Predicting the Photosynthetic Rate of Chinese Brassica Using Deep Learning Methods
Water stress is a significant element impacting photosynthesis, which is one of the major physiological activities governing crop growth and development. In this study, the photosynthetic rate of <i>Brassica chinensis</i> L. var. <i>parachinensis</i> (Bailey) (referred to as...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-10-01
|
Series: | Agronomy |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-4395/11/11/2145 |
_version_ | 1797511602005606400 |
---|---|
author | Peng Gao Jiaxing Xie Mingxin Yang Ping Zhou Gaotian Liang Yufeng Chen Daozong Sun Xiongzhe Han Weixing Wang |
author_facet | Peng Gao Jiaxing Xie Mingxin Yang Ping Zhou Gaotian Liang Yufeng Chen Daozong Sun Xiongzhe Han Weixing Wang |
author_sort | Peng Gao |
collection | DOAJ |
description | Water stress is a significant element impacting photosynthesis, which is one of the major physiological activities governing crop growth and development. In this study, the photosynthetic rate of <i>Brassica chinensis</i> L. var. <i>parachinensis</i> (Bailey) (referred to as Chinese Brassica hereafter) was predicted using the deep learning method. Five sets of Chinese Brassica were created, each with a different water stress gradient. Air temperature (Ta), relative humidity (RH), canopy temperature (Tc), transpiration rate (Tr), photosynthetic rate (Pn), and photosynthetically available radiation (PAR) were measured in different growth stages. The upper limit and lower limit equations were built using the non-water-stress baseline (NWSB) and hierarchical density-based spatial clustering of applications with noise (HDBSCAN) methods. The crop water stress index (CWSI) was then calculated using these built equations. The multivariate long short-term memory (MLSTM) model was proposed to predict Pn based on CWSI and other parameters. At the same time, the support vector regression (SVR) method was applied to provide a comparison to the MSLTM model. The results show that water stress had an important effect on the growth of Chinese Brassica. The more serious the water stress, the lower the growth range (GR). The HDBSCAN method had a lower root mean square error (RMSE) in calculating CWSI. Furthermore, the CWSI had a significant effect on predicting Pn. The regression fitting between measured Pn and predicted Pn showed that the determination coefficient (R<sup>2</sup>) and RMSE were 0.899 and 0.108 μmol·m<sup>−2</sup>·s<sup>−1</sup>, respectively. In this study, we successfully developed a method for the reliable prediction of Pn in Chinese Brassica, which can serve as a useful reference for application in water saving. |
first_indexed | 2024-03-10T05:48:32Z |
format | Article |
id | doaj.art-eacea0a58ee04b8d8e8d3543d082f7ae |
institution | Directory Open Access Journal |
issn | 2073-4395 |
language | English |
last_indexed | 2024-03-10T05:48:32Z |
publishDate | 2021-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Agronomy |
spelling | doaj.art-eacea0a58ee04b8d8e8d3543d082f7ae2023-11-22T22:01:12ZengMDPI AGAgronomy2073-43952021-10-011111214510.3390/agronomy11112145Predicting the Photosynthetic Rate of Chinese Brassica Using Deep Learning MethodsPeng Gao0Jiaxing Xie1Mingxin Yang2Ping Zhou3Gaotian Liang4Yufeng Chen5Daozong Sun6Xiongzhe Han7Weixing Wang8College of Electronic Engineering, South China Agricultural University, Guangzhou 510642, ChinaCollege of Electronic Engineering, South China Agricultural University, Guangzhou 510642, ChinaCollege of Electronic Engineering, South China Agricultural University, Guangzhou 510642, ChinaCollege of Electronic Engineering, South China Agricultural University, Guangzhou 510642, ChinaCollege of Electronic Engineering, South China Agricultural University, Guangzhou 510642, ChinaCollege of Electronic Engineering, South China Agricultural University, Guangzhou 510642, ChinaCollege of Electronic Engineering, South China Agricultural University, Guangzhou 