Blog
Filter by tag

Next Generation Machine Learning for Proactive Emergency Management

How Figure Eight Federal is Driving Transformational AI Innovations in Disaster Response and Recovery

At the Esri FedGIS Plenary in Washington DC, several exciting demonstrations were shared for the first time. On the Plenary stage, Jo Fraley and Brady Cline demonstrated how Figure Eight Federal has joined forces with Esri, the global leader in location intelligence, to build AI-based solutions for Humanitarian Assistance and Disaster Response (HADR) at the Department of Defense’s Joint Artificial Intelligence Center (JAIC). Supporting first responders has led to the expansion of Figure Eight Federal’s current work with the Department of Defense in pathfinder programs and National Mission Initiatives – applying AI and machine learning (ML) for effective human-machine teaming.

Natural disasters such as floods, hurricanes, and wildfires are becoming increasingly complex threats. Emergency Management resources are being stretched thin from the frequency and intensity of damage, and affected communities are now often left overwhelmed and devastated. In 2019, ten disasters alone – among them major flood events, a hurricane and a soaking from a tropical storm – inflicted over $1B in damage. First responders need new and improved tools to understand the depth and breadth of disasters so that they can make plans, acquire resources and respond accordingly to affected communities.

Before Figure Eight Federal and Esri joined forces, analysts would use disparate tools to manually comb through hours of video or images to identify damaged homes, roads, and debris. First responders in the field would work around-the-clock to develop damage estimates for a disaster declaration or to determine the funds needed for an affected community. Depending on the size and scope of the damage, this could take several hours or even days to complete.

This is where GeoAI, powered by Figure Eight Federal and Esri, can provide a force multiplier. Before any AI application or capability can operate effectively, the machine learning model that supports it must “learn” by being shown many examples of verified, ground-truth data instances (e.g. audio, text, image, or video data). The quality of training data sets critically affects the operation of an AI capability. Developing high-quality training data sets through data annotation (labeling), can be painstaking, laborious, technically challenging, and must be performed under rigorous quality control and security. It is, nonetheless, the most critical component. Nothing moves efficiently or effectively without high-quality training data.

disaster response and recovery training data annotation human-machine teaming annotation

Figure Eight Federal provides a turnkey solution to build ML training data at massive scale. The Figure Eight Federal platform offers a cloud-based platform coupled with a Crowd to transform hundreds of hours of video, and tens of thousands of images into high quality, valuable ML training data for the JAIC. Taking this a step further, Figure Eight Federal integrates directly into the Esri platform and ArcGIS Portal. Using Esri’s WebApp Builder on ArcGIS Portal, analysts and first responders can select data, such as damaged homes or structures, on-the-fly to be transformed into training data that ultimately improves the speed and effectiveness of their work.

Speed and accuracy are both critical to response and recovery efforts. ML models and a more automated process can provide analysts and first responders with more accurate information about damaged areas with greater frequency and accuracy. Near real-time updates from first responders applying ML models with high-quality training data can inform the public to coordinate response and recovery efforts. Accuracy is also important, especially as it relates to the precise location of a flooded road, a downed power line, or a home lifted off of its foundation.

By integrating Figure Eight Federal into core mission systems like Esri’s ArcGIS platform, Emergency Management partners can now rely on high-quality training data for any disaster.

From Preparedness to Working at the Response Edge: Making Human-Machine Teaming a Reality in the Emergency Management Lifecycle Through Quality ML Data Annotation

Comprehensive situational and operational awareness in disaster response requires access to data and the ability to transform it into actionable insight. Figure Eight Federal powers tools to enable awareness with machine speed and accuracy across the entire emergency management lifecycle.

Preparedness and Training

Figure Eight Federal’s ML training data helps emergency management build human-machine teaming capacity. First responders work diligently to prepare for a wide variety of disasters, collecting a wealth of data in the process. By leveraging quality, annotated, operational data, (about specific geography, for example) Emergency Management is prepared to address new challenges at machine speed. In training or in practice, quality ML data can provide the ground-truth in exercises where human-machine teaming can save seconds, and lives.

Mitigation

By providing training data for ML models that can scan thousands of acres in minutes, Figure Eight Federal can enable first responders to target and mitigate risk. First responders can use ML models to prioritize areas where flood, fire, or hurricane damage is most likely to happen, and proactively contact risky areas to make necessary changes before a disaster occurs. Quality training data is crucial, though, to identify and prioritize among areas of greatest risk.

Response

“You had to have been there.” A point of failure for many ML models can be their “brittleness,” or their ability to not perform well in situations for which they were not trained. Through innovative approaches to building ML training data, however, Figure Eight Federal offers new opportunities to generate content with near real-time context. Figure Eight Federal can apply, for example, ML-assisted annotation to streaming data, or near real-time data, using ML to generate annotations that are peer-reviewed by annotators, reducing the time needed to train ML models while increasing their accuracy. In addition, Figure Eight Federal provides the ability to capture and label data for annotation at the edge on mobile devices. The ability to capture and annotate data at the edge and train ML models to perform better brings effective human-machine teaming to the problem.

Recovery

Disasters are not static, nor is the damage that is left behind. As waters recede, winds die down, and fires are slowly contained, there is a transition from tactical to strategic response and long term sustainment of operations. ML models powered by quality training data can support both persistent situational awareness and logistics. Prioritizing among known and emerging threats is a constant need in a disaster zone. ML computer vision models can monitor and track problems as they evolve. ML models can also easily flag, and recalculate, logistical needs for affected areas dynamically. Robust ML models can help communities recover at the speed of relevance.

The New Normal: Figure Eight Federal and Esri Help First Responders with Machine Speed

The Figure Eight and Esri partnership enables a transformational Machine Learning Enterprise pipeline. Figure Eight Federal’s foundational training data capabilities, ML assisted annotation and data annotation at the edge (DAAE), paired with Esri’s ArcGIS platform, will dramatically benefit future disaster relief efforts.

“We work with the best organizations out there to deliver on unique sets of capabilities, scope, and scale when it comes to problem-solving applications for the US government’s Joint Artificial Intelligence Center,” said Jack Dangermond, Esri founder and president. “When we looked at high-quality AI training data providers, we found Figure Eight to be the industry standard, and we are very happy to partner with them to support search and discovery, resource allocation, and rescue or relief execution efforts at scale with the highest accuracy.”

AI-powered Global Humanitarian and Disaster Relief

The Figure Eight platform provides annotated data for Esri, which then uses the predictive power of AI and location analytics to provide new insights. Building on the work of the Figure Eight and Esri team, the disaster relief AI initiative will be carried out by JAIC and on-the-ground disaster relief teams using tablets and ML models.

This comes together to, for example, rapidly distinguish objects and areas to locate flood-affected areas and infrastructure, working to identify areas that have been damaged or people that are at-risk or in-need. First responders, government decision-makers, and local residents can then better deal with disaster relief and rescue operations.

Harnessing the power of high-quality training data for the greater good is something we strongly believe in and support at Figure Eight Federal.

For more information about Figure Eight Federal, contact Dave Cook.

Dave Cook

Dave Cook

Dave Cook is a data science and geospatial practitioner based in Washington, DC. He is passionate about how we can uncover, communicate and apply the value of data to improve lives and address critical needs. Over his 20+ year career, Dave has focused on solving complex challenges in law enforcement, intelligence, defense, government, and across leading corporations worldwide. Believing that data science and analytics is more a marathon than a sprint, Dave holds firmly to the power of lifelong learning, consistent training, and endless reinvention. He is currently the Government Leader for Figure Eight Federal in Washington DC.