National Transportation Safety Board Research Articles

Aviation-BERT-NER: Named Entity Recognition for Aviation Safety Reports

This work introduces Aviation-BERT-NER, a Named Entity Recognition (NER) system tailored for aviation safety reports, building on the Aviation-BERT base model developed at the Georgia Institute of Technology’s Aerospace Systems Design Laboratory. This system integrates aviation domain-specific data, including aircraft types, manufacturers, quantities, and aviation terminology, to identify named entities critical for aviation safety analysis. A key innovation of Aviation-BERT-NER is its template-based approach to fine-tuning, which utilizes structured datasets to generate synthetic training data that mirror the complexity of real-world aviation safety reports. This method significantly improves the model’s generalizability and adaptability, enabling rapid updates and customization to meet evolving domain-specific requirements. The development process involved careful data preparation, including the synthesis of entity types and the generation of labeled datasets through template filling. Testing on real-world narratives from the National Transportation Safety Board (NTSB) database highlighted Aviation-BERT-NER’s robustness, with a precision of 95.34%, recall of 94.62%, and F1 score of 94.78% when evaluated over 50 manually annotated (BIO tagged) paragraphs. This work addresses a critical gap in English language NER models for aviation safety, promising substantial improvements in the analysis and understanding of aviation safety reports.

Toxic marriage – Boeing and McDonnell Douglas

Research methodology Public data such as news reports, interviews and memos were used to craft the case. In addition, the technical reports released by the National Transportation Safety Board (NTSB), along with secondary data in the form of expert accounts and congressional hearings were used to round out the synopsis of the case study. Case overview/synopsis This case explores the Boeing–McDonnell Douglas merger and its impact on Boeing’s corporate culture, ethics and strategic decision-making. After the merger, Boeing shifted from a culture focused on engineering excellence to one emphasizing cost-cutting and shareholder value. This cultural shift contributed to the development failures and ethical lapses that resulted in the 737 MAX crisis, which involved two fatal crashes. The case is designed for courses in Strategic Management or Organizational Behavior. Complexity academic level Strategic Management or Organizational Behavior

Cognitive Biases in Commercial Aviation: Empirical Review of Accident Reports

Cognitive biases in commercial aviation can coax pilots into disregarding established protocols or overlooking potential hazards, a concern that the Federal Aviation Administration (FAA) has acknowledged. However, the concrete impact of these biases on aviation operations has not been adequately quantified; empirical evidence remains limited. Recognizing this research gap, our study seeks to provide a comprehensive analysis of cognitive biases within commercial aviation. We conducted a review of National Transportation Safety Board flight incident reports for air carriers across the United States, from 2014 to 2024. We also conducted an expert interview with an instructor who is an experienced pilot to ascertain current training material and its adequacy in addressing cognitive biases. Our analysis revealed cognitive biases not identified by the FAA (e.g., overconfidence) and training material gaps. Our research lays the groundwork for improved training protocols and the potential for a more nuanced understanding of pilot behavior and safety.

Is Declined Cognitive Function Predictive for Fatal Accidents Involving Aging Pilots?

Background. Civil aviation comprises airlines/charters and general aviation (GA). Currently, airlines are experiencing a pilot shortage, partly reflecting scheduled retirements mandatory for airline (but not GA) pilots aged 65 years, fueling a debate as to whether the retirement age should be increased. Herein, using 16–40 years-of-age aviators as a reference, we determined whether GA pilots aged 60+ years (i) incurred an elevated accident rate, employing, for the first time, age-tiered flight time as a measure of risk exposure and (ii) carried an excess risk for cognitive deficiency-related fatal accidents. Methods. Airplane accidents (2002–2016) involving Class 3 medical certificated pilots were per the National Transportation Safety Board (NTSB) databases. Age-tiered pilot risk exposure represented a summation of flight hours per Class 3 medical applications. Cognitive decline measures were per NTSB field codes. Statistical analyses employed Chi-Square, Mann–Whitney, logistic regression, and binomial tests. Results. Using flight hours as the denominator, the fatal accident rate for older pilots (41–80 years) was unchanged compared with aviators aged 16–40 years. In the logistic regression, no cognitive deficiency measure was predictive (p = 0.11, p = 0.15) for pilots aged 61+ years who were involved in fatal accidents. Conclusion. These findings question the necessity of an automatic disqualification of air transport pilots at 65 years of age.

