Artificial Intelligence and Computational Modeling for Complex Adaptive Systems
I develop computational methods for understanding complex systems and identifying the mechanisms capable of producing the behavior we observe.
My research combines artificial intelligence, agent-based modeling, network science, simulation, and statistical methods to study information diffusion, collective behavior, and complex adaptive systems.
Postdoctoral Researcher · University of Central Florida
Complex Adaptive Systems Lab
Research
What mechanisms are capable of generating the behavior we observe?
I study inverse problems in generative systems: when observations are produced by complex models, what can we infer about the rules or mechanisms that generated them? My current work focuses on equifinality, rule identification, and uncertainty-aware inference for agent-based models.
How do interactions among individuals produce diffusion, influence, and collective dynamics?
I study how information and behavior propagate through interacting populations, how influence can be represented and measured, and how local behavioral rules produce large-scale social dynamics.
How can machine learning, simulation, and scalable computation help us model and understand complex adaptive systems?
I develop and use computational models that combine simulation, machine learning, and scalable implementation to study systems whose collective behavior emerges from many interacting components.
How can complex longitudinal, categorical, relational, and behavioral data be represented and analyzed statistically?
I work on statistical representations and methods for complex social and behavioral data, including categorical longitudinal trajectories, network structure, and compositional similarity.
Projects
Many behavioral processes are observed as categorical trajectories rather than ordinary numeric time series. This work develops methods for representing and clustering densely observed categorical longitudinal data and applies them to social-media behavior.
Read the project ↗SocialSim investigated computational approaches to modeling and forecasting online social behavior. My work centered on a multi-platform simulation framework and the Multi-Action Cascade Model, connecting behavioral assumptions about influence with scalable implementation.
Read the project ↗Current-research flagship
Different generative mechanisms can produce similar observable behavior. This work investigates how machine learning and conformal prediction can be used to identify sets of plausible behavioral rules in agent-based models rather than forcing a single overconfident explanation.
Read the project ↗This line of work studies how information spreads through social systems and how influence can be measured across actors and communities. It spans my doctoral research, diffusion models, and DARPA MIPS work on influence pathways using transfer entropy and network-based methods.
Read the project ↗Publications
2026
Jayalath, C., Champon, X., Rand, W., Jasser, J., Garibay, O., Garibay, I.
Data & Policy (Cambridge University Press), 8, e4
Compares targeted, community-based intervention strategies against population-wide responses for shaping information diffusion outcomes on social media.
2026
Champon, X., Staicu, A., Weishampel, A., Jayalath, C., Rand, W.
Journal of the American Statistical Association
Develops categorical-valued functional data analysis methods for latent-process estimation and clustering of social media users' behavioral trajectories.
2026Accepted
Jayalath, C., Rand, W., Garibay, I.
Conference of the Computational Social Science Society of the Americas (CSS), Santa Fe, NM
Introduces a conformal-prediction approach to identifying plausible sets of behavioral rules in agent-based models, rather than a single point estimate.
Software
Software is a major part of my research practice. I build packages, simulation frameworks, and analytical tools that turn methodological ideas into reusable computational systems.
brandpy
Python package
Sole developer
A Python package interfacing with the Brandwatch API, enabling automated data retrieval and preprocessing for social-media research.
View ↗catfda
R package
Co-developed
An R package for categorical-valued functional data analysis, implementing methods for latent-process estimation and clustering of densely observed categorical longitudinal data using GAM-based modeling and functional principal component analysis.
View ↗funviewR
R package
Sole developer
An open-source R package for analyzing and interactively visualizing function-call dependencies in R codebases, helping users understand project structure, identify dependencies, and document complex R projects.
View ↗Influence Network Generator (ING)
Python package
Sole developer
An open-source Python package for generating influence networks from online social-media data, supporting large-scale diffusion modeling. Adopted in DARPA-funded research on information propagation.
View ↗About
My research has consistently centered on computational models of interacting systems. I began with computer graphics, simulation, and agent-based models of group behavior, then moved toward information diffusion and influence in online social systems. My current work asks the inverse question: when we observe the behavior of a complex system, what can we actually infer about the mechanisms that generated it?
Read the full journey ↗
Teaching
I teach computational methods by connecting theory to implementation: students should understand not only how an algorithm works, but what assumptions it makes, when it fails, and how to turn it into a working system.
6 graduate courses at UCF · mentoring across UCF and NCSU labs
Teaching & mentoring ↗Updates
I'm interested in collaborations and opportunities involving artificial intelligence, generative modeling, simulation, and complex adaptive systems.
acj.chathura@gmail.com