Machine learning in indoor agriculture: a systematic mapping and taxonomy

Authors

  • Bruno Guilherme Martini Universidade do Vale do Rio dos Sinos (UNISINOS)
  • Jorge Luis Victória Barbosa Unisinos - Universidade do Vale do Rio dos Sinos

DOI:

https://doi.org/10.5335/rbca.v16i3.15863

Keywords:

Artificial Intelligence, Indoor Agriculture, Indoor Farming, Machine Learning

Abstract

The present article describes a systematic mapping of works related to the application ofMachine Learning in Indoor Agriculture. This research encompasses searches conducted up toMarch 2024 in the IEEE Xplore, ACM Digital Library, Springer Library, Science Direct, Scopus, MDPI,Wiley, and Taylor & Francis databases. The initial search resulted in 10,149 articles, of which 76 studies were selected for full reading after applying the inclusion and exclusion criteria. This analysis led to the selection of 36 articles that were studied with the aim of answering 9 research questions along with a taxonomy proposal. The main results reveal that the selected articles employed 43 different machine learning techniques. Additionally, it was found that no study was published before the year 2018. Twenty-six distinct pieces of information were identified from the crops, with the cultivation of 17 different crops and the use of 4 devices for information collection, among other relevant information. The analysis of the articles evidenced a clear trend in the use
of machine learning in Indoor Agriculture.

Downloads

Download data is not yet available.

Published

2024-12-03

Issue

Section

Original Paper

How to Cite

[1]
2024. Machine learning in indoor agriculture: a systematic mapping and taxonomy. Brazilian Journal of Applied Computing. 16, 3 (Dec. 2024), 10–24. DOI:https://doi.org/10.5335/rbca.v16i3.15863.