Search NASA⌕ Search

SEARCH · Search NASA

Results for “adverse events”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 records
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Predicting Adverse Events and their Precursors in Aviation Using Multi-Class Multiple-Instance Learning

In recent years, there has been a rapid growth in the application of machine learning techniques that leverage aviation data collected from commercial airline operations to improve safety. Anomaly detection and predictive maintenance have been the main targets for machine learning applications. However, this paper focuses on the identification of precursors, which is a relatively newer application. Precursors are events correlated with adverse events that happen prior to the adverse event itself. Therefore, precursor mining provides many benefits including understanding the reasons behind a safety incident and the ability to identify signatures, which can be tracked throughout a flight to alert the operators of an potential upcoming adverse event. This work proposes using the multiple-instance learning (MIL) framework, a weakly supervised learning task, combined with a carefully designed Multi-Head Convolutional Neural Networks-Recurrent Neural Networks (MHCNN-RNN) architecture to predict different type of adverse events for any given flights and identify their precursors with little to no post-processing.Results obtained show that the MHCNN-RNN is able to accurately forecast high speed and high path angle events during the approach, and that it is also capable of determining the aircraft’s parameters that are correlated to these events. These parameters can be considered precursors to the events.

multiple instance learning↗
NASA NTRS2014

Prediction of Adverse Events in Time Series Data Using ACCEPT (Adverse Condition and Critical Event Prediction Toolbox)

Abstract:An open-source toolbox called ACCEPT (Adverse Condition and Critical Event Prediction Toolbox) that operates from within the Matlab programming environment is introduced. The toolbox provides an open source, special-purpose functionality that can be used specifically for the prediction or forecasting of adverse events in time series data. It also provides a single, unifying framework in which to compare a variety of combinations of algorithmic approaches addressing this problem. The architectural framework also offers the flexibility for expansion to accommodate the newest, latest popular regression and detection methods for this particular problem, enabling the development of an infrastructure that can act as a proving ground platform for comparing new techniques to the state of the art. As such, its intention is to act as a catalyst in advancing the state of the art in technologies related to this problem. There are a variety of other toolboxes that offer similar capabilities and features, however they are either more suitable as general purpose machine learning toolboxes or are only available commercially or through agreements. ACCEPT fills that niche by offering visibility into a specific approach for addressing the adverse event prediction problem.

programming environments↗
NASA NTRS2019

Deep Learning Method for Detecting Precursors to Adverse Events

With the recent advancements in Deep Learning methods, the ability to model large complex heterogeneous data sets are fundamentally changing industry and research. Coupled with hardware improvements, and ease of implementation, a wide variety of deep neural network architectures can quickly be developed to solve a sweeping range of problems such as: object detection in images, automatic healthcare diagnosis using heterogenous data sources, real time language translating and sentence prediction, upscaling low resolution images, and forecasting of multivariate timeseries. Generally, many of these architectures outperform classical machine learning approaches in their respective tasks, however, this typically comes at a cost of interpretability. These black box algorithms generally suffer from lack of transparency in both model complexity as well as the rationale behind the prediction. This lack of comprehension, is driving an emerging area of interest in “Explainable AI”. An algorithm called: “Deep Temporal Multiple Instance Learning”1 was a recently developed to identify precursors to adverse events and has been applied in the aviation domain. The deep learning architecture is designed to capture the evolution of the probability of the outcome over the time preceding the adverse event using a multiple instance learning approach as illustrated in Figure 1. Precursors are defined when the probability of the event has exceeded a threshold at some point in the timeseries, at which point, a sensitivity analysis is performed to determine contributing factors. The contributing factors are used to explain and define the precursor during the periods where the probability score is high. The identified contributing factors are then presented to subject matter experts to provide objective insights into the leading factors associated with the particular adverse event. The algorithm has been tested on flight data from a commercial airline and has the ability to discover precursors to known adverse events that take the form of safety critical operations, such as unstable approach events on final approach. Apart from detecting precursors to adverse events, the converse can also be leveraged to discover corrective actions. These positive actions manifest themselves as periods in the timeseries when the precursor score has been lowered from an elevated state; meaning that if the system had been left uncorrected, it would have eventually reached the adverse event state. Characterizing these state changes can help identify successful interventions that may not have been known before. Policy makers and procedure designers can use this additional knowledge to craft more safety and efficient resilient procedures for future operations and therefore improve the overall performance of the National Airspace.