Analysis of Helicopter Air Ambulance Accidents in the United States From 2010 to 2021

ObjectiveHelicopter air ambulance (HAA) services are essential to air medical transport in the United States. However, HAA accidents, incidents, and fatalities have been a reason for concern for HAA operations. This article analyzes the numbers, proportions, contributing or causal factors, and defining events of HAA accidents in the United States from 2010 to 2021. MethodsThe National Transportation Safety Board final investigation reports, defining events, findings, and summary data were analyzed for 83 HAA accidents in the United States from 2010 to 2021. The 2 proportions test was used to compare the proportions of fatal HAA accidents between 2010-2015 and 2016-2021. ResultsThe data show that 21/47 (45%) of HAA accidents in 2010-2015 and 6/36 (17%) in 2016-2021 were fatal, representing a significant (P < .01) reduction in the proportion of fatal accidents in 2016-2021 from 2010-2015 time period. VFR encounter IMC events accounted for 9/47 (19%) of HAA accidents in 2010-2015 and 1/36 (3%) accident in 2016-2021, representing a significant (P < .05) reduction in VFR encounter IMC accidents. ConclusionThere was a statistically significant decrease in the proportion of fatal HAA accidents from 2010-2015 to 2016-2021, which may be attributable to the changes in the regulatory framework, training protocols, safety awareness initiatives, and technological advancements to address HAA safety.

A new risk level identification model for aviation safety

The aviation safety reporting system (ASRS) data, which are accident investigation reports issued by the national transportation safety board (NTSB), are often used for aviation risk level identification modeling. However, ASRS data suffer from sample imbalance and inaccurate encoding of textual information. To address these issues, this paper proposes a novel risk identification model. Initially, the pre-trained sentence bidirectional encoder representations from transformers (SBERT) model is fine-tuned using the textual information in the ASRS data, improving the accuracy of the text encoding. Subsequently, a generative adversarial network (GAN) is employed to generate samples for underrepresented categories in the ASRS data, thereby addressing the sample imbalance problem. Finally, a bayesian optimization algorithm is integrated to automatically search for the hyperparameters of the risk identification model, further enhancing the model's performance in risk level identification. Experimental results demonstrate that not only does the SBERT fine-tuning substantially improve the accuracy of text information encoding, but both data augmentation and automatic hyperparameter search also significantly contribute to the performance improvement of the risk level recognition model.

Navigating the Skies: Unraveling Communication Challenges in Diverse Aviation Accidents

Effective communication is the lifeline of aviation safety, serving as the cornerstone for preventing accidents, mitigating crises, and ensuring seamless coordination among diverse stakeholders within the complex and dynamic aviation environment. The aim of this study is to provide a qualitative analysis of the 10 fatal accidents in aviation history and incidents and accidents that occurred in the past 10 years registered by the National Transportation Safety Board (NTSB). The content analysis of the reports of the fatal accidents and reports of the 48 events identified in the accident database search revealed themes such as miscommunication between flight crew members, challenges in emergent situations, and communication breakdowns with ATC. These findings align with existing literature, emphasizing the pivotal role of communication in aviation safety. The study offers recommendations to invest in CRM training, standardized phraseology, and advanced communication technologies for aviation safety. Future research directions include exploring human-machine interaction, artificial intelligence, and communication in Unmanned Aerial Systems. Moreover, grounded in these findings, airline companies can infer practical implications such as improved safety, operational efficiency, stress reduction, cost savings, regulatory compliance, and trust-building, thereby emphasizing the industry's commitment to continuous improvement in navigating the complexities of aviation communication.

Human Factors in General Aviation Loss of Control: Survey of Pilot Experiences

Inflight loss of control (LOC-I) is a major cause of general aviation (GA) accidents. Previous studies have identified LOC-I causes from sources such as the National Transportation Safety Board (NTSB) database. NTSB GA accident reports include limited detail on human factors. Getting pilots’ perspectives from other sources, such as surveys, may reveal insights into pilot actions and conditions. This study investigates the role of human factors in LOC-I by analyzing demographics in NTSB accidents and conducting a survey of pilots’ LOC-I experiences based on the Human Factors Analysis and Classification System framework. Note that 80% of the LOC-I events shared by the pilots involved pilot error, most of which were skill-based and decision errors. About one-quarter of pilots mentioned that their instructor had not prepared them well or taught them methods to recover from LOC-I. Several pilots mentioned that, because of their lack of LOC-I recovery training, they could not recover from LOC-I. The study helped in identifying specific pilot errors and issues in training that were not mentioned explicitly in the NTSB reports. Findings from the study may help improve training methods and operating procedures for GA pilots to prevent loss of control in the future.

