The Transportation Security Administration (TSA) uses AI in its day-to-day activities to protect the nation's transportation systems to ensure freedom of movement for people and commerce.
Below is an overview of each AI use case within TSA, as part of the Simplified DHS AI Use Case Inventory. More details about these use cases are available in the Full DHS AI Use Case Inventory on the DHS AI Use Case Inventory publication library.
AI use cases are listed by deployment status:
Pre-Deployment
Use Case Name: Automated Target Recognition (ATR) Developments for Standard Screening
Use Case ID: DHS-131
Use Case Summary: Automated Target Recognition (ATR) uses AI and machine learning to conduct real-time object recognition and anomaly, or target, detection on the Advanced Imaging Technology (AIT) machines to automatically detect possible prohibited items carried by passengers on their person through checkpoint. The system then reproduces the threat location on a representative human figure using a coordinate transform function (CTF) for resolution by Transportation Security Officers (TSOs). By using trained AI algorithms, TSA may display a potential threat location on a representative human figure to show TSOs visual outlines of suspected threat or prohibited items. The purpose of this use case is to improve upon ATR algorithms used to reduce privacy concerns because after this enhancement TSOs are no longer required to view AIT images. Operational systems do not continue to collect images or train the algorithm. The expected benefits are to increase detection, reduce false alarms, and improve efficiency and passenger experience.
The system reproduces the threat location, which is viewed as a bounding box on a representative human figure, for TSO resolution.
Use Case Topic Area: Transportation
Deployment Status: Pre-deployment (Acquisition and/or Development)
Safety- and/or rights-impacting? Yes. Safety- and rights-impacting. Before this AI use case is deployed, it will comply with risk management practices for deployed safety- and/or rights-impacting AI. Read more about compliance with required minimum risk management practices.
Use Case Name: Accessible Property Screening (APS) Checkpoint CT Prohibited Items
Use Case ID: DHS-132
Use Case Summary: This AI helps airplane luggage checks by the TSA officers scanning bags to have a continuous always watching partner to alert them to anything suspicious. Accessible Property Screening (APS) uses AI to identify both non-explosive threats and prohibited items in carry-on baggage as the bags pass through the Computed Tomography (CT) scanners at airports. The AI algorithms are trained to identify likely non-explosive threat and prohibited items through image segmentation and object recognition.
Currently, Transportation Security Officers (TSOs) assigned to scanners at airport checkpoints visually inspect each image. The TSOs resolve the system generated explosive alarms as well as visually inspect the image for the presence of non-explosive prohibited items such as guns and sharp objects. TSA is working on developing new AI and Machine Learning ML algorithms to automate the search for the non-explosive prohibited items (e.g. guns, knives, etc.). These AI solutions benefit the public by providing a consistent and uninterrupted level of threat detection as an added layer of security. The ML algorithms allow the TSOs to be more flexible and to better prioritize their attention on important items to improve security.
AI system output is a set of 3-dimentional bounding boxes that is displayed on the X-ray image. The bounding boxes are placed on top of objects or areas where the algorithm believes it has found a prohibited item (threat object).
Use Case Topic Area: Transportation
Deployment Status: Pre-deployment (Acquisition and/or Development)
Safety- and/or rights-impacting? Yes. Safety- and rights-impacting. Before this AI use case is deployed, it will comply with risk management practices for deployed safety- and/or rights-impacting AI. Read more about compliance with required minimum risk management practices.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Walk-Through Metal Detector (WTMD) Alternative Automated Target Recognition (ATR) Developments
Use Case ID: DHS-133
Use Case Summary: AI-enhanced Millimeter wave (mmWave) detectors are used as an alternative to Walk-Through Metal Detectors (WTMDs) for passenger screening to detect both metallic and non-metallic threats and prohibited items on passengers at the security checkpoint. These detectors are an improvement over traditional walk-through metal detectors and provide increased security and a better passenger experience. mmWave body scanners use safer, skin-sensitive, non-ionizing radiation to find concealed objects using pre-defined rule-based and deep learning algorithms to identify prohibited items and relay that information to the Transportation Safety Officers (TSOs) on duty at the checkpoint. An mmWave Automated Target Recognition (ATR) algorithm uses AI and machine learning (ML) to detect anomalies, or targets, on the body and reproduces the threat location on a representative human figure using a coordinate transform function (CTF) for TSO resolution. ATR algorithms are trained and then deployed. Operational systems do not continue to collect images or train the algorithm.
