Yield is impacted by the environmental conditions that plants are exposed to. Controlled environmental agriculture provides growers with an opportunity to fine-tune environmental conditions for optimising yield and crop quality. However, space and time constraints will limit the number of experimental conditions that can be tested, which will, in turn, limit the resolution to which environmental conditions can be optimised. Here we present an innovative experimental approach that utilises the existing heterogeneity in light quantity and quality across a vertical farm to evaluate hundreds of environmental conditions concurrently. Using an observational study design, we identify features in light quality that are most predictive of biomass in different kinds of microgreens (kale, radish and sunflower) that may inform future iterations of lighting technology development for vertical farms.

Plants respond to stresses like drought and heat through complex gene regulatory networks (GRNs). To improve resilience, understanding these is crucial, but large-scale GRNs (>100 genes) are difficult to model using ordinary differential equations (ODEs) due to the high number of parameters that have to be estimated. Here we solve this problem by introducing BADDADAN, which uses machine learning to identify gene modules—groups of co-expressed and/or co-regulated genes—and constructs an ODE model that predicts gene module dynamics under stress. By integrating time-series gene expression data with prior co-expression data it finds modules that are both coherent and interpretable. We demonstrate BADDADAN on heat and drought datasets of A. thaliana, modelling over 1,000 genes, recovering known mechanistic insights, and proposing new hypotheses. By combining machine learning with mechanistic modelling, BADDADAN deepens our understanding of stress-related GRNs in plants and potentially other organisms.