Data-Driven Discovery of Mechanistic Ecosystem Models with LLMs

Ecosystem models are essential for ecosystem management, but their development traditionally requires significant time and expertise, creating bottlenecks in addressing urgent environmental challenges. We present “AI for Models of Ecosystems” (AIME), a novel framework that integrates large language models (LLMs) with evolutionary optimization to automate the discovery of interpretable ecological models from time-series data. AIME addresses the inverse problem of inferring ecologically meaningful mechanistic models that explain observed data while maintaining biological plausibility. We critically review AIME’s ability to recover known ecological relationships through two complementary marine case studies: (1) a nutrient-phytoplankton-zooplankton model, and (2) a Crown-of-Thorns starfish (COTS) model. In the first case, our best models displayed almost perfect recovery of known ecological dynamics while maintaining strong predictive performance across multivariate time-series. In the second case, best AIME generated models approached human expert models in terms of their ability to successfully capture COTS outbreak dynamics and demonstrated strong out-of-sample predictive power. AIME produces interpretable models with meaningful parameters that capture real biological processes, facilitating scientific insight and potentially accelerating management applications. By dramatically accelerating model development while offering ecological interpretability, AIME offers a powerful new tool for addressing urgent ecological challenges in rapidly changing environments.