Paper Overview
Field: Machine Learning Authors: Benjamin Pianet, Baptiste Lesquoy, Paul Saves, Benoit Gaudou, Jean Villerd, Nicolas Verstaevel, Olivier Therond Published: 2026-10-19 arXiv: 2610.22420
Summary
Agent-based models are well-suited for modelling agro-ecological systems for decision-making, yet turning their simulations into actionable insight requires identifying which decisions actually drive the behaviours. In such a context, sensitivity analysis stumbles upon a structural feature of many complex systems: the parameters are not a flat vector but a decision tree in which many parameters appear only when a higher-level choice activates them. Classical global sensitivity analysis presupposes independent inputs over a fixed Cartesian product and is ill-posed on such a branched space and biased by construction.
The authors instead treat the structure of the decisions as a first-class modelling object. Using advanced surrogate modelling techniques, they encode the crop-management itinerary of the high-resolution agro-ecological modelling platform MAELIA as a hierarchical design space featuring both categorical and numerical variables. They propose a novel dedicated method to analyse this kind of hierarchical space — a random-forest-supervised HSIC-ANOVA — which ranks main effects and interactions natively on the tree while placing rarely and always active decisions on an equal footing.
They show how, when applied to simulation outputs such as nitrogen leaching, soil organic carbon variation, and yield predictions, it can deliver an interpretable, decision-oriented reading.
Key Contributions
- A hierarchical design-space encoding of agent-based crop-management decisions (categorical + numerical variables)
- A novel random-forest-supervised HSIC-ANOVA method for sensitivity analysis directly on decision trees
- Demonstrated application to nitrogen leaching, soil organic carbon dynamics, and yield predictions in MAELIA
Link
Paper: https://arxiv.org/abs/2610.22420