Use Case Topic Area: Transportation
Deployment Status: Pre-deployment (Acquisition and/or Development)
Safety- and/or rights-impacting? Yes. Safety- and rights-impacting. Before this AI use case is deployed, it will comply with risk management practices for deployed safety- and/or rights-impacting AI. Read more about compliance with required minimum risk management practices.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Synthetic Data for Improved Automated Thread Recognition (ATR) in Checkpoint Screening
Use Case ID: DHS-134
Use Case Summary: Engineers in the Transportation Security Administration’s (TSAs) Accessible Property Screening (APS) and On-Person Screening (OPS) program offices are developing AI to create images of prohibited items (i.e., synthetic data), such as knives or guns. These images are then used to train Automated Threat Recognition (ATR) and other AI models and systems to detect prohibited items in the screening processes.
Synthetic data can be quicker to produce which will improve effectiveness by addressing and adapting to new threats quicker. APS and OPS are working with vendors and evaluating AI-based synthetic data generation techniques to bolster the pool of training data available to develop machine learning algorithms in ATR applications. The AI will generate images that mimic the human body and various threats.
Use Case Topic Area: Transportation
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? Yes. Safety- and rights-impacting. Before this AI use case is deployed, it will comply with risk management practices for deployed safety- and/or rights-impacting AI. Read more about compliance with required minimum risk management practices.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: TSA Contact Center Virtual Assistant
Use Case ID: DHS-374
Use Case Summary: The Transportation Security Administration (TSA) Contact Center Virtual Assistant is an AI chat-bot designed to improve customer experience and increase efficiency on the TSA.gov website. An AI-powered virtual assistant serves as the initial point of contact for customers, using predictive AI or natural language processing (NLP), to answer routine questions. Customer service agents will remain available and will not be replaced by the virtual assistant.
The three goals for TSA’s virtual assistant are: (1) improve ease of access and increase efficiency be delivering timely, accurate responses to customers within and outside of the TSA Contact Center’s (TCC’s) operational hours; (2) improve effectiveness by collecting new customer insights to help drive agency improvements; and (3) improve fiscal responsibility by leveraging automation to meet increasing demand without the need for additional resources.
TSA’s virtual assistant, as a predictive AI tool, will not be able to create and provide original content to customers. It will be limited to providing responses to customer inquiries based on the existing content in the TCC’s knowledge library. However, it will record transactional data related to these customer inquiries (e.g., customer inputs, assistant outputs, topic classifications, etc.). TSA’s virtual assistant will create transactional data regarding customer inquiries in a consistent manner to our existing email and phone channels. TSA uses this transactional data to guide customer experience improvement efforts. This data offers TSA insights into what is working well, where the pain points are, where to improve public information, and what services are most requested.
Use Case Topic Area: Government Services (includes Benefits and Service Delivery)
Deployment Status: Pre-deployment (Acquisition and/or Development)
Safety- and/or rights-impacting? No
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Machine Learning Analysis Applied to Cyber Threat Hunt Data
Use Case ID: DHS-417
Use Case Summary: Cyber threat hunts typically involve a vast amount of data. Machine learning models can quickly and efficiently process this data as well as more effectively identify anomalous activity than humans. This could improve the efficiency and quality of cyber threat hunts by detecting suspicious behavior more quickly and increasing the amount of data that can be analyzed during a hunt. TSA is using machine learning (ML) models to analyze large volumes of TSA network log data from various systems to detect patterns more quickly and accurately than humans, aiding in more rapid response to potential threats. This tool currently detects anomalies or outliers within the collected data and could be expanded to include classification and categorization in the future. The analysis is run to explore the data and identify items for an analyst to analyze further. The ML output is a list of results with details including why that result was identified by the model and the statistical likelihood that it is a positive result. An analyst would then review these results and determine if any of the patterns might be associated with unusual cyber activity. The analyst then continues to analyze further as during normal cyber threat hunt operations.
