| Title | Automated Discovery of Relationships, Models, and Principles in Ecology |
| Abstract | 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. |
| Source | Frontiers in Ecology and Evolution 8 |
| Keywords | artificial intelligenceecological complexityevolutionary computationgenetic programmingspecies distribution modelingspecies richness estimationspecies-area relationshipsymbolic regression |
| Journal | Frontiers in Ecology and Evolution |
| Editor | Frontiers Media, Lausanne, Svizzera |
| Year | 2020 |
| Type | Articolo in rivista |
| DOI | 10.3389/fevo.2020.530135 |
| Authors | Cardoso, Pedro; Branco, Vasco V.; Borges, Paulo A.V.; Carvalho, José C.; Rigal, François; Gabriel, Rosalina; Mammola, Stefano; Cascalho, José; Correia, Luís |
| Text | 442462 2020 10.3389/fevo.2020.530135 Scopus 2 s2.0 85098171529 artificial intelligence ecological complexity evolutionary computation genetic programming species distribution modeling species richness estimation species area relationship symbolic regression Automated Discovery of Relationships, Models, and Principles in Ecology Cardoso, Pedro; Branco, Vasco V.; Borges, Paulo A.V.; Carvalho, Jose C.; Rigal, François; Gabriel, Rosalina; Mammola, Stefano; Cascalho, Jose; Correia, Luis Universidade dos Açores; Universite de Pau et des Pays de L Adour; Finnish Museum of Natural History; Consiglio Nazionale delle Ricerche; Universidade do Minho; Faculdade de Ciencias, Universidade de Lisboa; Departamento de Ci ncia Agrarias 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. 8 Published version http //www.scopus.com/record/display.url eid=2 s2.0 85098171529 origin=inward Main text 2020_CARDOSO ET AL Frontiers Ecol Evol.pdf Articolo in rivista Frontiers Media 2296 701X Frontiers in Ecology and Evolution Frontiers in Ecology and Evolution Frontiers in Ecology and Evolution Front. ecol. evol. stefano.mammola MAMMOLA STEFANO |
