Info

Integrated Initiative for Designing Future Society is pleased to announce the research achievements of a research group led by Associate Professor Daisuke Yasutake (Faculty of Agriculture), Decarbonization Unit / CO₂ Capture and Conversion Group, together with collaborators.

Key Points

• The world’s first monitoring technology targeting crop roots under actual cultivation conditions, rather than laboratory environments
• Visualization of the dry matter weight distribution of entire root systems using spectral images*¹ and machine learning*²
• Enables evaluation of time‑series changes in root growth (dry matter weight) over long cultivation periods

Overview

In the realization of data‑driven precision agriculture and smart farming, it is essential to accurately understand crop growth conditions. While monitoring technologies for visible above‑ground plant parts—such as leaves, stems, and fruits—have been well developed, technologies targeting roots have remained limited to laboratory‑scale experiments.

A research group comprising Mr. Jin Ziyi, a doctoral student at the Graduate School of Bioresource and Bioenvironmental Sciences, Kyushu University; Associate Professor Daisuke Yasutake of the Faculty of Agriculture, Kyushu University; and researchers from the IoP Co‑Creation Center at Kochi University and the Graduate School of Sciences and Technology for Innovation, Yamaguchi University, has developed a new technology to estimate root dry matter weight.

In this method, part of a hydroponic cultivation system is replaced with transparent materials, enabling observation of the entire root system. By applying a machine‑learning model*² based on the acquired spectral images*¹, the dry matter weight of roots can be estimated.

Using this technology, the research team successfully achieved high‑precision monitoring of root growth in leafy vegetables (spinach) under actual production conditions, covering the entire growth period from transplanting to harvest.

This technology is expected to contribute to the realization of smart agriculture, in which not only above‑ground parts (leaves, stems, fruits) but also root growth can be precisely monitored and controlled.

Publication Information

The research results were published online on March 10, 2026, in the academic journal Plant Methods (Springer Nature).

For further details, please refer to the related links below.

Glossary

*¹ Spectral Images
Images that record reflected light from objects by dividing it into numerous wavelength bands. While ordinary color images contain only three types of information (red, green, and blue), spectral images include information from hundreds of wavelength bands, allowing identification of object characteristics invisible to the human eye.

*² Machine Learning
A technology in which computers automatically learn patterns and rules from large datasets and use them to make predictions or decisions.