Automated Discovery of Relationships, Models, and Principles in Ecology

Frontiers in Ecology and Evolution

卷:8

José Cascalho¹  François Rigal²  Vasco V. Branco⁴  Luís Correia⁴  Stefano Mammola⁵  José C. Carvalho⁶  Pedro Cardoso⁷  Paulo A. V. Borges⁷  Rosalina Gabriel⁷ 

[1] Departamento de Ciências Agrárias, Núcleo de Investigação e Desenvolvimento em e-Saúde (NIDes), Angra do Heroísmo, Portugal;

[2] Institut Des Sciences Analytiques et de Physico Chimie pour L'environnement et les Materiaux UMR5254, Comité National de la Recherche Scientifique - University de Pau et des Pays de l'Adour - E2S UPPA, Pau, France;

[3] Laboratory for Integrative Biodiversity Research (LIBRe), Finnish Museum of Natural History Luomus, University of Helsinki, Helsinki, Finland;

[4] Laboratório de Sistemas Informáticos de Grande Escala, Faculdade de Ciências, Universidade de Lisboa, Lisbon, Portugal;

[5] Molecular Ecology Group (MEG), Water Research Institute, National Research Council, Verbania Pallanza, Italy;

[6] Molecular and Environmental Centre - Centre of Molecular and Environmental Biology, Department of Biology, University of Minho, Braga, Portugal;

[7] cE3c – Centre for Ecology, Evolution and Environmental Changes/Azorean Biodiversity Group, Departamento de Ciências Agrárias, Universidade dos Açores, Angra do Heroísmo, Portugal;

关键词: artificial intelligence;    ecological complexity;    evolutionary computation;    genetic programming;    species richness estimation;    species-area relationship;   

DOI  :  10.3389/fevo.2020.530135

来源: DOAJ

【 摘 要 】

Ecological systems are the quintessential complex systems, involving numerous high-order interactions and non-linear relationships. The most used statistical modeling techniques can hardly accommodate the complexity of ecological patterns and processes. Finding hidden relationships in complex data is now possible using massive computational power, particularly by means of artificial intelligence and machine learning methods. Here we explored the potential of symbolic regression (SR), commonly used in other areas, in the field of ecology. Symbolic regression searches for both the formal structure of equations and the fitting parameters simultaneously, hence providing the required flexibility to characterize complex ecological systems. Although the method here presented is automated, it is part of a collaborative human–machine effort and we demonstrate ways to do it. First, we test the robustness of SR to extreme levels of noise when searching for the species-area relationship. Second, we demonstrate how SR can model species richness and spatial distributions. Third, we illustrate how SR can be used to find general models in ecology, namely new formulas for species richness estimators and the general dynamic model of oceanic island biogeography. We propose that evolving free-form equations purely from data, often without prior human inference or hypotheses, may represent a very powerful tool for ecologists and biogeographers to become aware of hidden relationships and suggest general theoretical models and principles.

【 授权许可】

Unknown