A Soft Sensor to Estimate the Opening of Greenhouse Vents Based on an LSTM-RNN Neural Network
In greenhouses, sensors are needed to measure the variables of interest. They help farmers and allow automatic controllers to determine control actions to regulate the environmental conditions that favor crop growth. This paper focuses on the problem of the lack of monitoring and control systems in...
| Main Authors: | , , , |
|---|---|
| Format: | info:eu-repo/semantics/article |
| Language: | English |
| Published: |
MDPI
2023
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10835/14179 |
| _version_ | 1789406489382748160 |
|---|---|
| author | Guesbaya, Mounir García Mañas, Francisco Rodríguez Díaz, Francisco De Asís Megherbi, Hassina |
| author_facet | Guesbaya, Mounir García Mañas, Francisco Rodríguez Díaz, Francisco De Asís Megherbi, Hassina |
| author_sort | Guesbaya, Mounir |
| collection | DSpace |
| description | In greenhouses, sensors are needed to measure the variables of interest. They help farmers and allow automatic controllers to determine control actions to regulate the environmental conditions that favor crop growth. This paper focuses on the problem of the lack of monitoring and control systems in traditional Mediterranean greenhouses. In such greenhouses, most farmers manually operate the opening of the vents to regulate the temperature during the daytime. Therefore, the state of vent opening is not recorded because control systems are not usually installed due to economic reasons. The solution presented in this paper consists of developing a Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) as a soft sensor to estimate vent opening using the measurements of different inside and outside greenhouse climate variables as input data. A dataset from a traditional greenhouse located in Almería (Spain) was used. The data were processed and analyzed to study the relationships between the measured climate variables and the state of vent opening, both statistically (using correlation coefficients) and graphically (with regression analysis). The dataset (with 81 recorded days) was then used to train, validate, and test a set of candidate LSTM-based networks for the soft sensor. The results show that the developed soft sensor can estimate the actual opening of the vents with a mean absolute error of 4.45%, which encourages integrating the soft sensor as part of decision support systems for farmers and using it to calculate other essential variables, such as greenhouse ventilation rate. |
| format | info:eu-repo/semantics/article |
| id | oai:repositorio.ual.es:10835-14179 |
| institution | Universidad de Cuenca |
| language | English |
| publishDate | 2023 |
| publisher | MDPI |
| record_format | dspace |
| spelling | oai:repositorio.ual.es:10835-141792023-04-12T19:25:52Z A Soft Sensor to Estimate the Opening of Greenhouse Vents Based on an LSTM-RNN Neural Network Guesbaya, Mounir García Mañas, Francisco Rodríguez Díaz, Francisco De Asís Megherbi, Hassina protected agriculture greenhouse ventilation machine learning long short-term memory virtual sensor climate modeling In greenhouses, sensors are needed to measure the variables of interest. They help farmers and allow automatic controllers to determine control actions to regulate the environmental conditions that favor crop growth. This paper focuses on the problem of the lack of monitoring and control systems in traditional Mediterranean greenhouses. In such greenhouses, most farmers manually operate the opening of the vents to regulate the temperature during the daytime. Therefore, the state of vent opening is not recorded because control systems are not usually installed due to economic reasons. The solution presented in this paper consists of developing a Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) as a soft sensor to estimate vent opening using the measurements of different inside and outside greenhouse climate variables as input data. A dataset from a traditional greenhouse located in Almería (Spain) was used. The data were processed and analyzed to study the relationships between the measured climate variables and the state of vent opening, both statistically (using correlation coefficients) and graphically (with regression analysis). The dataset (with 81 recorded days) was then used to train, validate, and test a set of candidate LSTM-based networks for the soft sensor. The results show that the developed soft sensor can estimate the actual opening of the vents with a mean absolute error of 4.45%, which encourages integrating the soft sensor as part of decision support systems for farmers and using it to calculate other essential variables, such as greenhouse ventilation rate. 2023-01-25T18:20:04Z 2023-01-25T18:20:04Z 2023-01-21 info:eu-repo/semantics/article 1424-8220 http://hdl.handle.net/10835/14179 10.3390/s23031250 en https://www.mdpi.com/1424-8220/23/3/1250 Attribution-NonCommercial-NoDerivatives 4.0 Internacional http://creativecommons.org/licenses/by-nc-nd/4.0/ info:eu-repo/semantics/openAccess MDPI |
| spellingShingle | protected agriculture greenhouse ventilation machine learning long short-term memory virtual sensor climate modeling Guesbaya, Mounir García Mañas, Francisco Rodríguez Díaz, Francisco De Asís Megherbi, Hassina A Soft Sensor to Estimate the Opening of Greenhouse Vents Based on an LSTM-RNN Neural Network |
| title | A Soft Sensor to Estimate the Opening of Greenhouse Vents Based on an LSTM-RNN Neural Network |
| title_full | A Soft Sensor to Estimate the Opening of Greenhouse Vents Based on an LSTM-RNN Neural Network |
| title_fullStr | A Soft Sensor to Estimate the Opening of Greenhouse Vents Based on an LSTM-RNN Neural Network |
| title_full_unstemmed | A Soft Sensor to Estimate the Opening of Greenhouse Vents Based on an LSTM-RNN Neural Network |
| title_short | A Soft Sensor to Estimate the Opening of Greenhouse Vents Based on an LSTM-RNN Neural Network |
| title_sort | soft sensor to estimate the opening of greenhouse vents based on an lstm-rnn neural network |
| topic | protected agriculture greenhouse ventilation machine learning long short-term memory virtual sensor climate modeling |
| url | http://hdl.handle.net/10835/14179 |
| work_keys_str_mv | AT guesbayamounir asoftsensortoestimatetheopeningofgreenhouseventsbasedonanlstmrnnneuralnetwork AT garciamanasfrancisco asoftsensortoestimatetheopeningofgreenhouseventsbasedonanlstmrnnneuralnetwork AT rodriguezdiazfranciscodeasis asoftsensortoestimatetheopeningofgreenhouseventsbasedonanlstmrnnneuralnetwork AT megherbihassina asoftsensortoestimatetheopeningofgreenhouseventsbasedonanlstmrnnneuralnetwork AT guesbayamounir softsensortoestimatetheopeningofgreenhouseventsbasedonanlstmrnnneuralnetwork AT garciamanasfrancisco softsensortoestimatetheopeningofgreenhouseventsbasedonanlstmrnnneuralnetwork AT rodriguezdiazfranciscodeasis softsensortoestimatetheopeningofgreenhouseventsbasedonanlstmrnnneuralnetwork AT megherbihassina softsensortoestimatetheopeningofgreenhouseventsbasedonanlstmrnnneuralnetwork |