Revealing Complex Ecological Dynamics via Symbolic Regression. (16th October 2019)

• Record Type: Journal Article
• Authors: Chen, Yize; Angulo, Marco Tulio; Liu, Yang‐Yu
• Is Part Of: BioEssays. Volume 41:Number 12(2019:Dec.)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2019-10-16
• Subjects: community ecology -- ecological dynamics -- functional response -- symbolic regression; Molecular biology -- Periodicals; Cytology -- Periodicals; Developmental biology -- Periodicals; 572.8
• DOI: 10.1002/bies.201900069
• Languages: English
• ISSNs: 0265-9247

Abstract

Abstract: Understanding the dynamics of complex ecosystems is a necessary step to maintain and control them. Yet, reverse‐engineering ecological dynamics remains challenging largely due to the very broad class of dynamics that ecosystems may take. Here, this challenge is tackled through symbolic regression, a machine learning method that automatically reverse‐engineers both the model structure and parameters from temporal data. How combining symbolic regression with a "dictionary" of possible ecological functional responses opens the door to correctly reverse‐engineering ecosystem dynamics, even in the case of poorly informative data, is shown. This strategy is validated using both synthetic and experimental data, and it is found that this strategy is promising for the systematic modeling of complex ecological systems. Abstract : The proposed symbolic regression (SR) techniques would help ecologists infer ecological dynamics purely from temporal data. With additional prior information on possible forms of functional responses, SR works efficiently to discover the governing equations that explain interaction mechanisms.