510642, ChinaDepartment of Biosystems Engineering, College of Agriculture and Life Sciences, Kangwon National University, Chuncheon 24341, KoreaCollege of Electronic Engineering, South China Agricultural University, Guangzhou 510642, ChinaWater stress is a significant element impacting photosynthesis, which is one of the major physiological activities governing crop growth and development. In this study, the photosynthetic rate of <i>Brassica chinensis</i> L. var. <i>parachinensis</i> (Bailey) (referred to as Chinese Brassica hereafter) was predicted using the deep learning method. Five sets of Chinese Brassica were created, each with a different water stress gradient. Air temperature (Ta), relative humidity (RH), canopy temperature (Tc), transpiration rate (Tr), photosynthetic rate (Pn), and photosynthetically available radiation (PAR) were measured in different growth stages. The upper limit and lower limit equations were built using the non-water-stress baseline (NWSB) and hierarchical density-based spatial clustering of applications with noise (HDBSCAN) methods. The crop water stress index (CWSI) was then calculated using these built equations. The multivariate long short-term memory (MLSTM) model was proposed to predict Pn based on CWSI and other parameters. At the same time, the support vector regression (SVR) method was applied to provide a comparison to the MSLTM model. The results show that water stress had an important effect on the growth of Chinese Brassica. The more serious the water stress, the lower the growth range (GR). The HDBSCAN method had a lower root mean square error (RMSE) in calculating CWSI. Furthermore, the CWSI had a significant effect on predicting Pn. The regression fitting between measured Pn and predicted Pn showed that the determination coefficient (R<sup>2</sup>) and RMSE were 0.899 and 0.108 μmol·m<sup>−2</sup>·s<sup>−1</sup>, respectively. In this study, we successfully developed a method for the reliable prediction of Pn in Chinese Brassica, which can serve as a useful reference for application in water saving.https://www.mdpi.com/2073-4395/11/11/2145photosynthesisChinese BrassicaLSTMCWSIclusteringdeep learning |
spellingShingle | Peng Gao Jiaxing Xie Mingxin Yang Ping Zhou Gaotian Liang Yufeng Chen Daozong Sun Xiongzhe Han Weixing Wang Predicting the Photosynthetic Rate of Chinese Brassica Using Deep Learning Methods Agronomy photosynthesis Chinese Brassica LSTM CWSI clustering deep learning |
title | Predicting the Photosynthetic Rate of Chinese Brassica Using Deep Learning Methods |
title_full | Predicting the Photosynthetic Rate of Chinese Brassica Using Deep Learning Methods |
title_fullStr | Predicting the Photosynthetic Rate of Chinese Brassica Using Deep Learning Methods |
title_full_unstemmed | Predicting the Photosynthetic Rate of Chinese Brassica Using Deep Learning Methods |
title_short | Predicting the Photosynthetic Rate of Chinese Brassica Using Deep Learning Methods |
title_sort | predicting the photosynthetic rate of chinese brassica using deep learning methods |
topic | photosynthesis Chinese Brassica LSTM CWSI clustering deep learning |
url | https://www.mdpi.com/2073-4395/11/11/2145 |
work_keys_str_mv | AT penggao predictingthephotosyntheticrateofchinesebrassicausingdeeplearningmethods AT jiaxingxie predictingthephotosyntheticrateofchinesebrassicausingdeeplearningmethods AT mingxinyang predictingthephotosyntheticrateofchinesebrassicausingdeeplearningmethods AT pingzhou predictingthephotosyntheticrateofchinesebrassicausingdeeplearningmethods AT gaotianliang predictingthephotosyntheticrateofchinesebrassicausingdeeplearningmethods AT yufengchen predictingthephotosyntheticrateofchinesebrassicausingdeeplearningmethods AT daozongsun predictingthephotosyntheticrateofchinesebrassicausingdeeplearningmethods AT xiongzhehan predictingthephotosyntheticrateofchinesebrassicausingdeeplearningmethods AT weixingwang predictingthephotosyntheticrateofchinesebrassicausingdeeplearningmethods |