2027 Agenda
Beyond Situational Awareness: An Intelligence Model for Public Safety
Brooks T Shannon (Director of Emergency Communications Solutions, Esri)
Srini Samudrala (Sr. Director | Business Development | Public Safety | Qualcomm, Qualcomm)
Track:
Emerging Technologies: Drones, AI and NTN
Format:
Power Session
Vault Recording: TBD
Public safety organizations have access to more information than ever, yet emergency operations often remain reactive. Situational awareness can show call handlers, dispatchers, incident commanders, and responders what is happening. Situational intelligence can help them understand what it means, anticipate what may happen next, and make better decisions earlier.
This session introduces a situational intelligence model for public safety and explores it through practical future operational scenarios. Before an incident, digital twins and authoritative geospatial and operational data could support "public safety regression testing": repeatedly simulating severe weather, infrastructure failures, major events, communications outages, and compound emergencies to expose vulnerabilities and test preparedness. During an incident, live conditions could be compared with predicted outcomes to identify emerging risks, anticipate resource constraints, and recommend proactive actions. As more real data is collected, actual outcomes could improve future models, scenarios, and plans. Additionally, when conventional connectivity or the ability to get access to AI compute (that enables Situational Intelligence) is degraded, Edge AI compute deployed in a distributed manner, leveraging resilient, distributed communications infrastructures like Sidelink, would ensure that Situational Intelligence is available in a resilient manner, closer to the field for all personnel.
Using a severe-weather and infrastructure-disruption scenario, the presenters will show how the same intelligence cycle can support the control room and the frontline before, during, and after an emergency. The goal is not autonomous decision-making or more dashboards. It is better human decision-making: turning growing volumes of data into timely, actionable intelligence.
This session introduces a situational intelligence model for public safety and explores it through practical future operational scenarios. Before an incident, digital twins and authoritative geospatial and operational data could support "public safety regression testing": repeatedly simulating severe weather, infrastructure failures, major events, communications outages, and compound emergencies to expose vulnerabilities and test preparedness. During an incident, live conditions could be compared with predicted outcomes to identify emerging risks, anticipate resource constraints, and recommend proactive actions. As more real data is collected, actual outcomes could improve future models, scenarios, and plans. Additionally, when conventional connectivity or the ability to get access to AI compute (that enables Situational Intelligence) is degraded, Edge AI compute deployed in a distributed manner, leveraging resilient, distributed communications infrastructures like Sidelink, would ensure that Situational Intelligence is available in a resilient manner, closer to the field for all personnel.
Using a severe-weather and infrastructure-disruption scenario, the presenters will show how the same intelligence cycle can support the control room and the frontline before, during, and after an emergency. The goal is not autonomous decision-making or more dashboards. It is better human decision-making: turning growing volumes of data into timely, actionable intelligence.
Takeaway
1. Understand the difference between situational awareness and situational intelligence – and how public safety can move from seeing what is happening to anticipating what may happen next and acting earlier.
2. Learn how digital twins can support "public safety regression testing" by repeatedly simulating severe weather, infrastructure failures, major events, communications outages, and compound emergencies to expose vulnerabilities before they become consequences.
3. See how live operational data and AI can be used during an incident to compare expected versus actual conditions, identify emerging risks and resource constraints, and support more proactive human decision-making.
4. Explore how Edge AI, distributed compute, and resilient communications such as Sidelink can keep situational intelligence available closer to the field, even when access to centralized networks or cloud-based AI resources is degraded.
5. Understand how a continuous before-during-after intelligence cycle can improve preparedness over time, using actual incident outcomes to refine models, scenarios, plans, and future response decisions.
2. Learn how digital twins can support "public safety regression testing" by repeatedly simulating severe weather, infrastructure failures, major events, communications outages, and compound emergencies to expose vulnerabilities before they become consequences.
3. See how live operational data and AI can be used during an incident to compare expected versus actual conditions, identify emerging risks and resource constraints, and support more proactive human decision-making.
4. Explore how Edge AI, distributed compute, and resilient communications such as Sidelink can keep situational intelligence available closer to the field, even when access to centralized networks or cloud-based AI resources is degraded.
5. Understand how a continuous before-during-after intelligence cycle can improve preparedness over time, using actual incident outcomes to refine models, scenarios, plans, and future response decisions.