AUTHOR=Chang Sungyul , Lee Unseok , Hong Min Jeong , Jo Yeong Deuk , Kim Jin-Baek 

TITLE=Time-Series Growth Prediction Model Based on U-Net and Machine Learning in Arabidopsis

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 12 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2021.721512

DOI=10.3389/fpls.2021.721512

ISSN=1664-462X

ABSTRACT=Yield prediction for crops is essential information for food security. A high-throughput phenotyping platform (HTPP) generates the data of the complete life cycle of a plant; however, the data are rarely used for yield prediction because of the lack of quality image analysis method, yield data associated with HTPP, and time-series analysis method for yield prediction. To overcome limitations, this study employs multiple deep learning (DL) networks to extract high-quality HTTP data, establish an association between HTTP data and the yield performance of crops, and select essential time intervals using machine learning (ML). The images of Arabidopsis were taken 12 times under environmentally controlled HTPP over 23 days after sowing (DAS). First, the features from images were extracted using DL network UNet with SE-ResXt101 encoder and divided into early (15–21 DAS) and late (~21–23 DAS) preflowering developmental stages using the physiological characteristics of the Arabidopsis plant. Second, the late preflowering stage at 23 DAS can be predicted using the ML algorithm XGBoost, based only on a portion of the early preflowering stage (17–21 DAS). This was confirmed using an additional biological experiment (P < 0.01). Finally, the projected area (PA) was estimated into fresh weight (FW) and the correlation coefficient between FW and predicted FW was calculated as 0.901. This is the first study that analyzed time-series data to predict the FW of related but different developmental stages and predict the PA. The results of this study are informative and enable the understanding of the FW of Arabidopsis or yield of leafy plants and total biomass consumed in vertical farming. Moreover, this study highlights the reduction of time-series data for examining interesting traits and future application of time-series analysis in various HTPPs.