Use Case Topic Area: Mission-Enabling (internal agency support)
Deployment Status: Pre-deployment (Acquisition and/or Development)
Safety- and/or rights-impacting? No. It was presumed rights-impacting relating to hiring and employment, but the DHS Chief AI Officer determined this use case does not satisfy the definition of rights-impacting AI in M-24-10. This use case only detects anomalies or outliers on the TSA network that is then reviewed by a human analyst team to determine if any of the patterns might be associated with unusual activity. The use case does not perform workplace monitoring or surveillance. Read more about safety and/or rights-impacting AI.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Conversation Training and Feedback Simulator
Use Case ID: DHS-2395
Use Case Summary: TSA's Training and Development office is using an off-the-shelf, on-demand, employee learning/training platform which contains commercial training on many topics tailored to each user's interests and skill level to support their personalized training plans and goals. One available component of the platform uses a large language model (LLM) as part of an interactive, dialogue-style training functionality to communicate with and advise the learner to develop critical non-security sensitive soft skills such as customer service and communicating on difficult topics using this conversation simulation tool. This function, if enabled, is intended to augment, and not replace, professional training interventions and human interaction.
Use Case Topic Area: Education & Workforce
Deployment Status: Pre-deployment (Acquisition and/or Development)
Safety- and/or rights-impacting? No
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: OTA Automated Passenger Screening Gate System
Use Case ID: DHS-2397
Use Case Summary: The automated passenger screening system regulates and expedites traveler screening by guiding passengers though the queue to the Advanced Imaging Technology (AIT) scanners. The system uses machine vision, a technology that enables computers to interpret and understand visual information, to assess body positioning and automatically initiate the screening process when the passenger is in the optimum position. The purpose is to manage passenger flow while reducing human interaction by using AI to assess body positioning and automatically initiate the screening process when the passenger is in the optimum position. The AI system initiates an AIT scan when the passenger is in the optimum position. Depending on the results of the AIT scan, the passenger would be routed either for additional screening or to the re-composure area to claim their accessible property and transit into the sterile area.
Use Case Topic Area: Transportation
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Axon Capture Application
Use Case ID: DHS-2399
Use Case Summary: The Transportation Security Administration (TSA) uses body-worn cameras that incorporate AI as a part of the underlying software. The tool is designed to provide rapid access to law enforcement and investigative data to assist Law Enforcement Officers (LEOs) and those reviewing evidence to quickly sort and categorize data. Once electronic evidence/video footage is transferred to the tool, AI provides rapid transcription and translation of audio recordings. The embedded translation tools use machine learning to convert speech from one language to another. The AI will transcribe audio/video data and provide a printable artifact. The embedded AI also categorizes video evidence to allow reviewers to quickly identify areas within the video that may need to be redacted if the data needs to be released (e.g., drivers licenses, passport, the faces of youth, license plates, monitor screens, etc.) This will cut investigative processing time significantly, while also increasing accuracy. The AI only provides recommendations the final usable data is reviewed and certified by TSA staff.
Use Case Topic Area: Law & Justice
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? Yes. Rights-impacting. Before this AI use case is deployed, it will comply with risk management practices for deployed safety- and/or rights-impacting AI. Read more about compliance with required minimum risk management practices.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Answer Engine
Use Case ID: DHS-2400
Use Case Summary: The TSA Answer Engine is an LLM AI running on a closed, internal system that is trained to generate human-like outputs to expedite employee workflows by answering questions and assisting with tasks. The initial scope of the Answer Engine will permit TSA employees to ask questions related to the screening procedures and receive an answer based on volumes of TSA regulations, guidance, and requirements data. This platform is anticipated to harness the power of AI to provide intelligent, context-aware responses and insights.
TSA aims to enhance its capabilities in managing and analyzing complex data, ultimately contributing to more effective and efficient security operations and optimizing the TSA's operational workflows and support capabilities.