Matthews, Bryan L.↗
NASA NTRS2010

Near Real-Time Optimal Prediction of Adverse Events in Aviation Data

The prediction of anomalies or adverse events is a challenging task, and there are a variety of methods which can be used to address the problem. In this paper, we demonstrate how to recast the anomaly prediction problem into a form whose solution is accessible as a level-crossing prediction problem. The level-crossing prediction problem has an elegant, optimal, yet untested solution under certain technical constraints, and only when the appropriate modeling assumptions are made. As such, we will thoroughly investigate the resilience of these modeling assumptions, and show how they affect final performance. Finally, the predictive capability of this method will be assessed by quantitative means, using both validation and test data containing anomalies or adverse events from real aviation data sets that have previously been identified as operationally significant by domain experts. It will be shown that the formulation proposed yields a lower false alarm rate on average than competing methods based on similarly advanced concepts, and a higher correct detection rate than a standard method based upon exceedances that is commonly used for prediction.

Martin, Rodney Alexander↗
NASA NTRSDate not supplied

Capturing Complex Multivariate Time Series Interactions to Detect High-Risk Adverse Events During Flight

The reduction of aviation safety metrics below target thresholds continue to drive down the number of aviation fatalities and accidents. To meet future safety demands, sustained efforts by aviation agencies promoting safety assurance processes and systems have prompted ongoing research on identifying and mitigating in-flight risks. With the projected increase in passenger load factor and rollout of more autonomous systems into the national airspace, the need to detect high-risk events in-time or ahead-of-time is becoming increasingly crucial. New anomaly detection and precursor identification algorithms will need to scale to different airframes, levels of autonomy, and system complexity. While the pervasiveness of deep learning has resulted in the development of performant anomaly detection methods, these sophisticated models currently suffer from low end-user interpretability. Building off our previous work on identifying adverse events in multivariate flight data during descent, we propose a data-driven approach for detecting in-flight adverse events caused by the complex interplay of flight variables. Our approach utilizes ordinal patterns of important aircraft stability variables (e.g., airspeed and descent rate) to capture multivariate flight dynamics that can be used to predict the onset of unstable approaches, a high-risk adverse event that can occur during approach. Through the use of ordinal patterns, we aim to create more interpretable detection models of in-flight adverse events that can be translated to future autonomous systems without difficulty. Our analysis shows the presence of distinct ordinal pattern distributions that can be used to predict unstable approaches 1 minute ahead of time with an accuracy of 0.69 and a recall of 0.73 and 30 seconds ahead with an accuracy of 0.70 and a recall of 0.86.

Risk detection↗
NASA NTRS2004

Analysis of Adverse Events in Identifying GPS Human Factors Issues

The purpose of this study was to analyze GPS related adverse events such as accidents and incidents (A/I), Aviation Safety Reporting System (ASRS) reports and Pilots Deviations (PDs) to create a framework for developing a human factors risk awareness program. Although the occurrence of directly related GPS accidents is small the frequency of PDs and ASRS reports indicated there is a growing problem with situational awareness in terminal airspace related to different types of GPs operational issues. This paper addresses the findings of the preliminary research and a brief discussion of some of the literature on related GPS and automation issues.

