Our research focuses on advanced network-based modeling designed for accurate prediction and real-time forecasting across a wide range of domains. We target critical areas such as disease outbreaks, social trends, and infrastructure behavior, where understanding the dynamics of complex networks is key to effective decision-making. At the core of our work is the "predictive" aspect of network intelligence, harnessing the power of sophisticated modeling techniques to anticipate future outcomes and trends. By leveraging these tools, we aim to provide insights that support proactive decision-making in dynamic, interconnected systems, bridging the gap between network theory and practical applications, helping decision-makers navigate uncertainty and respond swiftly to emerging challenges.
Complex Systems Forecasting
Featured projects
Epydemix, the ABC of epidemics
This open-source Python package is designed to support users through the last mile of epidemic modeling. From model definition to calibration and scenario exploration. It allows users to build models with an arbitrary number of compartments and transitions, providing the flexibility to define custom transition rules, time-varying parameters, and the impact of interventions on both contact structures and disease parameters. The package supports classic models (e.g., SIR, SEIR) and enables custom modifications, including behavioral dynamics and intervention effects. It is built in Python and openly available, allowing the community to contribute and extend its capabilities.
Epistorm
Part of InsightNet, Epistorm is a CDC-funded national initiative that aims to forecast infectious disease outbreaks much like weather systems. It combines data from genomics, wastewater, and mobility with AI tools to support faster, more accurate public health responses.
