You are here:
EmergencAI Tool | Data Management Tabletop Exercise (Data TTX) Summary Report
Citation:
Boe, T., W. Calfee, S. Serre, E. Silvestri, J. Falik, J. Deagan, K. McConkey, M. Rodgers, AND E. Rebour. EmergencAI Tool | Data Management Tabletop Exercise (Data TTX) Summary Report. U.S. Environmental Protection Agency, Washington, DC, EPA/600/R-23/070, 2023.
Impact/Purpose:
Through this effort, a novel new artificial intelligence-based tool that can be used to generate tabletop exercise scenarios was exercised and evaluated. Observations and recommendations related to data that are generated, managed, used, and communicated during an incident, simulated by using the tool, were also documented to enhance the United States Coast Guard (USCG) and EPA’s ability to respond to and recover from a CBRN incident. The operational considerations and feedback received through this data tabletop exercise provided invaluable information for improvements to the tool.
Description:
In the event of a chemical, biological, radiological, and/or nuclear (CBRN) wide-area incident, the U.S. Environmental Protection Agency (EPA) is responsible for environmental remediation, waste disposal processes, data collection, and data quality checks to advise decision-making. The U.S. Coast Guard (USCG) shares this responsibility for certain incidents in the maritime domain<span style='mso-element:field-begin'>CITATION NRF \l 1033 <span style='mso-element:field-separator'> (National Response Framework - Fourth Edition, Emergency Support Function (ESF) #10 2019)<span style='mso-element:field-end'>. To prepare emergency response personnel, agencies conduct “tabletop” training exercises (TTX) where teams of participants are charged with developing strategies and response plans that address conditions that are characterized in the exercise scenarios. Historically, TTXs have been created by experts in emergency response and require extensive resources to plan and prepare supporting information. Given this, EPA sought to develop a solution to dynamically create instantaneous and realistic training scenarios and related assets that can be used to train response personnel. EPA created the EmergencAI tool to facilitate CBRN scenario development in support of training and exercising agencies’ capabilities<span style='mso-element:field-begin'> CITATION TTXPPT \l 1033 <span style='mso-element:field-separator'> (Boe, Calfee and Holt, et al. 2022)<span style='mso-element:field-end'>. The tool is designed to generate a detailed and realistic CBRN scenario, in real time based on user inputs and accompanied by relevant data, to allow TTX participants to play through a scenario in a traditional tabletop exercise. In association with EPA’s Homeland Security Research Program and the Department of Homeland Security (DHS)/EPA-sponsored Analysis for Coastal Operational Resiliency (AnCOR) Data project, EPA held an EmergencAI Tool and Data Management TTX (Data TTX) on August 16th of 2022 at the Joint Base McGuire-Dix-Lakehurst in Burlington County, New Jersey. The Data TTX was conducted to introduce the EmergencAI Tool to responders, planners, and researchers; simulate developing TTX scenarios; identify how data are shared or exchanged among response phases; and evaluate proxy data that are generated by the tool in support of the scenario. Critical user feedback gathered during the Data TTX will be used to inform future revisions to the tool and data management strategies. Observations and recommendations related to data that are generated, managed, used, and communicated during an incident were also documented to enhance the USCG and EPA’s ability to respond to and recover from a CBRN incident. Through this project, EPA gained valuable feedback validating the utility and applicability of the tool and obtained insightful suggestions to consider as future enhancements. Overall, participants agreed that the scenarios developed by the tool were creative and impressive, but participants were left wanting more detail in the scenario that would inform strategies for determining sampling, decontamination, or waste management plans. Five key takeaways to inform future priorities included: · Improved scenario realism; · Allow scenario tailoring to align with user-defined objectives; · Incorporate additional scenario inputs that correlate to varying response types; · Further training and/or analyzing AI model results; and · Consider allowing flexible source data to generate scenario data. Lastly, participants emphasized the ongoing challenge with interagency data sharing and recommended that EPA identify and communicate suitable platforms (that maintain necessary views and roles) that can be used to share and communicate data during a response would be valuable.