Graphical AbstractTo mechanistically understand the dynamics of complex ecosystems, Yize Chen et al. employ symbolic regression (SR), a machine learning method that automatically reverse-engineers both model structure and parameters from temporal data. SR randomly assembles candidate models, computes the model fitness, and employs mutation and crossover to build better ones. The Pareto front reflects the trade-off between complexity and fitness of candidate models. More details can be found in article number 1900069 by Yize Chen et al.

Understanding the dynamics of complex ecosystems is a necessary step to maintain and control them. Yet, reverse-engineering ecological dynamics remains challenging largely due to the very broad class of dynamics that ecosystems may take. Here, this challenge is tackled through symbolic regression, a machine learning method that automatically reverse-engineers both the model structure and parameters from temporal data. How combining symbolic regression with a “dictionary” of possible ecological functional responses opens the door to correctly reverse-engineering ecosystem dynamics, even in the (...) case of poorly informative data, is shown. This strategy is validated using both synthetic and experimental data, and it is found that this strategy is promising for the systematic modeling of complex ecological systems. (shrink)