Adams, Catherine A.↗
NASA NTRS2011

Causal Factors and Adverse Events of Aviation Accidents and Incidents Related to Integrated Vehicle Health Management

Causal factors in aviation accidents and incidents related to system/component failure/malfunction (SCFM) were examined for Federal Aviation Regulation Parts 121 and 135 operations to establish future requirements for the NASA Aviation Safety Program s Integrated Vehicle Health Management (IVHM) Project. Data analyzed includes National Transportation Safety Board (NSTB) accident data (1988 to 2003), Federal Aviation Administration (FAA) incident data (1988 to 2003), and Aviation Safety Reporting System (ASRS) incident data (1993 to 2008). Failure modes and effects analyses were examined to identify possible modes of SCFM. A table of potential adverse conditions was developed to help evaluate IVHM research technologies. Tables present details of specific SCFM for the incidents and accidents. Of the 370 NTSB accidents affected by SCFM, 48 percent involved the engine or fuel system, and 31 percent involved landing gear or hydraulic failure and malfunctions. A total of 35 percent of all SCFM accidents were caused by improper maintenance. Of the 7732 FAA database incidents affected by SCFM, 33 percent involved landing gear or hydraulics, and 33 percent involved the engine and fuel system. The most frequent SCFM found in ASRS were turbine engine, pressurization system, hydraulic main system, flight management system/flight management computer, and engine. Because the IVHM Project does not address maintenance issues, and landing gear and hydraulic systems accidents are usually not fatal, the focus of research should be those SCFMs that occur in the engine/fuel and flight control/structures systems as well as power systems.

Reveley, Mary S.↗
NASA NTRS2018

Using ADOPT Algorithm and Operational Data to Discover Precursors to Aviation Adverse Events

The US National Airspace System (NAS) is making its transition to the NextGen system and assuring safety is one of the top priorities in NextGen. At present, safety is managed reactively (correct after occurrence of an unsafe event). While this strategy works for current operations, it may soon become ineffective for future airspace designs and high density operations. There is a need for proactive management of safety risks by identifying hidden and "unknown" risks and evaluating the impacts on future operations. To this end, NASA Ames has developed data mining algorithms that finds anomalies and precursors (high-risk states) to safety issues in the NAS. In this paper, we describe a recently developed algorithm called ADOPT that analyzes large volumes of data and automatically identifies precursors from real world data. Precursors help in detecting safety risks early so that the operator can mitigate the risk in time. In addition, precursors also help identify causal factors and help predict the safety incident. The ADOPT algorithm scales well to large data sets and to multidimensional time series, reduce analyst time significantly, quantify multiple safety risks giving a holistic view of safety among other benefits. This paper details the algorithm and includes several case studies to demonstrate its application to discover the "known" and "unknown" safety precursors in aviation operation.

aviation safet↗
NASA NTRS2011

An Examination of Commercial Aviation Accidents and Incidents Related to Integrated Vehicle Health Management

The Integrated Vehicle Health Management (IVHM) Project is one of the four projects within the National Aeronautics and Space Administration's (NASA) Aviation Safety Program (AvSafe). The IVHM Project conducts research to develop validated tools and technologies for automated detection, diagnosis, and prognosis that enable mitigation of adverse events during flight. Adverse events include those that arise from system, subsystem, or component failure, faults, and malfunctions due to damage, degradation, or environmental hazards that occur during flight. Determining the causal factors and adverse events related to IVHM technologies will help in the formulation of research requirements and establish a list of example adverse conditions against which IVHM technologies can be evaluated. This paper documents the results of an examination of the most recent statistical/prognostic accident and incident data that is available from the Aviation Safety Information Analysis and Sharing (ASIAS) System to determine the causal factors of system/component failures and/or malfunctions in U.S. commercial aviation accidents and incidents.

Reveley, Mary S.↗
NASA NTRS2014

Are Medications Involved in Vision and Intracrancial Pressure Changes Seen in Spaceflight?

