Data-Driven Optimization Method for Recurrent Neural Network Algorithm: Greenhouse Internal Temperature Prediction Model

We developed an internal environment prediction model for smart greenhouses using machine learning models. Machine learning models were developed by finding certain rules based on the data obtained from the target system and have the advantage of learning various characteristics that are difficult t...

Full description

Saved in:
Bibliographic Details
Main Authors: Kwang Cheol Oh, Sunyong Park, Seok Jun Kim, La Hoon Cho, Chung Geon Lee, Dae Hyun Kim
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Agronomy
Subjects:
Online Access:https://www.mdpi.com/2073-4395/14/11/2545
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850217006210482176
author Kwang Cheol Oh
Sunyong Park
Seok Jun Kim
La Hoon Cho
Chung Geon Lee
Dae Hyun Kim
author_facet Kwang Cheol Oh
Sunyong Park
Seok Jun Kim
La Hoon Cho
Chung Geon Lee
Dae Hyun Kim
author_sort Kwang Cheol Oh
collection DOAJ
description We developed an internal environment prediction model for smart greenhouses using machine learning models. Machine learning models were developed by finding certain rules based on the data obtained from the target system and have the advantage of learning various characteristics that are difficult to define theoretically. However, the model accuracy and precision can change according to the model structure (hyperparameters, algorithms, epoch) and data characteristics. In this study, the analysis was performed according to the collected weather data characteristics. The model performance was low when the amount of training data was obtained over less than three days (4320 ea). The model performance improved with an increase in the amount of training data. Model performance stabilized when the training data volume exceeded seven days (10,080 ea). The optimal amount of data was determined to be between three and seven days, with an average model r<sup>2</sup> of 0.8811 and an RMSE of 2.056 for the gated recurrent unit algorithm. This study verified the possibility of developing a predictive model for the internal environment of a greenhouse based on weather data from outside. This study is limited to a specific target greenhouse, and further analysis of data from various greenhouses and climates is necessary to achieve global optimization.
format Article
id doaj-art-8a9ac40ed47b4ceaa12b02dab62fdff0
institution OA Journals
issn 2073-4395
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Agronomy
spelling doaj-art-8a9ac40ed47b4ceaa12b02dab62fdff02025-08-20T02:08:11ZengMDPI AGAgronomy2073-43952024-10-011411254510.3390/agronomy14112545Data-Driven Optimization Method for Recurrent Neural Network Algorithm: Greenhouse Internal Temperature Prediction ModelKwang Cheol Oh0Sunyong Park1Seok Jun Kim2La Hoon Cho3Chung Geon Lee4Dae Hyun Kim5Agriculture and Life Science Research Institute, Kangwon National University, Hyoja 2 Dong 192-1, Chuncheon-si 24341, Republic of KoreaAgriculture and Life Science Research Institute, Kangwon National University, Hyoja 2 Dong 192-1, Chuncheon-si 24341, Republic of KoreaDepartment of Interdisciplinary Program in Smart Agriculture, Kangwon National University, Hyoja 2 Dong 192-1, Chuncheon-si 24341, Republic of KoreaDepartment of Interdisciplinary Program in Smart Agriculture, Kangwon National University, Hyoja 2 Dong 192-1, Chuncheon-si 24341, Republic of KoreaNational Academy of Agricultural Science, Rural Development Administration, Jeonju 54874, Republic of KoreaAgriculture and Life Science Research Institute, Kangwon National University, Hyoja 2 Dong 192-1, Chuncheon-si 24341, Republic of KoreaWe developed an internal environment prediction model for smart greenhouses using machine learning models. Machine learning models were developed by finding certain rules based on the data obtained from the target system and have the advantage of learning various characteristics that are difficult to define theoretically. However, the model accuracy and precision can change according to the model structure (hyperparameters, algorithms, epoch) and data characteristics. In this study, the analysis was performed according to the collected weather data characteristics. The model performance was low when the amount of training data was obtained over less than three days (4320 ea). The model performance improved with an increase in the amount of training data. Model performance stabilized when the training data volume exceeded seven days (10,080 ea). The optimal amount of data was determined to be between three and seven days, with an average model r<sup>2</sup> of 0.8811 and an RMSE of 2.056 for the gated recurrent unit algorithm. This study verified the possibility of developing a predictive model for the internal environment of a greenhouse based on weather data from outside. This study is limited to a specific target greenhouse, and further analysis of data from various greenhouses and climates is necessary to achieve global optimization.https://www.mdpi.com/2073-4395/14/11/2545smart greenhouseartificial intelligence modelmachine learningdata characteristics
spellingShingle Kwang Cheol Oh
Sunyong Park
Seok Jun Kim
La Hoon Cho
Chung Geon Lee
Dae Hyun Kim
Data-Driven Optimization Method for Recurrent Neural Network Algorithm: Greenhouse Internal Temperature Prediction Model
Agronomy
smart greenhouse
artificial intelligence model
machine learning
data characteristics
title Data-Driven Optimization Method for Recurrent Neural Network Algorithm: Greenhouse Internal Temperature Prediction Model
title_full Data-Driven Optimization Method for Recurrent Neural Network Algorithm: Greenhouse Internal Temperature Prediction Model
title_fullStr Data-Driven Optimization Method for Recurrent Neural Network Algorithm: Greenhouse Internal Temperature Prediction Model
title_full_unstemmed Data-Driven Optimization Method for Recurrent Neural Network Algorithm: Greenhouse Internal Temperature Prediction Model
title_short Data-Driven Optimization Method for Recurrent Neural Network Algorithm: Greenhouse Internal Temperature Prediction Model
title_sort data driven optimization method for recurrent neural network algorithm greenhouse internal temperature prediction model
topic smart greenhouse
artificial intelligence model
machine learning
data characteristics
url https://www.mdpi.com/2073-4395/14/11/2545
work_keys_str_mv AT kwangcheoloh datadrivenoptimizationmethodforrecurrentneuralnetworkalgorithmgreenhouseinternaltemperaturepredictionmodel
AT sunyongpark datadrivenoptimizationmethodforrecurrentneuralnetworkalgorithmgreenhouseinternaltemperaturepredictionmodel
AT seokjunkim datadrivenoptimizationmethodforrecurrentneuralnetworkalgorithmgreenhouseinternaltemperaturepredictionmodel
AT lahooncho datadrivenoptimizationmethodforrecurrentneuralnetworkalgorithmgreenhouseinternaltemperaturepredictionmodel
AT chunggeonlee datadrivenoptimizationmethodforrecurrentneuralnetworkalgorithmgreenhouseinternaltemperaturepredictionmodel
AT daehyunkim datadrivenoptimizationmethodforrecurrentneuralnetworkalgorithmgreenhouseinternaltemperaturepredictionmodel