A Bayesian Neural ODE for a Lettuce Greenhouse

Sjoerd Boersma*, Xiaodong Cheng*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference paperAcademicpeer-review

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.

Original languageEnglish
Title of host publication2024 IEEE Conference on Control Technology and Applications, CCTA 2024
PublisherIEEE
Pages782-786
Number of pages5
ISBN (Electronic)9798350370942
ISBN (Print)9798350370959
DOIs
Publication statusPublished - 11 Sept 2024
Event2024 IEEE Conference on Control Technology and Applications, CCTA 2024 - Newcastle upon Tyne, United Kingdom
Duration: 21 Aug 202423 Aug 2024

Publication series

Name2024 IEEE Conference on Control Technology and Applications, CCTA 2024
ISSN (Print)2768-0762
ISSN (Electronic)2768-0770

Conference/symposium

Conference/symposium2024 IEEE Conference on Control Technology and Applications, CCTA 2024
Country/TerritoryUnited Kingdom
CityNewcastle upon Tyne
Period21/08/2423/08/24

Fingerprint

Dive into the research topics of 'A Bayesian Neural ODE for a Lettuce Greenhouse'. Together they form a unique fingerprint.

Cite this