Use Case Topic Area: Mission-Enabling (internal agency support)
Deployment Status: Pre-deployment (Acquisition and/or Development)
Safety- and/or rights-impacting? No
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Contract Requirement Automation
Use Case ID: DHS-2428
Use Case Summary: The Transportation Security Administration (TSA) is testing a contract documentation platform, Carver, to streamline the creation, management, and generation of requirement documentation for purchase request documents. . The tool leverages AI technologies like large language models (LLMs) and machine learning (ML) for automation. Based on user inputs, the system generates and manages standard language for key documents, such as Statements of Work (SOW), Performance Work Statements (PWS), and Statements of Objectives (SOO).
The tool attempts to provide the TSA user with contextually accurate outputs (primarily in the form of automated document generation and recommendations for procurement documentation) tailored to specific requirements. The platform provides contextual recommendations during the document creation process to ensure completeness and compliance with procurement requirements. The tool provides recommendations and decision support to guide users through the proper documentation structure and content requirements.
This will significantly reduce manual effort and errors in document creation while improving accuracy, consistency, compliance, and efficiency. By streamlining the procurement process, the agency can complete more procurement actions with existing resources, maximizing taxpayer dollars. The automated tool also reduces the time spent on manual or repetitive tasks (e.g., manual document creation and management), allowing for better resource allocation. The system's outputs always require human verification as part of the workflow, ensuring that all generated content is reviewed and approved by qualified personnel before being finalized in the procurement process.
Use Case Topic Area: Mission-Enabling (internal agency support)
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: TSA Case Handling Platform
Use Case ID: DHS-2429
Use Case Summary: The Transportation Safety Administration’s (TSA’s) Case Handling Platform is a custom case management platform developed for TSA’s Civil Rights and Civil Liberties Office that leverages AI technologies like large language models (LLMs) and machine learning (ML) to generate recommended language for common documents and reports for claims handlers working on Equal Employment Opportunity (EEO) claims by synthesizing the information collected about a case and input into the platform. Language recommendations are assessed by human reviewers before implementation.
The tool saves case workers manual time to download, order, and compile reports. The case workers can then use their time to work on cases rather than administrative tasks. The use case has the potential of streamlining collection processes related to cases, creating custom reports from various materials during the case managers interview process, producing a centralized tool to manage, and controlling all steps within each case.
Use Case Topic Area: Mission-Enabling (internal agency support)
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Automated Field Data Collection
Use Case ID: DHS-2430
Use Case Summary: Automated Field Data Collection technology leverages AI through machine vision, a technology that enables computers to interpret and understand visual information, to automatically collect, analyze and report observational field data of checkpoint and checked baggage screening operations. This solution provides the Transportation Security Administration (TSA) with near-real-time rates of passenger flows at various points in the checkpoint process to inform staffing resource allocation, reduce passenger wait times, and reduce the cognitive load on Transportation Security Officers (TSOs).
The AI will analyze screening environments via closed circuit television (CCTV) footage and extract passenger processing times of various steps within the screening processes. Enabling AI to extract and visualize this data (including screening location performance, rates and standards of the end-to-end screening system, and passenger wait times) will enable TSA to make data-informed decisions while testing or deploying new screening equipment, identify anomalies, establish real-world rates and standards, and reduce or eliminate TSA’s need to deploy data collection teams, resulting in real-time data collection and significantly reduced computational time of findings.
Use Case Topic Area: Transportation
Deployment Status: Pre-deployment (Acquisition and/or Development)
Safety- and/or rights-impacting? No
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Plan of Day Staff Operations
Use Case ID: DHS-2431
Use Case Summary: Plan of Day is the Transportation Security Administration’s (TSA’s) approach to modernize screening resource allocations, leverage data to inform decisions, and realize efficiencies. Plan of Day leverages AI to assist in checkpoint operational determinations and activities by conducting historical data analytics to help determine optimal screening lane hours and locations, predict necessary staffing requirements, and provide notifications to Transportation Security Officers (TSOs) when scheduling and leave requests are approved.
Plan of Day will automate TSA screening staff optimization though models capable of prescribing when screening lanes should be opened/closed, determining when/where screening staff is required to absorb operational peaks, determining optimal gender and certification ratios, recommending when to schedule overtime/shift adjustments, drafting lane rotation plans, and informing national TSA staffing requirements, factoring in changes to both optimization plans airline schedules.
