Using machine learning as a surrogate model for agent-based simulations.
Using machine learning as a surrogate model for agent-based simulations.
复制标题
将机器学习作为基于代理的模拟的替代模型。
DOI：
10.1371/journal.pone.0263150
复制
发表时间：
2022
期刊：
影响因子：
3.7
通讯作者：
Yaneske E
中科院分区：
文献类型：
--
作者：
Angione C;Silverman E;Yaneske E
在这项概念验证工作中，我们评估了多种机器学习方法作为代理模型的性能，用于分析基于代理的模型（ABM）。分析基于代理的建模输出可能具有挑战性，因为即使在相对简单的模型中，输入参数之间的关系也可能是非线性的，甚至是混乱的，并且每个模型运行可能需要大量的CPU时间。替代模型，其中的反弹道导弹的统计模型的构建，以方便详细的模型分析，已被提出作为一种替代计算昂贵的蒙特卡罗方法。在这里，我们比较了多种机器学习方法的反弹道导弹代理建模，以确定最适合作为一个代理建模的复杂行为的反弹道导弹的方法。我们的研究结果表明，在大多数情况下，人工神经网络（ANN）和梯度提升树优于高斯过程代理，目前最常用的方法复杂的计算模型的代理建模。人工神经网络在模型运行次数较多的情况下产生了最准确的模型复制，尽管训练时间比其他方法长。我们建议基于代理的建模将受益于使用机器学习方法进行代理建模，因为这可以促进模型的更稳健的灵敏度分析，同时在校准和分析模拟时减少CPU时间消耗。
In this proof-of-concept work, we evaluate the performance of multiple machine-learning methods as surrogate models for use in the analysis of agent-based models (ABMs). Analysing agent-based modelling outputs can be challenging, as the relationships between input parameters can be non-linear or even chaotic even in relatively simple models, and each model run can require significant CPU time. Surrogate modelling, in which a statistical model of the ABM is constructed to facilitate detailed model analyses, has been proposed as an alternative to computationally costly Monte Carlo methods. Here we compare multiple machine-learning methods for ABM surrogate modelling in order to determine the approaches best suited as a surrogate for modelling the complex behaviour of ABMs. Our results suggest that, in most scenarios, artificial neural networks (ANNs) and gradient-boosted trees outperform Gaussian process surrogates, currently the most commonly used method for the surrogate modelling of complex computational models. ANNs produced the most accurate model replications in scenarios with high numbers of model runs, although training times were longer than the other methods. We propose that agent-based modelling would benefit from using machine-learning methods for surrogate modelling, as this can facilitate more robust sensitivity analyses for the models while also reducing CPU time consumption when calibrating and analysing the simulation.
登录
查看更多内容
影响因子：
5.1
作者：
Chai, T.;Draxler, R. R.
通讯作者：
Draxler, R. R.
DOI：
10.1073/pnas.2002959117
发表时间：
2020-08-04
影响因子：
11.1
作者：
Culley, Christopher;Vijayakumar, Supreeta;Angione, Claudio
通讯作者：
Angione, Claudio
影响因子：
56.9
作者：
AXELROD, R;HAMILTON, WD
通讯作者：
HAMILTON, WD
影响因子：
22.7
作者：
Lipton, Zachary C.
通讯作者：
Lipton, Zachary C.
影响因子：
4.5
作者：
Friedman, JH
通讯作者：
Friedman, JH