Convenience Zone Generation & Pre-Computation

Our team specializes in designing innovative algorithms that lay the foundation for accurate and detailed simulations.

Clustering Movement Data: Using U.S. Census data and SafeGraph mobility patterns, we group census block groups (CBGs) to reveal how populations interact and move within a city. Our algorithm produces dynamic map visualizations that showcase these connections over time, offering insights into the interconnectedness of neighborhoods.

Modeling Realistic Movement Patterns: We build synthetic populations that replicate real-world movement behaviors. By simulating interactions at homes, workplaces, and community spaces, we capture the complexity of daily life, integrating travel and daily routines to create a flexible framework.

Our simulation framework is at the heart of understanding disease dynamics in communities.

When someone is marked as infected, our Disease Modeling Platform (DMP) tracks their progression through various health states, guided by scientifically derived transition matrices. This allows for a realistic representation of disease spread over time.

By integrating clustering algorithms, population data, and movement patterns, the simulator models disease progression within pre-defined geographic regions. Each module is fully customizable, enabling users to adapt the system for unique research needs.

Our platform brings complex simulations to life with intuitive and impactful visualizations seen on this very website.

Users can explore the spread of disease through dynamic heatmaps, zoom into specific facilities or households, and analyze infection trends, demographic breakdowns, and state transitions. These tools offer an in-depth view of how infections impact different parts of a community.

We're constantly enhancing our visualizations to present data in more meaningful and actionable ways, helping users uncover patterns and insights at a glance.