Estimation of rice seedling growth traits with an end-to-end multi-objective deep learning framework
In recent years, rice seedling raising factories have gradually been promoted in China. The seedlings bred in the factory need to be selected manually and then transplanted to the field. Growth-related traits such as height and biomass are important indicators for quantifying the growth of rice seed...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-06-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2023.1165552/full |
| _version_ | 1797813617940234240 |
|---|---|
| author | Ziran Ye Xiangfeng Tan Mengdi Dai Yue Lin Xuting Chen Pengcheng Nie Yunjie Ruan Yunjie Ruan Dedong Kong |
| author_facet | Ziran Ye Xiangfeng Tan Mengdi Dai Yue Lin Xuting Chen Pengcheng Nie Yunjie Ruan Yunjie Ruan Dedong Kong |
| author_sort | Ziran Ye |
| collection | DOAJ |
| description | In recent years, rice seedling raising factories have gradually been promoted in China. The seedlings bred in the factory need to be selected manually and then transplanted to the field. Growth-related traits such as height and biomass are important indicators for quantifying the growth of rice seedlings. Nowadays, the development of image-based plant phenotyping has received increasing attention, however, there is still room for improvement in plant phenotyping methods to meet the demand for rapid, robust and low-cost extraction of phenotypic measurements from images in environmentally-controlled plant factories. In this study, a method based on convolutional neural networks (CNNs) and digital images was applied to estimate the growth of rice seedlings in a controlled environment. Specifically, an end-to-end framework consisting of hybrid CNNs took color images, scaling factor and image acquisition distance as input and directly predicted the shoot height (SH) and shoot fresh weight (SFW) after image segmentation. The results on the rice seedlings dataset collected by different optical sensors demonstrated that the proposed model outperformed compared random forest (RF) and regression CNN models (RCNN). The model achieved R2 values of 0.980 and 0.717, and normalized root mean square error (NRMSE) values of 2.64% and 17.23%, respectively. The hybrid CNNs method can learn the relationship between digital images and seedling growth traits, promising to provide a convenient and flexible estimation tool for the non-destructive monitoring of seedling growth in controlled environments. |
| first_indexed | 2024-03-13T07:55:27Z |
| format | Article |
| id | doaj.art-c4110f041d3048eaa60454d12621e385 |
| institution | Directory Open Access Journal |
| issn | 1664-462X |
| language | English |
| last_indexed | 2024-03-13T07:55:27Z |
| publishDate | 2023-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj.art-c4110f041d3048eaa60454d12621e3852023-06-02T05:56:32ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2023-06-011410.3389/fpls.2023.11655521165552Estimation of rice seedling growth traits with an end-to-end multi-objective deep learning frameworkZiran Ye0Xiangfeng Tan1Mengdi Dai2Yue Lin3Xuting Chen4Pengcheng Nie5Yunjie Ruan6Yunjie Ruan7Dedong Kong8Institute of Digital Agriculture, Zhejiang Academy of Agricultural Sciences, Hangzhou, ChinaInstitute of Digital Agriculture, Zhejiang Academy of Agricultural Sciences, Hangzhou, ChinaInstitute of Digital Agriculture, Zhejiang Academy of Agricultural Sciences, Hangzhou, ChinaInstitute of Spatial Information for City Brain (ISICA), Hangzhou City University, Hangzhou, ChinaInstitute of Digital Agriculture, Zhejiang Academy of Agricultural Sciences, Hangzhou, ChinaInstitute of Agricultural Bio-Environmental Engineering, College of Bio-systems Engineering and Food Science, Zhejiang University, Hangzhou, ChinaInstitute of Agricultural Bio-Environmental Engineering, College of Bio-systems Engineering and Food Science, Zhejiang University, Hangzhou, ChinaAcademy of Rural Development, Zhejiang University, Hangzhou, ChinaInstitute of Digital Agriculture, Zhejiang Academy of Agricultural Sciences, Hangzhou, ChinaIn recent years, rice seedling raising factories have gradually been promoted in China. The seedlings bred in the factory need to be selected manually and then transplanted to the field. Growth-related traits such as height and biomass are important indicators for quantifying the growth of rice seedlings. Nowadays, the development of image-based plant phenotyping has received increasing attention, however, there is still room for improvement in plant phenotyping methods to meet the demand for rapid, robust and low-cost extraction of phenotypic measurements from images in environmentally-controlled plant factories. In this study, a method based on convolutional neural networks (CNNs) and digital images was applied to estimate the growth of rice seedlings in a controlled environment. Specifically, an end-to-end framework consisting of hybrid CNNs took color images, scaling factor and image acquisition distance as input and directly predicted the shoot height (SH) and shoot fresh weight (SFW) after image segmentation. The results on the rice seedlings dataset collected by different optical sensors demonstrated that the proposed model outperformed compared random forest (RF) and regression CNN models (RCNN). The model achieved R2 values of 0.980 and 0.717, and normalized root mean square error (NRMSE) values of 2.64% and 17.23%, respectively. The hybrid CNNs method can learn the relationship between digital images and seedling growth traits, promising to provide a convenient and flexible estimation tool for the non-destructive monitoring of seedling growth in controlled environments.https://www.frontiersin.org/articles/10.3389/fpls.2023.1165552/fullgrowth traitsfresh weightrice seedlingdeep learningconvolution neural network |
| spellingShingle | Ziran Ye Xiangfeng Tan Mengdi Dai Yue Lin Xuting Chen Pengcheng Nie Yunjie Ruan Yunjie Ruan Dedong Kong Estimation of rice seedling growth traits with an end-to-end multi-objective deep learning framework Frontiers in Plant Science growth traits fresh weight rice seedling deep learning convolution neural network |
| title | Estimation of rice seedling growth traits with an end-to-end multi-objective deep learning framework |
| title_full | Estimation of rice seedling growth traits with an end-to-end multi-objective deep learning framework |
| title_fullStr | Estimation of rice seedling growth traits with an end-to-end multi-objective deep learning framework |
| title_full_unstemmed | Estimation of rice seedling growth traits with an end-to-end multi-objective deep learning framework |
| title_short | Estimation of rice seedling growth traits with an end-to-end multi-objective deep learning framework |
| title_sort | estimation of rice seedling growth traits with an end to end multi objective deep learning framework |
| topic | growth traits fresh weight rice seedling deep learning convolution neural network |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2023.1165552/full |
| work_keys_str_mv | AT ziranye estimationofriceseedlinggrowthtraitswithanendtoendmultiobjectivedeeplearningframework AT xiangfengtan estimationofriceseedlinggrowthtraitswithanendtoendmultiobjectivedeeplearningframework AT mengdidai estimationofriceseedlinggrowthtraitswithanendtoendmultiobjectivedeeplearningframework AT yuelin estimationofriceseedlinggrowthtraitswithanendtoendmultiobjectivedeeplearningframework AT xutingchen estimationofriceseedlinggrowthtraitswithanendtoendmultiobjectivedeeplearningframework AT pengchengnie estimationofriceseedlinggrowthtraitswithanendtoendmultiobjectivedeeplearningframework AT yunjieruan estimationofriceseedlinggrowthtraitswithanendtoendmultiobjectivedeeplearningframework AT yunjieruan estimationofriceseedlinggrowthtraitswithanendtoendmultiobjectivedeeplearningframework AT dedongkong estimationofriceseedlinggrowthtraitswithanendtoendmultiobjectivedeeplearningframework |