, broken down by the operator's region and the level of damage sustained to the aircraft. North America had the most aircraft accidents, with 11 resulting in substantial damage in that year.

Air travel fatalities have been recorded in each of the last 16 years, with a total of 176 deaths in 2021 due to air crashes. However, despite some pronounced year-to-year differences, the overall trend has been for a reduction in the number of fatalities – a trend confirmed when looking at a slightly longer or much longer time frame. Fatal airline accidents According to the Convention on International Civil Aviation, air traffic fatalities refer to an incident where a person is fatally injured due to an occurrence associated with the operation of the aircraft. This definition covers any time from when the first person starts boarding to when the final person disembarks the plane. Corporate jet and military transport accidents are generally excluded. Overall safety of air travel The overall trend downward in air travel fatalities is notable given that the volume of passenger air traffic has increased by more than 66 percent since 2004. Indeed, when considered in terms of the number of accidents per distance travelled, air travel is statistically the safest form of transport. For example, in both the United States and the United Kingdom, air travel is many thousands of times safer than the most dangerous form of travel – motorcycle riding.

A sampling of Flight Attendant reports involving aircraft cabin issues.

The worldwide civilian aviation system is one of the most complex dynamical systems created. Most modern commercial aircraft have onboard flight data recorders that record several hundred discrete and continuous parameters at approximately 1Hz for the entire duration of the flight. These data contain information about the flight control systems, actuators, engines, landing gear, avionics, and pilot commands. In this paper, recent advances in the development of a novel knowledge discovery process consisting of a suite of data mining techniques for identifying precursors to aviation safety incidents are discussed. The data mining techniques include scalable multiple-kernel learning for large-scale distributed anomaly detection. A novel multivariate time-series search algorithm is used to search for signatures of discovered anomalies on massive datasets. The process can identify operationally significant events due to environmental, mechanical, and human factors issues in the high-dimensional flight operations quality assurance data. All discovered anomalies are validated by a team of independent domain experts. This novel automated knowledge discovery process is aimed at complementing the state-of-the-art human-generated exceedance-based analysis that fails to discover previously unknown aviation safety incidents. In this paper, the discovery pipeline, the methods used, and some of the significant anomalies detected on real-world commercial aviation data are discussed.

More than one half of respondents in Russia considered it safe to fly with domestic airlines, according to a survey from January 2020. In contrast, about one third of Russians did not consider domestic airlines to be a safe mode of transport. Trust in the safety of foreign airlines was slightly lower among Russians.

In October 2022, 73 percent of respondent to a survey in the UK were confident in the safety of UK airlines and airports. This number remained stable compared to the previous year but but had dropped to 66 percent of adults who were confident in the safety of UK airlines and airports in November 2020 and 2021.

The statistics, which interpret and summarize the air occurrence data, are released monthly and then compiled as annual statistical summaries. Only five years is displayed.

A sampling of reports referencing Commuter and Corporate flight crew fatigue issues and duty periods.

As a result of the continued annual growth in global air traffic passenger demand, the number of airplanes that were involved in accidents is on the increase. Although the United States is ranked among the 20 countries with the highest quality of air infrastructure, the U.S. reports the highest number of civil airliner accidents worldwide. 2020 was the year with more plane crashes victims, despite fewer flights The number of people killed in accidents involving large commercial aircraft has risen globally in 2020, even though the number of commercial flights performed last year dropped by 57 percent to 16.4 million. More than half of the total number of deaths were recorded in January 2020, when an Ukrainian plane was shot down in Iranian airspace, a tragedy that killed 176 people. The second fatal incident took place in May, when a Pakistani airliner crashed, killing 97 people. Changes in aviation safety In terms of fatal accidents, it seems that aviation safety experienced some decline on a couple of parameters. For example, there were 0.37 jet hull losses per one million flights in 2016. In 2017, passenger flights recorded the safest year in world history, with only 0.11 jet hull losses per one million flights. In 2020, the region with the highest hull loss rate was the Commonwealth of Independent States. These figures do not take into account accidents involving military, training, private, cargo and helicopter flights.

A sampling of reports involving parachuting activity and conflicts with aircraft.

The FAA is reforming its aircraft certification processes and boosting oversight on Boeing to improve air safety, reflecting a shift in regulatory strategies and potentially affecting aviation trade.

A variety of reports from ATC Controllers.

General aviation fatalities include private aviation operations and excludes Federal Aviation Regulation (FAR) Part 121 (Air Carriers), 129 (Foreign), 135 (On-Demand), and Non-U.S./Commercial operations. The National Transportation Safety Board releases aviation fatality data in the Aviation Accident Database.

A sampling of reports from flight crew of rotary wing aircraft.

A sampling of reports involving air carrier (FAR 121) flight crew fatigue.

A sampling of aircraft icing encounter reports from GA and Commuter flight crews.

Data base of 207 accidents and incidents from Aviation Safety Network, based on the Flightcrew - Safety issue list, selecting only those from 2000 to 2016.