The Food and Drug Association Adverse Event Reports (FDA AER) from 2009-2011 were used to create a database from millions of known and suspected medication-related adverse events among the general public. Vision changes, sometimes associated with intracranial pressure changes (VIIP), have been noted in some long duration crewmembers. Changes in vision and blood pressure (which can subsequently affect intracranial pressure) are fairly common side effects of medications. The purpose of this study was to explore the possibility of medication involvement in crew VIIP symptoms. Reports of suspected medication-related adverse events may be filed with the Food and Drug Administration (FDA) by medical professionals or consumers. Quarterly compilations of these reports are available for public download. Adverse Event Reporting System (AERS) reports from 1/1/2009- 6/30/2012 were downloaded and compiled into a searchable database for this study. Reports involving individuals under the age of 18 and older than 65 were excluded from this analysis. Case reports involving chronic diseases such as cancer, diabetes, multiple sclerosis and other serious conditions were also excluded. A scan of the medical literature for medication-related VIIP-like adverse events was used to create a list of suspect medications. These medications, as well as certain medications used frequently by ISS crew, were used to query the database. Queries for use of suspected medications were run, and the nature of the symptoms reported in those cases were tabulated. Symptoms searched in the FDA AERS were chosen to include the typical symptoms noted in crewmembers with VIIP. Vision symptoms searched were: visual acuity reduced, visual impairment, and vitreous floaters. Pressure changes included: abnormal sensation in eye, intracranial pressure increased, intraocular pressure increased, optic neuritis, optic neuropathy, and papilloedema. Limited demographic information is included with the FDA AERS; relevant data were also sorted by age and sex from each report. RESULTS Steroid-containing oral contraceptives had the highest number of reports associated with vision (n=166) and pressure symptoms (n=54). Corticosteroid-containing medications were also high; prednisone, for example, had 137 reports of vision issues and 79 of pressure issues. Pain relievers were also a medication class with vision and pressure-related adverse events reported. Common over-the-counter medications such as acetaminophen, aspirin and ibuprofen each had multiple reports for both vision and pressure symptoms. Antimicrobial medications ciprofloxacin and diflucan were also associated with a number of vision and pressure-related AERS. Unexpectedly, pseudoephedrine and promethazine were mentioned in fewer than 20 reports each over the 3.5 years of data examined. The FDA AERS represents a wealth of data, but there are several limitations to its use. The data are entered by the public or medical professionals, but are not checked for accuracy or completeness and may even be entered multiple times. The causal relationship between a particular adverse event and a particular medication is not tested. The cases represent a broad spectrum of demographics, occupations, and health histories, and thus do not model the astronaut population well. There is no information on the frequency of use of a medication for comparison purposes; it is not possible to assign a rate for any particular adverse event. Nonetheless, there are compelling trends. Use of corticosteroid-containing medications, pain relievers (even over-the-counter), and oral contraceptives were associated with higher numbers of vision- or intracranial pressure-related adverse events. In general, there were more vision problems than pressure problems reported. Certain medications that were once suspected of playing a role in the crew VIIP syndrome, namely pseudoephedrine and promethazine, were found to have extremely low numbers of VIIP-like AERS in the FDA data. However, crew use of corticosteroid-containing medications and pain relievers may warrant additional investigation

Faust, K. M.↗
NASA NTRS2013

Evidence Report: Risk of Crew Adverse Health Event Due to Altered Immune Response

The Risk of Crew Adverse Health Event Due to Altered Immune Response is identified by the National Aeronautics and Space Administration (NASA) Human Research Program (HRP) as a recognized risk to human health and performance in space. The HRP Program Requirements Document (PRD) defines these risks. This Evidence Report provides a summary of the evidence that has been used to identify and characterize this risk. It is known that human immune function is altered in‐ and post‐flight, but it is unclear at present if such alterations lead to increased susceptibility to disease. Reactivation of latent viruses has been documented in crewmembers, although this reactivation has not been directly correlated with immune changes or with observed diseases. As described in this report, further research is required to better characterize the relationships between altered immune response and susceptibility to disease during and after spaceflight. This is particularly important for future deep‐space exploration missions.