A data-driven conceptual framework for understanding the nature of hazards in railway accidents

Hazards threaten railway safety by their potential to trigger railway accidents, resulting in significant costs and impacting the public's willingness to use railways. Whilst many prior works investigate railway hazards, few offer a holistic view of hazards across jurisdictions and time because the large number of primary sources make synthesising such learnings time consuming and potentially incomplete. The conceptual framework HazardMap is developed to overcome this gap, employing open-sourced Natural Language Processing topic modelling for the automated analysis of textual data from Rail Accident Investigation Branch (RAIB), Australian Transport Safety Bureau (ATSB), National Transportation Safety Board (NTSB) and Transportation Safety Board of Canada (TSB) railway accident reports. The topic modelling depicts the relationships between hazards, railway accidents and investigator recommendations and is further extended and integrated with the existing risk theory and epidemiological accident models. The results allow the different aspects of each hazard to be listed along with the potential combinations of hazards that could trigger railway accidents. Better understanding of the aspects of individual hazards and the relationships between hazards and previous accidents can inform more effective hazard mitigation policies including technical or regulatory interventions. A case study of the risk at level crossings is provided to illustrate how HazardMap works with real-world data. This demonstrates a high degree of coverage within the existing risk management system, indicating the capability to better inform policymaking for managing risks. The primary contributions of the framework proposed are to enable a large amount of knowledge accumulated to be summarised for an intuitive policymaking process, and to allow other railway investigators to leverage lessons learnt across jurisdictions and time with limited human intervention. Future research could apply the technique to road, aviation or maritime accidents.

Survival After Ditching in Motorized Aircraft, 1989-2022.

INTRODUCTION: Although an unintended aircraft landing on water (referred to as ditching) is a rare event, the potential for occupant injury/fatality increases immediately following the event due to adverse conditions. However, to date, few studies have addressed the subject. Herein, ditching events and post-ditching survival were investigated.METHODS: Ditchings (1982-2022) in the United States were identified from the National Transportation Safety Board database. Occupant injury severity, aircraft type, pilot experience, flight conditions, and number of occupants were extracted. Poisson distribution, the Chi-squared test (2-tailed), Mann-Whitney U test, and Kruskal-Wallis one-way analysis of variance were employed.RESULTS: A total of 96 ditchings were identified. A systematic survey was hampered by the lack of a standardized reporting matrix in the reports. In total, 77 reports were included in the analysis. Across all ditchings, 128 of 169 (76%) occupants survived ditching and were rescued. Importantly, the initial ditching event was survived by 95% of all occupants. However, 32 (19%) occupants died post-ditching by drowning (21/32 cases) or for undetermined reasons. Considering probability per ditching event, in 26 (34%) of all ditchings, one or more occupants was/were fatally injured.DISCUSSION: Initial survival of the emergency ditching is high. Drowning was the leading cause of death after ditching and reduced the overall survival to 76%. Further investigation is needed to identify risk factors for fatal outcomes and/or improve probability of survival after ditching.Schick VC, Boyd DD, Hippler C, Hinkelbein J. Survival after ditching in motorized aircraft, 1989-2022. Aerosp Med Hum Perform. 2024; 95(5):254-258.

Nose-Over and Nose-Down Accidents in General Aviation: Tailwheels and Aging Airplanes

Safety in General Aviation has been a continuous concern. About 12% of all airplane accidents in General Aviation involve nose-overs and nose-down events. A total of 134 accidents reported by the National Transportation Safety Board that include nose-overs and nose-downs were analyzed for their main causes. It was found that 35% of the defining events involved a loss of control on the ground while 58% of the total dataset involved tailwheel-type aircraft. A relatively high proportion of aircraft built before 1950 were found, which are also aircraft that have tailwheel-type landing gear, and thereby a higher propensity for ground loops and nose-overs. It is shown that the high accident rate in General Aviation, especially for accidents that did not result in a fatality, was, to an important extent, explained by tailwheel and older aircraft in the US General Aviation airplane fleet struggling with controlling the aircraft on the ground. Attention to this group of aircraft in future studies may help to more effectively address the relatively high accident rates in General Aviation.

