Estimation of rice seedling growth traits with an end-to-end multi-objective deep learning framework

Ziran Ye; Xiangfeng Tan; Mengdi Dai; Yue Lin; Xuting Chen; Pengcheng Nie; Yunjie Ruan; Dedong Kong

doi:10.3389/fpls.2023.1165552

Estimation of rice seedling growth traits with an end-to-end multi-objective deep learning framework

Front Plant Sci. 2023 Jun 2:14:1165552. doi: 10.3389/fpls.2023.1165552. eCollection 2023.

Authors

Ziran Ye¹, Xiangfeng Tan¹, Mengdi Dai¹, Yue Lin², Xuting Chen¹, Pengcheng Nie³, Yunjie Ruan^{3

4}, Dedong Kong¹

Affiliations

¹ Institute of Digital Agriculture, Zhejiang Academy of Agricultural Sciences, Hangzhou, China.
² Institute of Spatial Information for City Brain (ISICA), Hangzhou City University, Hangzhou, China.
³ Institute of Agricultural Bio-Environmental Engineering, College of Bio-systems Engineering and Food Science, Zhejiang University, Hangzhou, China.
⁴ Academy of Rural Development, Zhejiang University, Hangzhou, China.

Abstract

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.

Keywords: convolution neural network; deep learning; fresh weight; growth traits; rice seedling.

Grants and funding

This research was supported by the Key R&D Program of Zhejiang Province (Grant No. 2022C02026 and 2022C02003) and Zhejiang Provincial Basic Public Welfare Research Project of China under Grant No. LGN22C130016.