Depending on the amount of data to process, file generation may take longer.

If it takes too long to generate, you can limit the data by, for example, reducing the range of years.

Article

Download BibTeX

Title

Plant production yield optimization and cost-effectiveness using an innovative artificial multiple intelligence system

Authors

[ 1 ] Instytut Logistyki, Wydział Inżynierii Zarządzania, Politechnika Poznańska | [ P ] employee

Scientific discipline (Law 2.0)

[6.6] Management and quality studies

Year of publication

2024

Published in

Annals of Operations Research

Journal year: 2024 | Journal volume: vol. 2024

Article type

scientific article

Publication language

english

Keywords
EN
  • Plant production yield optimization
  • D-optimal design
  • Multiple regression model
  • Artificial multiple intelligence system (AMIS)
Abstract

EN Contingent upon the establishment of optimal cultivation conditions, particularly in the realm of hydroponics greenhouses. Here, the failure to meticulously regulate environmental parameters may precipitate escalated production expenditures. Our research is primarily focused on the optimization of plant growth parameters, with the objective of maximizing production yield whilst concurrently minimizing associated costs, thereby constituting a multi-objective problem (MOP). Central to our investigation is the identification of optimal values for key growth parameters, encompassing carbon dioxide (CO2) concentration, light intensity (LI), duration of light exposure (DL), specific Centella Asiatica Urban (CAU) cultivars or strains (SC), and the balanced distribution of different light spectra within the growth environment (RL).To achieve our objectives,we have develop a newhybrid approach combining statistical methods and metaheuristics is proposed to solve the MOP.We integrate a D-optimal design, multiple regression, and an innovative artificial multiple intelligence system (AMIS). This study, makes a significant contribution to the theory and practice by introducing a comprehensive and species-specific cultivation model, using as an example CAU.Through rigorous comparative analysis, the advantage of theAMIS algorithm over genetic algorithms (GA) and differential evolution algorithms (DE) is evident, resulting in substantial yield improvements. Our findings demonstrate an enhancement of 14.27%, 5.24%, 4.41% and 5.11%concerning real experiments, design-expert prediction (DEP),DE, and GA, respectively. Additionally, the implementation of AMIS facilitates significant cost reductions, boasting savings of 8.63%, 5.28%, 4.23%, and 4.05% compared to the real experiment, DEP, DE, and GA, respectively.

Date of online publication

21.02.2024

Pages (from - to)

1 - 36

DOI

10.1007/s10479-024-05835-7

URL

https://doi.org/10.1007/s10479-024-05835-7

Ministry points / journal

70

Impact Factor

4,8 [List 2022]

This website uses cookies to remember the authenticated session of the user. For more information, read about Cookies and Privacy Policy.