Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 28, 2026

Using Flatbed Scanners to Collect High-resolution Time-lapsed Images of the Arabidopsis Root Gravitropic Response

Using Flatbed Scanners to Collect High-resolution Time-lapsed Images of the Arabidopsis Root Gravitropic Response

Published on: January 25, 2014

Deep learning-based association analysis of root image data and cucumber yield.

Cuifang Zhu¹, Hongjun Yu¹, Tao Lu¹

¹State Key Laboratory of Vegetable Biobreeding, Institute of Vegetables and Flowers, Chinese Academy of Agricultural Sciences, Beijing, 100081, China.

The Plant Journal : for Cell and Molecular Biology

|January 9, 2024

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

A SlERF4-SlTPP1 module enhances drought tolerance in tomato by increasing the root/shoot ratio.

Horticulture research·2026

Same author

Role of Starch Accumulation at the Mature Green Stage in Shaping Tomato Fruit Quality.

Plants (Basel, Switzerland)·2026

Same author

Computational analysis and expression profiling of the Sulfate Transporter gene family in tomato under selenium and abiotic stress treatment.

BMC plant biology·2026

Same author

Cancer-Associated Fibroblasts Promote Tumor Immunosuppression in Hepatocellular Carcinoma via the NNMT-ANGPTL4 Axis.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026

Same author

Molecular insights into Candida auris glycosylphosphatidylinositol transamidase.

Protein & cell·2026

Same author

Structural basis of EGF-repeat O-glucosylation by the protein O-glucosyltransferase POGLUT2.

The Journal of biological chemistry·2026

Researchers used deep learning to analyze cucumber root system architecture (RSA) and predict yield. Automated image analysis accurately segmented roots and identified key traits like root angle, enabling faster breeding for high-yield, stress-resistant crops.

Area of Science:

Agricultural Science
Plant Biology
Computer Vision

Background:

Root system architecture (RSA) is crucial for plant water and nutrient uptake, directly impacting crop yield and stress resistance.
Optimizing RSA is a key objective in agricultural improvement for enhanced productivity and adaptability.
Understanding the correlation between RSA and crop yield is vital for developing superior crop varieties.

Purpose of the Study:

To explore the relationship between cucumber root system architecture and crop yield.
To develop and apply deep learning models for automated root system analysis and yield prediction.
To identify specific RSA traits that correlate with cucumber productivity.

Main Methods:

Collected and analyzed root system images and yield data from 277 cucumber varieties using germination plates and greenhouse cultivation.

Keywords:

cucumber deep learning nutrient absorption root system architecture yield prediction

More Related Videos

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols

Published on: August 8, 2017

Related Experiment Videos

Last Updated: May 28, 2026

Using Flatbed Scanners to Collect High-resolution Time-lapsed Images of the Arabidopsis Root Gravitropic Response

Using Flatbed Scanners to Collect High-resolution Time-lapsed Images of the Arabidopsis Root Gravitropic Response

Published on: January 25, 2014

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols

Published on: August 8, 2017

Trained ResNet50 and U-Net deep learning models for image classification, segmentation, quality inspection, and yield prediction of cucumber seedlings.

Utilized automated root system segmentation and image analysis for high-throughput phenotyping (HTP).

Main Results:

The U-Net model achieved high-quality automatic extraction of cucumber root systems (F1 score ≥ 0.95).
The ResNet50 model accurately predicted cucumber yield grade from seedling root images, with the highest F1 score reaching 0.86 at 10 days.
Root angle was the most significant factor correlated with yield, with shallow angles positively and steep angles negatively impacting yield.

Conclusions:

Deep learning models can effectively analyze RSA and predict crop yield from seedling images, offering a novel approach for rapid crop breeding.
The developed germination plate method and automated segmentation model facilitate high-throughput phenotyping of root systems.
RSA, in conjunction with nutrient absorption, significantly influences cucumber production capacity, highlighting the importance of targeted breeding strategies.