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.
26 27 1. Ecological systems are the quintessential complex systems, involving numerous high-28 order interactions and non-linear relationships. The most commonly used statistical 29 modelling techniques can hardly reflect the complexity of ecological patterns and 30 processes. Finding hidden relationships in complex data is now possible through the use 31 of massive computational power, particularly by means of Artificial Intelligence 32 methods, such as evolutionary computation. 33 2. Here we use symbolic regression (SR), which searches for both the formal structure of 34 equations and the fitting parameters simultaneously, hence providing the required 35 flexibility to characterize complex ecological systems. 36 3. First, we demonstrate how SR can deal with complex datasets for: 1) modelling species 37 richness; and 2) modelling species spatial distributions. Second, we illustrate how SR can 38 be used to find general models in ecology, by using it to: 3) develop species richness 39 estimators; and 4) develop the species-area relationship and the general dynamic model 40 of oceanic island biogeography.41 4. All the examples suggest that evolving free-form equations purely from data, often 42 without prior human inference or hypotheses, may represent a very powerful tool for 43 ecologists and biogeographers to become aware of hidden relationships and suggest 44 general theoretical models and principles. 45 46 3
Recently, efforts have been made to add programming activities to the curriculum that promote computational thinking and foster 21st-century digital skills. One of the programming modalities is the use of Tangible Programming Languages (TPL), used in activities with 4+ year old children. In this review, we analyze solutions proposed for TPL in different contexts crossing them with non-TPL solutions, like Graphical Programming Languages (GPL). We start to characterize features of language interaction, their use, and what learning activities are associated with them. Then, in a diagram, we show a relation between the complexity of the languages with factors such as target age and output device types. We provide an analysis considering the type of input (e.g., TPL versus GPL) and output devices (e.g., physical robot versus graphical simulation) and evaluate their contribution to further insights about the general trends with respect to educational robotic systems. Finally, we discuss the opportunities to extend and improve TPLs based on the different solutions identified.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.