Crucian, Brian↗
NASA NTRSDate not supplied

Capturing Multivariate Time Series Interactions to Detect High‑Risk Instability During Approach

The reduction of aviation safety metrics below target thresholds continue to drive down the number of aviation fatalities and accidents. To meet future safety demands, sustained efforts by aviation agencies promoting safety assurance processes and systems have prompted ongoing research on identifying and mitigating in-flight risks. With the projected increase in passenger load factor and rollout of more autonomous systems into the national airspace, the need to detect high-risk events in-time or ahead-of-time is becoming increasingly crucial. New anomaly detection and precursor identification algorithms will need to scale to different airframes, levels of autonomy, and system complexity. While the pervasiveness of deep learning has resulted in the development of performant anomaly detection methods, these sophisticated models currently suffer from low end-user interpretability. Building off our previous work on identifying adverse events in multivariate flight data during descent, we propose a data-driven approach for detecting in-flight adverse events caused by the complex interplay of flight variables. Our approach utilizes ordinal patterns of important aircraft stability variables (e.g., airspeed and descent rate) to capture multivariate flight dynamics that can be used to predict the onset of unstable approaches, a high-risk adverse event that can occur during approach. Through the use of ordinal patterns, we aim to create more interpretable detection models of in-flight adverse events that can be translated to future autonomous systems without difficulty. Our analysis shows the presence of distinct ordinal pattern distributions that can be used to predict unstable approaches 1 minute ahead of time with an accuracy of 0.69 and a recall of 0.73 and 30 seconds ahead with an accuracy of 0.70 and a recall of 0.86.

Risk detection↗
NASA NTRS2003

A Survey of Logic Formalisms to Support Mishap Analysis

Mishap investigations provide important information about adverse events and near miss incidents. They are intended to help avoid any recurrence of previous failures. Over time, they can also yield statistical information about incident frequencies that helps to detect patterns of failure and can validate risk assessments. However, the increasing complexity of many safety critical systems is posing new challenges for mishap analysis. Similarly, the recognition that many failures have complex, systemic causes has helped to widen the scope of many mishap investigations. These two factors have combined to pose new challenges for the analysis of adverse events. A new generation of formal and semi-formal techniques have been proposed to help investigators address these problems. We introduce the term mishap logics to collectively describe these notations that might be applied to support the analysis of mishaps. The proponents of these notations have argued that they can be used to formally prove that certain events created the necessary and sufficient causes for a mishap to occur. These proofs can be used to reduce the bias that is often perceived to effect the interpretation of adverse events. Others have argued that one cannot use logic formalisms to prove causes in the same way that one might prove propositions or theorems. Such mechanisms cannot accurately capture the wealth of inductive, deductive and statistical forms of inference that investigators must use in their analysis of adverse events. This paper provides an overview of these mishap logics. It also identifies several additional classes of logic that might also be used to support mishap analysis.

Johnson, Chris↗
NASA NTRS2014

2013 Immune Risk Standing Review Panel Evidence Review for: The Risk of Crew Adverse Health Event Due to Altered Immune Response

The 2013 Immune Risk Standing Review Panel (from here on referred to as the SRP) met for a site visit in Houston, TX on February 3-4, 2014. The SRP reviewed the new Evidence Report for the Risk of Crew Adverse Health Event Due to Altered Immune Response (from here on referred to as the 2013 Immune Evidence Report), as well as the Research Plan for this Risk that is in the current version of the Human Research Program’s (HRP) Integrated Research Plan (IRP).

Steinberg, Susan↗
NASA NTRS2002

The Strengths and Weaknesses of Logic Formalisms to Support Mishap Analysis

The increasing complexity of many safety critical systems poses new problems for mishap analysis. Techniques developed in the sixties and seventies cannot easily scale-up to analyze incidents involving tightly integrated software and hardware components. Similarly, the realization that many failures have systemic causes has widened the scope of many mishap investigations. Organizations, including NASA and the NTSB, have responded by starting research and training initiatives to ensure that their personnel are well equipped to meet these challenges. One strand of research has identified a range of mathematically based techniques that can be used to reason about the causes of complex, adverse events. The proponents of these techniques have argued that they can be used to formally prove that certain events created the necessary and sufficient causes for a mishap to occur. Mathematical proofs can reduce the bias that is often perceived to effect the interpretation of adverse events. Others have opposed the introduction of these techniques by identifying social and political aspects to incident investigation that cannot easily be reconciled with a logic-based approach. Traditional theorem proving mechanisms cannot accurately capture the wealth of inductive, deductive and statistical forms of inference that investigators routinely use in their analysis of adverse events. This paper summarizes some of the benefits that logics provide, describes their weaknesses, and proposes a number of directions for future research.

