A Bayesian Neural ODE for a Lettuce Greenhouse

TL;DR

This paper introduces a Bayesian Neural ODE approach for modeling lettuce greenhouse systems, effectively capturing nonlinear dynamics and quantifying uncertainty in environmental and growth predictions.

Contribution

It presents a novel sparse Bayesian deep learning method that combines Neural ODEs with Bayesian inference for greenhouse system identification.

Findings

Model accurately captures greenhouse nonlinear behavior

Provides probabilistic estimates of environmental variables

Quantifies uncertainty in lettuce growth predictions

Abstract

Greenhouse production systems play a crucial role in modern agriculture, enabling year-round cultivation of crops by providing a controlled environment. However, effectively quantifying uncertainty in modeling greenhouse systems remains a challenging task. In this paper, we apply a novel approach based on sparse Bayesian deep learning for the system identification of lettuce greenhouse models. The method leverages the power of deep neural networks while incorporating Bayesian inference to quantify the uncertainty in the weights of a Neural ODE. The simulation results show that the generated model can capture the intrinsic nonlinear behavior of the greenhouse system with probabilistic estimates of environmental variables and lettuce growth within the greenhouse.