Application of Machine Learning Techniques to an Agent-Based Model of Pantoea

Abstract

Agent-based modeling (ABM) is a powerful simulation technique which describes a complex dynamic system based on its interacting constituent entities. While the flexibility of ABM enables broad application, the complexity of real-world models demands intensive computing resources and computational time; however, a metamodel may be constructed to gain insight at less computational expense. Here, we developed a model in NetLogo to describe the growth of a microbial population consisting of Pantoea. We applied 13 parameters that defined the model and actively changed seven of the parameters to modulate the evolution of the population curve in response to these changes. We efficiently performed more than 3,000 simulations using a Python wrapper, NL4Py. Upon evaluation of the correlation between the active parameters and outputs by random forest regression, we found that the parameters which define the depth of medium and glucose concentration affect the population curves significantly. Subsequently, we constructed a metamodel, a dense neural network, to predict the simulation outputs from the active parameters and found that it achieves high prediction accuracy, reaching an R2 coefficient of determination value up to 0.92. Our approach of using a combination of ABM with random forest regression and neural network reduces the number of required ABM simulations. The simplified and refined metamodels may provide insights into the complex dynamic system before their transition to more sophisticated models that run on high-performance computing systems. The ultimate goal is to build a bridge between simulation and experiment, allowing model validation by comparing the simulated data to experimental data in microbiology.

Investigating factors in indoor transmission of respiratory disease through agent‐based modeling

“…In this study, we employed an ML emulator to conduct sensitivity analysis. Emulators are useful in approximating the relationship between inputs and outputs of simulations to reduce computational intensity of sensitivity analysis (Chen et al, 2021; Ligmann‐Zielinska et al, 2020). To approximate our simulation model, we used linear, ridge, and lasso regression models to fit the results.…”

“…Sensitivity analysis is a tool for reducing model uncertainty by identifying how the variance of inputs contributes to the outcome of ABMs and discrepancies between outcomes and observed data (Kang et al, 2022;Kang & Aldstadt, 2019;Ligmann-Zielinska, 2013;Saltelli et al, 1999). In this study, we employed an ML emulator outputs of simulations to reduce computational intensity of sensitivity analysis (Chen et al, 2021;Ligmann-Zielinska et al, 2020). To approximate our simulation model, we used linear, ridge, and lasso regression models to fit the results.…”

Investigating the growth of an engineered strain of Cyanobacteria with an Agent-Based Model and a Recurrent Neural Network

“…It’s not the first time that an artificial neural network is used to build a metamodel of an ABM. For example, in [41], we showed that a fully dense neural network was capable of reproducing the ABM population curves for Pantoea . What is novel about using a metamodel based on a RNN is the fact that with such a metamodel one can reproduce ABM synthetic images of growth.…”

Exploring the Use of Artificial Intelligence in Agent-Based Modeling Applications: A Bibliometric Study

“…ABM is a powerful simulation technique that characterizes a complex dynamic system through its interacting entities [1][2][3]. While ABM provides extensive flexibility for various applications, the complexity of real-world models necessitates the intensive use of computing resources and significant computational time.…”