Transportation of hazardous material via railroad: Incident investigation and a case study of derailment in 2023

AbstractRailway transportation of hazardous materials (HAZMAT) is common and is generally considered safe. However, transporting toxic, flammable, and explosive substances via railways carries significant risk due to their high volume, proximity to populated areas, low public awareness, and potential domino effect. Particularly, the practice has come into question after a Norfolk Southern train derailed in Ohio in February of 2023. This derailment continuously reminds the public and the industry that such incidents can profoundly affect a community, critical infrastructure, and the environment. To identify the root cause of the Ohio train derailment and discover the deficiency of the safety system applied, combining the cause mapping approach with the safety triad concept was employed in this study. Based on this approach and the preliminary incident investigation released by the National Transportation Safety Board, the incident sequence is established, and the causal events leading to this incident are identified in the three essential pillars of its safety system: prevention, mitigation, and response, respectively. The study subsequently develops recommendations to improve the safety system of HAZMAT freight trains. This is expected to lower further the probability and consequence of HAZMAT freight train incidents and ultimately result in long‐term changes in railroad transportation.

Discovering latent themes in aviation safety reports using text mining and network analytics

Aviation accidents, referring to unexpected and undesirable events involving aircraft, often cause great damage to property and human life. Learning from historical accidents is pivotal for improving safety in aviation. However, aviation accidents are typically documented and stored as unstructured or semi-structured free-text, rendering the ability to analyze such data a difficult task. This study presents a novel framework that combines text mining and network analytics techniques and provides the ability to analyze aviation accident reports automatically. The framework comprises a four-step modelling approach to: (1) the transformation of unstructured aviation safety report texts into structured numeric matrices using the TF-IDF matrix; (2) the identification of aviation accident topics using a Structural Topic Model (STM); (3) the production of a Word Co-occurrence Network (WCN) to determine the interrelations between aviation safety risk factors; and (4) quantitative analysis by technology of keywords to pinpoint key causal factors in aviation safety events. The proposed framework is validated by analyzing aviation accident reports collected by the National Transportation Safety Board (NTSB). The results indicate that STM provides a more granular partitioning of topics and better distinguishes between similar events compared to traditional Latent Dirichlet Allocation (LDA). Among the identified topics, “Fuel and Power” and “En-route Phase” have the highest occurrence rate according to STM. Additionally, “Aircraft Crash” is the most prevalent topic in aviation accidents that resulted in fatal injuries, while “Landing phase” is the most prevalent topic in non-fatal injuries on accidents. Based on the word co-occurrence network, three centrality measures highlight “inspection of equipment” and “take off” as the most important risk factors in aviation safety. The proposed framework provides a comprehensive solution for in-depth analysis of aviation safety reports, offering decision support for aviation safety management and accident prevention, thereby reducing risks and strengthening safety measures.

Assessment of aviation accident datasets in severity prediction through machine learning

The importance and seriousness of civil aviation safety have become more noticeable due to the intricate advancement of air transportation. It is crucial to apply diverse datasets to evaluate and anticipate the degree of aviation safety. Data on the different causes of accidents can be analyzed and applied to predict and prevent potential accidents. The main goal of this research is to explore how Machine Learning (ML) techniques can be used to identify correlations and connections between various contributing factors in aviation accidents. It applies ML algorithms on datasets extracted from original data sourced from the National Transportation Safety Board (NTSB) of the United States, Transportation Safety Board (TSB) of Canada, and Australian Transport Safety Bureau (ATSB) aviation accident records spanning from January 2008 to January 2023. Initially, this study uses Artificial Neural Network (ANN), Decision Tree (DT), and Support Vector Machine (SVM) models to predict the civil aviation accident rates for the United States, Canada, and Australia data separately. Sequentially, by extracting Common Features (CF) and reclassifying the Common Sub-Features (CSF) of these three countries, a comprehensive model is created. Finally, it evaluates the differences and limitations of these countries' datasets. The results show that the separate models exhibit a higher level of prediction accuracy and lower errors compared to the common models and the best results (81% accuracy) were achieved through SVM.

