Biology subjects

Fulton, E. A.

Publications and source records attributed to Fulton, E. A..

4 recordsLinked to original sources

bioRxiv2025

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 LEMMA (LLM Enabled Mechanistic Modelling for ecosystem Assessment), a framework that programmatically generates and iteratively refines mechanistic ecosystem models by combining large language models (LLMs) for equation synthesis and parameter search, evolutionary algorithms for structural optimization, and Template Model Builder (TMB) for efficient parameter estimation. We critically review LEMMAs 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 LEMMA 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. LEMMA 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, LEMMA offers a powerful new tool for addressing urgent ecological challenges in a changing world.

ecology↗

bioRxiv2025

The Green Band: Using Production and Catch to Judge Distortive Pressure on an Ecosystem

Ecosystem based fisheries management is an increasingly accepted approach for many fisheries management agencies. Indicators and methods that can usefully support the aspiration of making ecosystem based fisheries management decisions on tactical time frames are slowly accumulating, but have primarily focused on biomass status and trends. We first verify that fishing can distort the cumulative distribution of connections within an ecosystem, and then show (via theoretical testing and application to four contrasting case study locations) how relating catch with production by defining an acceptable band of exploitation pressure - the "Green Band" - can help inform fisheries decision makers as to whether an ecosystem is under distortive patterns of fishing pressure that will ultimately undermine the structure of the ecosystem.

ecology↗

bioRxiv2025

Automated Diet Matrix Construction for Marine Ecosystem Models Using Generative AI

We introduce a proof-of-concept framework, Synthesising Parameters for Ecosystem modelling with LLMs (SPELL), that automates species grouping and diet matrix generation to accelerate food web construction for ecosystem models. SPELL retrieves species lists, classifies them into functional groups, and synthesizes trophic interactions by integrating global biodiversity databases (e.g., FishBase, GLOBI), species interaction repositories, and optionally curated local knowledge using Large Language Models (LLMs). We validate the approach through a marine case study across four Australian regions, achieving high reproducibility in species grouping (>99.7%) and moderate consistency in trophic interactions (51-59%). Comparison with an expert-derived food web for the Great Australian Bight indicates strong but incomplete ecological accuracy: 92.6% of group assignments were at least partially correct and 82% of trophic links were identified. Specialized groups such as benthic organisms, parasites, and taxa with variable feeding strategies remain challenging. These findings highlight the importance of expert review for fine-scale accuracy and suggest SPELL is a generalizable tool for rapid prototyping of trophic structures in marine and potentially non-marine ecosystems. HighlightsO_LILLM-based framework automates species grouping and diet matrix creation with >99.7% consistency C_LIO_LI51-59% of trophic interactions show high stability (stability score > 0.7) across iterations C_LIO_LIIn expert comparison, SPELL achieved 81.6% agreement and 80% of diet differences < 0.2 C_LIO_LILLM-driven synthesis integrates global databases with unstructured local knowledge C_LIO_LIReduces ecosystem model development time from months to hours C_LI

ecology↗

bioRxiv2018

Ensemble projections of global ocean animal biomass with climate change

Climate change is shifting the abundance and distribution of marine species with consequences for ecosystem functioning, seafood supply, management and conservation. Several approaches for future projection exist but these have never been compared systematically to assess their variability. We conducted standardized ensemble projections including 6 global fisheries and marine ecosystem models, forced with 2 Earth-system models and 4 emission scenarios in a fished and unfished ocean, to derive average trends and associated uncertainties. Without fishing, mean global animal biomass decreased by 5% ({+/-}4%) under low and 17% ({+/-}11%) under high emissions by 2100, primarily driven by increasing temperature and decreasing primary production. These climate-change effects were slightly weaker for larger animals and in a fished ocean. Considerable regional variation ranged from strong biomass increases in high latitudes to strong decreases in mid-low latitudes, with good model agreement on the direction of change but variable magnitude. Uncertainties due to differences among ecosystem or Earth-system models were similar, suggesting equal need for model improvement. Our ensemble projections provide the most comprehensive outlook on potential climate-driven ecological changes in the ocean to date. Realized future trends will largely depend on how fisheries and management adapt to these changes in a changing climate.

ecology↗