Johnson, C. W.↗
NASA NTRS2014

2013 Immune Risk Standing Review Panel Research Plan Review for: The Risk of Crew Adverse Health Event Due to Altered Immune Response

The 2013 Immune Risk Standing Review Panel (from here on referred to as the SRP) participated in a meeting with representatives from the Human Research Program (HRP) Human Health Countermeasures (HHC) Element and HRP management on February 3-4, 2014 in Houston, TX to review the updated Research Plan for the Risk of Crew Adverse Health Event Due to Altered Immune Response in the HRP Integrated Research Plan. The SRP is impressed with the work the immune discipline has done since the 2012 SRP review and agrees with the new wording of the Gaps, no longer questions, now statements. The SRP also likes the addition of adding targets for closing the Gaps, but it is not clear how they got to some of the interim stages (interval percentages). A major concern that the SRP has mentioned since the initial 2009 SRP meeting is that there is still not enough emphasis on the interdisciplinary aspect of the immune risk associated with other risks (i.e., nutrition, radiation, etc.). The SRP recommends that a "translational SRP" or advisory group be developed that is composed of members from all of the HRP SRPs. The SRP also thinks that the immune discipline should consider a more systems biology approach. Lastly, the SRP is concerned that the risks observed in research from low Earth orbit (LEO) missions may not accurately reflect all the risks of longer duration flight beyond LEO. Also, there does not seem to be a concern for immune responses that may occur when someone is in space longer than six months, for example, a Mars mission would take three years. The absence of disease in past and current flight scenarios does not mean the risk may not be there in future flight settings.

Steinberg, Susan↗
NASA NTRSDate not supplied

An Approach to Identifying Aspects of Positive Pilot Behavior within the Aviation Safety Reporting System

The National Airspace System (NAS) is constantly evolving as air traffic continues to ramp up to pre-pandemic numbers and projected to grow to unprecedented levels in the coming years. As well as increasing demand to the current system, emerging operations such as Unmanned Autonomous Systems are also expected to add to complexity in the airspace. To address these issues, the industry and government agencies supporting the NAS will need to rely upon additional automation and new technologies to address future operational requirements, while continuing to be a world-leading safe transportation system. As these new technologies are implemented, the system continues to rely on human pilots and controllers in the loop to monitor the system and intervene in situations the automation cannot handle. The goal of proactively addressing safety is of foremost concern to ensure passenger confidence. The industry has implemented various Safety Monitoring Systems to identify safety risks and proactively address them before they result in a serious incident or accident. One such program is the Aviation Safety Reporting System (ASRS). ASRS is a long-established system where pilots and controllers voluntarily and anonymously report safety incidents they experienced and observed during line operations by providing rich text narratives describing the events, the environment, and conditions leading to the safety event of concern. These narratives provide insight and context around events of interest and can be used to identify emerging problems. They can trigger investigations within Flight Operational Quality Assurance or Flight Data Monitoring programs. However, this process typically focuses on the adverse events and the unsafe aspects of the operations surrounding the reported or detected events. This perspective of investigating factors that went wrong around an adverse event is commonly referred to as Safety I. Alternatively, characterizing successful actions that operators perform every day under varying conditions that keep the system within safe operating bounds is a concept referred to as Safety II. The benefit of the Safety II view is that the scope is much larger than that of Safety I since a vast majority of the operations result in successful flights. Many of the successful techniques used to manage operational threats are not documented in standard operating procedures or taught during training. They are typically acquired over time by working with experienced pilots during line operations or in many cases after experiencing a problem for the first time and reacting to it in situ, drawing from years of experience to manage the threat. In an attempt to quantify these positive actions, we are proposing an approach to extracting key behaviors within ASRS reports that can support the Safety II concept. Our analysis assumes that ASRS reports contain some descriptions of corrective actions that operators performed to prevent a situation from leading to an accident. Leveraging recent advances in Natural Language Process modeling, we have developed an approach to extract positive sentiment from reports, embed these positive statements in a vector space where they can be numerically analyzed, and clustering these statements into similar contextual categories. From these contextualized categories we can attempt to summarized and distilled aspects of the positive behavior. The goal is to identify categories of behavior that describe consistent operator techniques that supports the Safety II concept. With this information, airlines may enable learning from these positive actions, or address procedures that need to be changed to avoid having pilots implement a workaround. These insights can provide a lens into what is “going right” in the operations that may otherwise not be known widely within the community. It is envisioned that this approach can be extended to other narrative programs such as Line Operation Safety Audit or Learning Improvement Team reports where similar observed behavior can be analyzed to extract positive actions and inform the overall operations.

