Species Field Theory: Discovery of Latent Ecological Structure from Community Time Series

This is a Preprint and has not been peer reviewed. This is version 2 of this Preprint. You must log in to post a comment. There are no comments or no comments have been made public for this article. This is a Preprint and has not been peer reviewed. This is version 2 of this Preprint. Add a Comment You must log in to post a comment. Comments There are no comments or no comments have been made public for this article. 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. https://doi.org/10.32942/X2VH42 Population Biology Species Field Theory, ecological time series, latent ecological structure, ecological dynamics, field-based representation, machine learning Published: 2026-05-04 11:06 Last Updated: 2026-05-04 11:06 CC-BY Attribution-No Derivatives 4.0 International Language: English