Use Case Topic Area: Transportation
Deployment Status: Pre-deployment (Acquisition and/or Development)
Safety- and/or rights-impacting? No
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Low Probability of False Alarm (Low-PFA) Algorithm for On-Person Screening
Use Case ID: DHS-135
Use Case Summary: TSA uses Low Probability of False Alarm (Low-PFA) algorithms to train AI systems deployed for on-person screening. It utilizes ML to improve detection performance while decreasing alarm rates and passengers touch rates. The algorithm is gender agnostic, no longer requiring officers to select a passenger’s gender prior to being scanned. AIT scanner throughput and utilization have increased with this new algorithm. Once the algorithm is trained, it is locked down and no longer learning.
Use Case Topic Area: Transportation
Deployment Status: Deployed (Implementation and Assessment)
Safety- and/or rights-impacting? Yes. Safety- and rights-impacting
Key Identified Risk & Mitigations: Security risks include false negatives allowing threats to get through the sterile side of the airport or high false alarm rates slowing operations. The program follows the Test & Evaluation (T&E) process documented in the TSA T&E Policy, T&E Guidebook, TSA Acquisition Qualification Policy, and TSA Third Party Testing Strategy, which includes independent test & evaluation. Various types of testing were conducted, including functional testing, developmental test & evaluation, independent test & evaluation, and integration/implementation testing. Tests were conducted on a variety of body types with varying concealment locations, concealment methods, and target types. Metrics include probability of detection, probability of false alarm, mean time between failure, mean down time, mean time to repair, and percentage of eligible passengers unable to be screened. All tests met or exceeded expectations. TSA performs regular checks to verify performance of the scanner (which includes the AI model) using Operational Test Kits (OTK). OTKs are used daily, whenever a scanner is moved, whenever a scanner is power-cycled, and as needed to verify performance. OTKs are created by each OEM and are specific to their scanners. They contain items that when concealed on a scanned person will result in a positive scan for a target.
Read more about safety and/or rights-impacting AI and compliance with required minimum risk management practices.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Credential Authentication Technology with Camera System (CAT-2) and AutoCAT (CAT-2 in an E-Gate Form Factor)
Use Case ID: DHS-327
Use Case Summary: The Transportation Security Administration (TSA) uses one-to-one (1:1) facial matching technologies at some checkpoints to assist human reviewers with traveler identity verification. These systems temporarily capture an image of a traveler who chooses to use the screening method and then utilizes biometric technology to match the traveler to the identity document they have presented at the checkpoint. No images are retained by TSA, and the voluntary process increases speed and improves accuracy of identity verification by the human reviewer at the checkpoint.
Use Case Topic Area: Transportation
Deployment Status: Deployed (Operation and Maintenance)
Safety- and/or rights-impacting? Yes. Rights-impacting
Key Identified Risks & Mitigations: In the event of a non-match, the traveler may make a second attempt or TSA may perform additional identity verification steps to verify the identity of the traveler. This process may add between 20 seconds or a few minutes to the identity verification and security screening process. This is mitigated through T&E and continuous monitoring.
Read more about safety and/or rights-impacting AI and compliance with required minimum risk management practices.
Face Recognition/Face Capture (FR/FC)? Yes. All Face Recognition and Face Capture (FR/FC) technology is tested both prior to operational use and at least every three years during operational use. DHS Science and Technology (S&T) oversees testing and evaluation based on International Organization for Standardization/ International Electrotechnical Commission (ISO/IEC) standards and technical guidance issued by National Institute of Standards and Technology (NIST). DHS S&T applies laboratory, scenario, and operational testing to cost-effectively characterize technology performance and, when feasible, disaggregate performance by user demographics such as gender, age, and skin tone.
The DHS 2024 report on Use of Face Recognition and Face Capture Technologies provides additional information about use of FR/FC at DHS, including testing and evaluation of this use case.