Aircraft accident reports: A corpus-based genre analysis

Based on a corpus of ‘Aircraft Accident Reports’ (AARs) collected from the official website of The National Transportation Safety Board (NTSB), issued during the years 2000–2021, this study used Bhatia’s Critical Genre Analysis (CGA) framework to examine how this type of techno-professional discourse is recognized by considering the text, the genre, the professional practice, and the professional culture of the corpus. It was found that (1) textually, both Move2 collecting information, and Move3 Analyzing Information are the lengthiest moves within the corpus regarding the number of tokens, while Move1 Summarizing the Accident, Move4 Reaching Conclusion, Move5 Sharing Recommendations, and Move6 Board Member Statement are the shortest in length; (2) the generic move structure of the corpus contained six-move pattern (five of them are obligatory, and only one is optional), 11 steps, and 40 sub-steps; (3) the professional practice of the corpus is expressed through two types of discursive processes, they are: genre-mixing, and genre-embedding; and (4) the professional culture is presented through a set of professional values imbedded in the corpus, they are: embracing change and learn from mistakes, and maintaining objectivity and impartiality. The results of this study contribute in understanding the realization of professional discourse and expand the application of CGA in professional practices.

Amphibious Airplane Accidents: An Exploratory Analysis

Causes and contributing factors of amphibious airplane accidents are examined by comparing the proportion of fatal accidents for different causes of accidents, with a focus on landings on water and low-level flying maneuvers. A set of 183 accidents involving amphibious planes from 2005 to 2020 was extracted from the National Transportation Safety Board’s online database. Amphibious airplane accidents are reported to be fatal in 34% of cases, which is higher than the average of 20% for general aviation. Logistic regression analysis shows that the maneuvering flight phase and decision-making factors are significantly more often associated with fatal accidents than other flight phases and causes. In addition, the number of accidents associated with decision-making factors significantly increased during the studied time period. Amphibious airplanes benefit from accident analysis despite the absence of denominator data and the limitations of most general aviation accident reports. Intentional low-level flying is shown to be a central area of concern that may be addressed at the operational as well as the training level. Landing accidents could be avoided by introducing additional warning systems and training regarding (retractable) landing gear as well as general awareness training of decision-making during landings on water.

Wire Strikes and In-Air Obstacle Collisions During Agricultural Aviation Operations.

INTRODUCTION: Wire strikes and in-air collisions with obstacles are a leading cause of accidents in the aerial application industry. While some of these collisions occur due to unseen obstacles, some pilots report being previously aware of the obstacles that they collide with. Whether or not pilots are aware of obstacles pre-collision is an important factor to inform methods of accident prevention.METHODS: Final reports from the National Transportation Safety Board were analyzed for Part 137 Agricultural Operation accidents that took place between January 2020 and December 2022. A deeper analysis of cases that involved an in-air collision with an obstacle was performed, excluding cases that were attributable to an external cause (e.g., aerodynamic stall). The pilot's awareness of the obstacle pre-accident was inferred from accident narratives if available.RESULTS: Nearly half of all accidents (N = 45 of 107) involved an in-air collision with an obstacle (e.g., wire, tree, pole) as the defining event. In cases where pilot awareness of the obstacle was determinable through the accident report, over half of pilots (N = 21 of 39) had previously seen this obstacle yet still made contact with it.DISCUSSION: In-air obstacle collisions make up a substantial portion of accidents within Part 137 Agricultural Operations. Nearly half of pilots were already aware of the obstacle before collision, indicating that inadequate preparation in scoping the field is not a predominant driver of these events. Instead, these findings suggest that other factors including distractions, high task difficulty, and errors in decision-making may contribute.Baumgartner HM. Wire strikes and in-air obstacle collisions during agricultural aviation operations. Aerosp Med Hum Perform. 2023; 94(11):852-856.

Deficient Aeronautical Decision-Making Contributions to Fatal General Aviation Accidents.

