Brian MacPherson

A machine learning approach to investigate the reasons behind species extinction

Abstract Species extinction is one of the most important phenomena in conservation biology. Many factors are involved in the disappearance of species, including stochastic population fluctuations, habitat change, resource depletion, and inbreeding. Due to the complexity of the interactions between these various factors and the lengthy time period required to make empirical observations, studying the phenomenon of species extinction can prove to be very difficult in nature. On the other hand, an investigation of the various features involved in species extinction using individual-based simulation modeling and machine learning techniques can be accomplished in a reasonably short period of time. Thus, the aim of this paper is to investigate multiple factors involved in species extinction using computer simulation modeling. We apply several machine learning techniques to the data generated by EcoSim, a predator–prey ecosystem simulation, in order to select the most prominent features involved in species extinction, along with extracting rules that outline conditions that have the potential to be used for predicting extinction. In particular, we used five feature selection methods resulting in the selection of 25 features followed by a reduction of these to 14 features using correlation analysis. Each of the remaining features was placed in one of three broad categories, viz., genetic, environmental, or demographic. The experimental results suggest that factors such as population fluctuation, reproductive age, and genetic distance are important in the occurrence of species extinction in EcoSim, similar to what is observed in nature. We argue that the study of the behavior of species through Individual-Based Modeling has the potential to give rise to new insights into the central factors involved in extinction for real ecosystems. This approach has the potential to help with the detection of early signals of species extinction that could in turn lead to conservation policies to help prevent extinction.

EcoSim, an Enhanced Artificial Ecosystem: Addressing Deeper Behavioral, Ecological, and Evolutionary Questions

This chapter discusses individual-based models (IBMs) and uses the Overview, Design concepts, and Details (ODD) protocol to describe a predator-prey evolutionary ecosystem IBM called EcoSim. EcoSim is one of the most complex and large-scale IBMs of its kind, allowing hundreds of thousands of intricate individuals to interact and evolve over thousands of time steps. Individuals in EcoSim have a behavioral model represented by a fuzzy cognitive map (FCM). The FCM, described in this chapter, is a cognitive architecture well-suited for individuals in EcoSim due to its efficiency and the complexity of decision-making it allows. Furthermore, it can be encoded as a vector of real numbers, lending itself to being part of the genetic material passed on by individuals during reproduction. This allows for meaningful evolution of their behaviors and natural selection without predefined fitness. EcoSim has been enhanced to increase the breadth and depth of the questions it can answer. New features include: fertilization of primary producers by consumers, predator-prey combat, sexual reproduction, sex-linkage of genes, multiple modes of reproduction, size-based dominance hierarchy, and more. In addition to describing EcoSim in detail, we present data from default EcoSim runs to show potential users the types of data EcoSim generates. Furthermore, we present a brief sensitivity analysis of some variables in EcoSim, and a case study that demonstrates research that can be performed using EcoSim. In the case study, we elucidate some evolutionary and behavioral impacts on animals under two conditions: when primary production is limited, and when energy expenditure is reduced.

A comparison of stable and fluctuating resources with respect to evolutionary adaptation and life-history traits using individual-based modeling and machine learning

There are three non-mutually-exclusive key strategies evolved by gene pools to cope with fluctuating food resource availability, including evolutionary adaptation, phenotypic plasticity, and migration. We focus primarily on evolutionary adaptation and behavioral plasticity, which is a type of phenotypic plasticity, resulting in life-history changes as ways of dealing with fluctuations in food resource availability. Using EcoSim, a predator-prey individual-based model, we compare individuals with stable food resources with those in environments where there are fluctuating food resources in terms of adaptation through behavioral plasticity and evolution. The purpose of our study is to determine whether evolution and behavioral plasticity truly play a role in adapting to an environment with fluctuating food resources, as well as to determine whether there are specific gene divergences between gene pools in fluctuating food resource environments versus gene pools where food resources are relatively stable. An important result of our study is that individuals in environments that are unstable with respect to food resource availability exhibited significant differences in behaviors versus those in environments with stable food resources. Although behavioral plasticity facilitates a rapid response to unstable food conditions, our study revealed the evolution of perceptual traits such as vision range in reaction to fluctuating food resources, indicating the importance of evolution in adapting to unstable resource environments in the long run. Moreover, using decision trees, we found that there were significant behavioral gene divergences between individuals in environments with fluctuating food resources as opposed to individuals in environments with stable food resources.

Exploring the connection between emergent animal personality and fitness using a novel individual-based model and decision tree approach

Abstract The connection between reproductive fitness and animal personality is not fully understood. Using computer simulations and machine learning, we found high accuracy rules that predict which personalities are associated with fitness for two correlated measures of components of fitness applied a posteriori for classificatory purposes: fitness component (1) in terms of survival and short-term reproductive success, and fitness component (2) in terms of long term reproductive success which is indirectly related to survival of the parents. Animals are represented in the abstract as individuals with a genome that through time develops into certain characteristic behaviors and personalities. To the best of our knowledge, this is the first simulation study of its kind that extracts rules to investigate the link between personality and fitness. Clearly separated behaviors between fit and non-fit individuals emerged through the evolution of the population over time without top-down processing. Moreover, we did not employ a pre-defined fitness function, in order to minimize any possible biases toward a specific type of behavior. With respect to fitness component (1), we found that individuals with one of two extreme values of a personality trait (either bold or fearful) tend to be most fit, which agrees with empirical studies. With respect to fitness component (2), we found that when resources are low, fit individuals search for food whereas if food is abundant, they focus on reproduction, thereby suggesting the context dependence of fitness related behaviors. Once again, these results agree with empirical studies.