Accurate Imputation of Greenhouse Environment Data for Data Integrity Utilizing Two-Dimensional Convolutional Neural Networks
Greenhouses require accurate and reliable data to interpret the microclimate and maximize resource use efficiency. However, greenhouse conditions are harsh for electrical sensors collecting environmental data. Convolutional neural networks (ConvNets) enable complex interpretation by multiplying the...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/6/2187 |
| _version_ | 1797540551175700480 |
|---|---|
| author | Taewon Moon Joon Woo Lee Jung Eek Son |
| author_facet | Taewon Moon Joon Woo Lee Jung Eek Son |
| author_sort | Taewon Moon |
| collection | DOAJ |
| description | Greenhouses require accurate and reliable data to interpret the microclimate and maximize resource use efficiency. However, greenhouse conditions are harsh for electrical sensors collecting environmental data. Convolutional neural networks (ConvNets) enable complex interpretation by multiplying the input data. The objective of this study was to impute missing tabular data collected from several greenhouses using a ConvNet architecture called U-Net. Various data-loss conditions with errors in individual sensors and in all sensors were assumed. The U-Net with a screen size of 50 exhibited the highest coefficient of determination values and the lowest root-mean-square errors for all environmental factors used in this study. U-Net<sub>50</sub> correctly learned the changing patterns of the greenhouse environment from the training dataset. Therefore, the U-Net architecture can be used for the imputation of tabular data in greenhouses if the model is correctly trained. Growers can secure data integrity with imputed data, which could increase crop productivity and quality in greenhouses. |
| first_indexed | 2024-03-10T13:02:48Z |
| format | Article |
| id | doaj.art-4b6f5baf0ce94939a503f1708194d4e7 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T13:02:48Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-4b6f5baf0ce94939a503f1708194d4e72023-11-21T11:20:54ZengMDPI AGSensors1424-82202021-03-01216218710.3390/s21062187Accurate Imputation of Greenhouse Environment Data for Data Integrity Utilizing Two-Dimensional Convolutional Neural NetworksTaewon Moon0Joon Woo Lee1Jung Eek Son2Department of Agriculture, Forestry and Bioresources, Seoul National University, Seoul 08826, KoreaDepartment of Smart Agriculture, Jeonju University, Jeonju 55069, KoreaDepartment of Agriculture, Forestry and Bioresources, Seoul National University, Seoul 08826, KoreaGreenhouses require accurate and reliable data to interpret the microclimate and maximize resource use efficiency. However, greenhouse conditions are harsh for electrical sensors collecting environmental data. Convolutional neural networks (ConvNets) enable complex interpretation by multiplying the input data. The objective of this study was to impute missing tabular data collected from several greenhouses using a ConvNet architecture called U-Net. Various data-loss conditions with errors in individual sensors and in all sensors were assumed. The U-Net with a screen size of 50 exhibited the highest coefficient of determination values and the lowest root-mean-square errors for all environmental factors used in this study. U-Net<sub>50</sub> correctly learned the changing patterns of the greenhouse environment from the training dataset. Therefore, the U-Net architecture can be used for the imputation of tabular data in greenhouses if the model is correctly trained. Growers can secure data integrity with imputed data, which could increase crop productivity and quality in greenhouses.https://www.mdpi.com/1424-8220/21/6/2187artificial intelligencedeep learninginterpolationmachine learningplant environment |
| spellingShingle | Taewon Moon Joon Woo Lee Jung Eek Son Accurate Imputation of Greenhouse Environment Data for Data Integrity Utilizing Two-Dimensional Convolutional Neural Networks Sensors artificial intelligence deep learning interpolation machine learning plant environment |
| title | Accurate Imputation of Greenhouse Environment Data for Data Integrity Utilizing Two-Dimensional Convolutional Neural Networks |
| title_full | Accurate Imputation of Greenhouse Environment Data for Data Integrity Utilizing Two-Dimensional Convolutional Neural Networks |
| title_fullStr | Accurate Imputation of Greenhouse Environment Data for Data Integrity Utilizing Two-Dimensional Convolutional Neural Networks |
| title_full_unstemmed | Accurate Imputation of Greenhouse Environment Data for Data Integrity Utilizing Two-Dimensional Convolutional Neural Networks |
| title_short | Accurate Imputation of Greenhouse Environment Data for Data Integrity Utilizing Two-Dimensional Convolutional Neural Networks |
| title_sort | accurate imputation of greenhouse environment data for data integrity utilizing two dimensional convolutional neural networks |
| topic | artificial intelligence deep learning interpolation machine learning plant environment |
| url | https://www.mdpi.com/1424-8220/21/6/2187 |
| work_keys_str_mv | AT taewonmoon accurateimputationofgreenhouseenvironmentdatafordataintegrityutilizingtwodimensionalconvolutionalneuralnetworks AT joonwoolee accurateimputationofgreenhouseenvironmentdatafordataintegrityutilizingtwodimensionalconvolutionalneuralnetworks AT jungeekson accurateimputationofgreenhouseenvironmentdatafordataintegrityutilizingtwodimensionalconvolutionalneuralnetworks |