INTRODUCTION: General aviation (GA), mainly comprised of light (≤12,500 lb) aircraft, maintains an inferior safety record compared with air carriers. To improve safety, aeronautical decision-making (ADM) practices have been advocated to GA pilots since 1991. Herein, we determined the extent to which GA pilots disregard such practices.METHODS: Fatal accidents (1991-2019) involving private pilots (PPLs) in single-engine airplanes were identified (N = 1481) from the National Transportation Safety Board AccessR database. Of these, deficient go/no-go and in-flight ADM-related mishaps were scored using the PAVE (pilot, aircraft, environment, external pressure)/IMSAFE (illness, medicine, stress, alcohol, fatigue, eating) and PPP (perceive, process, perform) models, respectively. Statistical testing used Poisson distributions, Fisher exact tests, and Mann-Whitney U-tests.RESULTS: Of the 1481 accidents, 846 were identified as deficient ADM-related. Electing to depart into a hazardous environment (PAVE), disregarding wellness (IMSAFE), and poor aircraft familiarity (PAVE) represented the most common categories (54%, 21%, and 20%, respectively) of errant go/no-go ADM. A 64% decline in fatal accidents related to errant go/no-go decisions for the environment category was evident over the 30-yr period, with little decrements in the other domains. Within the errant environment-related category accidents, the decision to depart into forecasted adverse weather (e.g., degraded visibility, icing, thunderstorms) constituted the most prevalent subcategory (56%, N = 195). Surprisingly, of this subcategory, accidents were overrepresented by over nine- and threefold for instrument-rated PPLs disregarding icing and thunderstorm forecasts, respectively.CONCLUSION: With little decrement in ADM-related accidents in the pilot, aircraft, and external pressure domains, new strategies to address such deficiencies for PPLs are warranted.Boyd DD, Scharf MT. Deficient aeronautical decision-making contributions to fatal general aviation accidents. Aerosp Med Hum Perform. 2023; 94(11):807-814.

The Five “I” Framework of crash investigation: Linking investigation practices to safety reform

Crash investigation is vital to the advancement of road safety, and it is a foundation for determining effective countermeasures and interventions for true road safety reform. However, the way in which road crash investigations are conducted substantially influences the quality of understanding and the effectiveness of responses. In crash investigations, we traditionally focus first on the question: “What caused this crash?” when it would be more efficient to ask immediately: “What could have prevented this crash?” or better yet, “What are all the ways this crash could have been prevented?”In this paper, we first explore a few common road crash investigation approaches where prosecution, retribution, or compensation are primary. We then examine investigation approaches where prevention is primary, especially investigations aimed at determining every point on the timeline preceding the crash where an intervention would have prevented the outcome, as illustrated by the Swiss Cheese Model. We draw from examples from the aviation industry, the occupational health and safety field, the U.S. National Transportation Safety Board (NTSB), and others, to identify strengths and weaknesses. We bring together good practices from several investigative approaches through the lens of diverse experiences in transportation safety and root-cause analysis to present a practical and proactive framework for road crash investigation. The Five “I” Framework provides guiding characteristics for prevention-focused safety investigations for road crashes: Immediate, In-Depth, Impartial, Independent, and Injury Prevention.The Five “I” Framework is a practical guide for investigations to move beyond crash causation to crash prevention, aligning with the Safe Systems Approach, Vision Zero, and the public health perspective. Rather than focusing primarily on on any single factor such as vehicle defect or driver error, it leads investigations to an array of countermeasures that involve collective action and systems change, and thus, to more effective road safety reform. Nevertheless, as a practical framework, it is the start (not the end) of discussions on how we can continue to move towards more multidisciplinary, collaborative, innovative, and ethical prevention efforts.

Nonlinear Time Series Analysis and Prediction of General Aviation Accidents Based on Multi-Timescales

General aviation accidents have complex interactions and influences within them that cannot be simply explained and predicted by linear models. This study is based on chaos theory and uses general aviation accident data to conduct research on different timescales (HM-scale, ET-scale, and EF-scale). First, time series are constructed by excluding seasonal patterns from the statistics of general aviation accidents. Secondly, the chaotic properties of multi-timescale series are determined by the 0–1 test and Lyapunov exponent. Finally, by introducing the sparrow search algorithm and tent chaotic mapping, a CSSA-LSSVM prediction model is proposed. The accident data of the National Transportation Safety Board (NTSB) of the United States in the past 15 years is selected for case analysis. The results show that the phase diagram of the 0–1 test presents Brownian motion characteristics, and the maximum Lyapunov exponents of the three scales are all positive, proving the chaotic characteristics of multi-timescale series. The CSSA-LSSVM prediction model’s testing results illustrate its superiority in time series predicting, and when the timescale declines, the prediction error reduces gradually while the fitting effect strengthens and then decreases. This study uncovers the nonlinear chaotic features of general aviation accidents and demonstrates the significance of multi-timescale research in time series analysis and prediction.