This is a Preprint and has not been peer reviewed. This is version 2 of this Preprint.
Species Field Theory: Discovery of Latent Ecological Structure from Community Time Series
Downloads
Authors
Abstract
Ecological abundance time series are shaped not only by interactions among species, but also by broader community-level dynamics such as hidden resources and shared ecological constraints. We introduce Species Field Theory (SFT), a field-based framework for discovering latent ecological structure from abundance time series. SFT recovered directed interactions in a six-species Lotka--Volterra system, achieving a mean signed Spearman correlation of 0.887 across five random seeds. In a Huisman resource-competition system, SFT latent states aligned with hidden resource dynamics. These results suggest that interaction recovery is a special case of broader latent ecological structure discovery.
DOI
https://doi.org/10.32942/X2VH42
Subjects
Population Biology
Keywords
Species Field Theory, ecological time series, latent ecological structure, ecological dynamics, field-based representation, machine learning
Dates
Published: 2026-05-04 12:06
Last Updated: 2026-05-04 12:06
Older Versions
License
CC-BY Attribution-No Derivatives 4.0 International
Additional Metadata
Language:
English
There are no comments or no comments have been made public for this article.