Estimation of Greenhouse Tomato Foliage Temperature Using DNN and ML Models
Since leaf temperature (LT) is not a trivial measurement, deep-neural networks (DNN) and machine learning (ML) models were evaluated in this study as tools for estimating foliage temperature. Two DNN methods were used. The first DNN used convolutional layers, while the second DNN was based on fully-...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-07-01
|
Series: | Agriculture |
Subjects: | |
Online Access: | https://www.mdpi.com/2077-0472/12/7/1034 |
_version_ | 1797433937556930560 |
---|---|
author | Roei Grimberg Meir Teitel Shay Ozer Asher Levi Avi Levy |
author_facet | Roei Grimberg Meir Teitel Shay Ozer Asher Levi Avi Levy |
author_sort | Roei Grimberg |
collection | DOAJ |
description | Since leaf temperature (LT) is not a trivial measurement, deep-neural networks (DNN) and machine learning (ML) models were evaluated in this study as tools for estimating foliage temperature. Two DNN methods were used. The first DNN used convolutional layers, while the second DNN was based on fully-connected layers and was trained by cross-validation techniques. The machine learning used the K-nearest neighbors (KNN) method for LT estimation. All models used the meteorological and microclimatic parameters (hereafter referred to as features) of the examined greenhouses to determine the average foliage temperature. The models were trained on 75% of the collected data and tested on the remaining 25%. RMS and absolute error were used to evaluate the performance of the different models compared to the LT values measured by a thermal camera. In addition, after finding the correlation of each feature to the leaf temperature, the models were trained based on the high-correlated features only. The machine learning model was superior to DNN when all available features were used and when only high-correlated features were used, resulting in errors of 0.7 °C and 0.8 °C, respectively. |
first_indexed | 2024-03-09T10:24:00Z |
format | Article |
id | doaj.art-47accd18a3e64a6fb748a25e3f5eea7d |
institution | Directory Open Access Journal |
issn | 2077-0472 |
language | English |
last_indexed | 2024-03-09T10:24:00Z |
publishDate | 2022-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Agriculture |
spelling | doaj.art-47accd18a3e64a6fb748a25e3f5eea7d2023-12-01T21:46:01ZengMDPI AGAgriculture2077-04722022-07-01127103410.3390/agriculture12071034Estimation of Greenhouse Tomato Foliage Temperature Using DNN and ML ModelsRoei Grimberg0Meir Teitel1Shay Ozer2Asher Levi3Avi Levy4Institute of Agricultural Engineering, Agricultural Research Organisation, Volcani Center, HaMaccabim Road 68, P.O. Box 15159, Rishon LeZion 7505101, IsraelInstitute of Agricultural Engineering, Agricultural Research Organisation, Volcani Center, HaMaccabim Road 68, P.O. Box 15159, Rishon LeZion 7505101, IsraelInstitute of Agricultural Engineering, Agricultural Research Organisation, Volcani Center, HaMaccabim Road 68, P.O. Box 15159, Rishon LeZion 7505101, IsraelInstitute of Agricultural Engineering, Agricultural Research Organisation, Volcani Center, HaMaccabim Road 68, P.O. Box 15159, Rishon LeZion 7505101, IsraelDepartment of Mechanical Engineering, Ben-Gurion University of the Negev, P.O. Box 653, Beer-Sheva 8410501, IsraelSince leaf temperature (LT) is not a trivial measurement, deep-neural networks (DNN) and machine learning (ML) models were evaluated in this study as tools for estimating foliage temperature. Two DNN methods were used. The first DNN used convolutional layers, while the second DNN was based on fully-connected layers and was trained by cross-validation techniques. The machine learning used the K-nearest neighbors (KNN) method for LT estimation. All models used the meteorological and microclimatic parameters (hereafter referred to as features) of the examined greenhouses to determine the average foliage temperature. The models were trained on 75% of the collected data and tested on the remaining 25%. RMS and absolute error were used to evaluate the performance of the different models compared to the LT values measured by a thermal camera. In addition, after finding the correlation of each feature to the leaf temperature, the models were trained based on the high-correlated features only. The machine learning model was superior to DNN when all available features were used and when only high-correlated features were used, resulting in errors of 0.7 °C and 0.8 °C, respectively.https://www.mdpi.com/2077-0472/12/7/1034leaf temperatureremote sensingdeep-learningmachine learninggreenhouse |
spellingShingle | Roei Grimberg Meir Teitel Shay Ozer Asher Levi Avi Levy Estimation of Greenhouse Tomato Foliage Temperature Using DNN and ML Models Agriculture leaf temperature remote sensing deep-learning machine learning greenhouse |
title | Estimation of Greenhouse Tomato Foliage Temperature Using DNN and ML Models |
title_full | Estimation of Greenhouse Tomato Foliage Temperature Using DNN and ML Models |
title_fullStr | Estimation of Greenhouse Tomato Foliage Temperature Using DNN and ML Models |
title_full_unstemmed | Estimation of Greenhouse Tomato Foliage Temperature Using DNN and ML Models |
title_short | Estimation of Greenhouse Tomato Foliage Temperature Using DNN and ML Models |
title_sort | estimation of greenhouse tomato foliage temperature using dnn and ml models |
topic | leaf temperature remote sensing deep-learning machine learning greenhouse |
url | https://www.mdpi.com/2077-0472/12/7/1034 |
work_keys_str_mv | AT roeigrimberg estimationofgreenhousetomatofoliagetemperatureusingdnnandmlmodels AT meirteitel estimationofgreenhousetomatofoliagetemperatureusingdnnandmlmodels AT shayozer estimationofgreenhousetomatofoliagetemperatureusingdnnandmlmodels AT asherlevi estimationofgreenhousetomatofoliagetemperatureusingdnnandmlmodels AT avilevy estimationofgreenhousetomatofoliagetemperatureusingdnnandmlmodels |