NLP↗
NASA NTRSDate not supplied

An Approach to Identifying Aspects of Positive Pilot Behavior within the Aviation Safety Reporting System

The National Airspace System (NAS) is constantly evolving as air traffic continues to ramp up to pre-pandemic numbers and projected to grow to unprecedented levels in the coming years. As well as increasing demand to the current system, emerging operations such as Unmanned Autonomous Systems are also expected to add to complexity in the airspace. To address these issues, the industry and government agencies supporting the NAS will need to rely upon additional automation and new technologies to address future operational requirements, while continuing to be a world-leading safe transportation system. As these new technologies are implemented, the system continues to rely on human pilots and controllers in the loop to monitor the system and intervene in situations the automation cannot handle. The goal of proactively addressing safety is of foremost concern to ensure passenger confidence. The industry has implemented various Safety Monitoring Systems to identify safety risks and proactively address them before they result in a serious incident or accident. One such program is the Aviation Safety Reporting System (ASRS). ASRS is a long-established system where pilots and controllers voluntarily and anonymously report safety incidents they experienced and observed during line operations by providing rich text narratives describing the events, the environment, and conditions leading to the safety event of concern. These narratives provide insight and context around events of interest and can be used to identify emerging problems. They can trigger investigations within Flight Operational Quality Assurance or Flight Data Monitoring programs. However, this process typically focuses on the adverse events and the unsafe aspects of the operations surrounding the reported or detected events. This perspective of investigating factors that went wrong around an adverse event is commonly referred to as Safety I. Alternatively, characterizing successful actions that operators perform every day under varying conditions that keep the system within safe operating bounds is a concept referred to as Safety II. The benefit of the Safety II view is that the scope is much larger than that of Safety I since a vast majority of the operations result in successful flights. Many of the successful techniques used to manage operational threats are not documented in standard operating procedures or taught during training. They are typically acquired over time by working with experienced pilots during line operations or in many cases after experiencing a problem for the first time and reacting to it in situ, drawing from years of experience to manage the threat. In an attempt to quantify these positive actions, we are proposing an approach to extracting key behaviors within ASRS reports that can support the Safety II concept. Our analysis assumes that ASRS reports contain some descriptions of corrective actions that operators performed to prevent a situation from leading to an accident. Leveraging recent advances in Natural Language Process modeling, we have developed an approach to extract positive sentiment from reports, embed these positive statements in a vector space where they can be numerically analyzed, and clustering these statements into similar contextual categories. From these contextualized categories we can attempt to summarized and distilled aspects of the positive behavior. The goal is to identify categories of behavior that describe consistent operator techniques that supports the Safety II concept. With this information, airlines may enable learning from these positive actions, or address procedures that need to be changed to avoid having pilots implement a workaround. These insights can provide a lens into what is “going right” in the operations that may otherwise not be known widely within the community. It is envisioned that this approach can be extended to other narrative programs such as Line Operation Safety Audit or Learning Improvement Team reports where similar observed behavior can be analyzed to extract positive actions and inform the overall operations.

NLP↗