Enhancing generalizability of model discovery across parameter space with multi-experiment equation learning (ME-EQL)
This work addresses the challenge of computational inefficiency and lack of generalizability in modeling self-organizing biological systems, though it appears incremental as it extends existing equation learning methods.
The paper tackled the problem of improving the generalizability of equation learning methods for deriving continuum models from agent-based simulations across different parameter sets, and the result was that both proposed methods significantly reduced relative error in parameter recovery, with one method offering better generalizability.
Agent-based modeling (ABM) is a powerful tool for understanding self-organizing biological systems, but it is computationally intensive and often not analytically tractable. Equation learning (EQL) methods can derive continuum models from ABM data, but they typically require extensive simulations for each parameter set, raising concerns about generalizability. In this work, we extend EQL to Multi-experiment equation learning (ME-EQL) by introducing two methods: one-at-a-time ME-EQL (OAT ME-EQL), which learns individual models for each parameter set and connects them via interpolation, and embedded structure ME-EQL (ES ME-EQL), which builds a unified model library across parameters. We demonstrate these methods using a birth--death mean-field model and an on-lattice agent-based model of birth, death, and migration with spatial structure. Our results show that both methods significantly reduce the relative error in recovering parameters from agent-based simulations, with OAT ME-EQL offering better generalizability across parameter space. Our findings highlight the potential of equation learning from multiple experiments to enhance the generalizability and interpretability of learned models for complex biological systems.