Use Case Name: PreCheck Touchless Identity Solution (TIS)
Use Case ID: DHS-345
Use Case Summary: The Transportation Security Administration (TSA) uses one-to-many (1:n) facial identification technologies as an optional process at some checkpoints to assist human reviewers with traveler identity verification. This additional TSA PreCheck feature is voluntary, and passengers may opt-out of the process at any time and instead choose the standard identity verification by a Transportation Security Officer (TSO). These systems temporarily capture an image of a traveler who chooses to use the screening method and then cross references Customs and Border Protection’s (CBP’s) Traveler Verification Service (TVS) to compare the passenger’s live image to a gallery of pre-staged, enrolled reference photos. No images are retained by TSA, and the voluntary process increases speed and improves accuracy of identity verification by the human reviewer at the checkpoint.
Use Case Topic Area: Transportation
Deployment Status: Deployed (Operation and Maintenance)
Safety- and/or rights-impacting? Yes. Rights-impacting
Key Identified Risks & Mitigations: The key risk is the degradation of the TVS verification to degrade overtime based on the parameters of assessment for comparing images to templates. This was mitigated by testing the threshold for the biometric matching extensively with a variety of face types for several months to establish a match threshold for the identification. The algorithms have been trained on hundreds of millions of data points from a combination of public and private data sources. The underlying data covers a wide variety of demographics (e.g., age, race, gender, etc.) representative of the general population. During model training and refinement shortcomings (e.g., certain combinations of flesh tones and lighting, facial hair variations, etc.) were compensated for. The algorithms are industry leading as measured by NIST. This mitigates the risk of poor performance and algorithmic discrimination.
Read more about safety and/or rights-impacting AI and compliance with required minimum risk management practices.
Face Recognition/Face Capture (FR/FC)? Yes. All Face Recognition and Face Capture (FR/FC) technology is tested both prior to operational use and at least every three years during operational use. DHS Science and Technology (S&T) oversees testing and evaluation based on International Organization for Standardization/ International Electrotechnical Commission (ISO/IEC) standards and technical guidance issued by National Institute of Standards and Technology (NIST). DHS S&T applies laboratory, scenario, and operational testing to cost-effectively characterize technology performance and, when feasible, disaggregate performance by user demographics such as gender, age, and skin tone.
The DHS 2024 report on Use of Face Recognition and Face Capture Technologies provides additional information about use of FR/FC at DHS, including testing and evaluation of this use case.
Use Case Name: Airport Throughput Predictive Model
Use Case ID: DHS-2432
Use Case Summary: This use case is a predictive model for passenger volume to help with airport staffing. The Airport Throughput Predictive Model is an A) model which ingests checkpoint screening throughput data to train the predictive model, to provide projections for future-date throughput. Once a month the data is ingested, the predictive model is trained, and predictions of airport checkpoint throughput are made for the airports.
The projections produced by the model are incorporated into Business Intelligence dashboards for airport coordination centers to access. This model was designed to inform future operational planning, such as staffing needs projections, for all Transportation Security Administration (TSA) security checkpoints.
Use Case Topic Area: Mission-Enabling (internal agency support)
Deployment Status: Deployed (Operation and Maintenance)
Safety- and/or rights-impacting? No
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: CDC Airport Hotspot Throughput
Use Case ID: DHS-342
Use Case Summary: TSA launched the “Stay Healthy. Stay Secure.” campaign, which details proactive and protective measures implemented at security checkpoints to make the screening process safer for passengers and our workforce by reducing the potential of exposure to the coronavirus. The campaign includes guidance and resources to help passengers prepare for the security screening process in the COVID environment. A big part of that campaign was the development of the Centers for Disease Control and Prevention's Airport Hotspot Throughput. This capability determines the domestic airports that have the highest rank of connecting flights during the holiday travel season to help mitigate the spread of COVID-19. This capability is a DHS-developed artificial intelligence model written in Spark/Scala that takes historical non-PII travel data and computes the highest-ranking airports based on the PageRank algorithm. TSA does not make decisions about flight cancellations or airport closures. These decisions are made locally, on a case-by-case basis, by individual airlines, airports, and public health officials. TSA will continuously evaluate and adapt procedures and policies to keep the public and our workforce safe as we learn more about this devastating disease and how it spreads.
Deployment Status: Inactive (no longer used)
Safety- and/or rights-impacting? No
Face Recognition/Face Capture (FR/FC)? No
No changes to AI use cases within TSA since December 16, 2024. For other updates view the Full DHS AI Use Case Inventory on the DHS AI Use Case Inventory publication library.