Department of Environmental Science and Policy, University of California-Davis, Davis, CA, 95616, USA.
Department of Ecology and Evolutionary Biology, University of Michigan, Ann Arbor, MI, 48109, USA.
Sci Rep. 2023 Mar 8;13(1):3881. doi: 10.1038/s41598-023-30313-8.
As modeling tools and approaches become more advanced, ecological models are becoming more complex. Traditional sensitivity analyses can struggle to identify the nonlinearities and interactions emergent from such complexity, especially across broad swaths of parameter space. This limits understanding of the ecological mechanisms underlying model behavior. Machine learning approaches are a potential answer to this issue, given their predictive ability when applied to complex large datasets. While perceptions that machine learning is a "black box" linger, we seek to illuminate its interpretive potential in ecological modeling. To do so, we detail our process of applying random forests to complex model dynamics to produce both high predictive accuracy and elucidate the ecological mechanisms driving our predictions. Specifically, we employ an empirically rooted ontogenetically stage-structured consumer-resource simulation model. Using simulation parameters as feature inputs and simulation output as dependent variables in our random forests, we extended feature analyses into a simple graphical analysis from which we reduced model behavior to three core ecological mechanisms. These ecological mechanisms reveal the complex interactions between internal plant demography and trophic allocation driving community dynamics while preserving the predictive accuracy achieved by our random forests.
随着建模工具和方法变得更加先进，生态模型变得越来越复杂。传统的敏感性分析难以识别这种复杂性产生的非线性和相互作用，尤其是在广泛的参数空间内。这限制了对模型行为背后的生态机制的理解。鉴于机器学习方法在应用于复杂大数据集时具有预测能力，它们可能是解决这个问题的答案。虽然人们仍然认为机器学习是一个“黑盒子”，但我们试图阐明它在生态建模中的解释潜力。为此，我们详细介绍了应用随机森林来模拟复杂模型动态的过程，以产生高预测准确性并阐明驱动我们预测的生态机制。具体来说，我们使用了一个基于经验的、具有个体发生阶段结构的消费者-资源模拟模型。我们将模拟参数作为特征输入，并将模拟输出作为随机森林中的因变量，从而将特征分析扩展到一个简单的图形分析中，从中我们将模型行为简化为三个核心生态机制。这些生态机制揭示了内部植物动态和营养分配之间的复杂相互作用，从而驱动群落动态，同时保持我们的随机森林所达到的预测准确性。
