Machine learning-assisted non-destructive prediction of root architecture in early-stage tomato rootstocks

Hatice Şeyma Yücel · 2026

Read Machine learning-assisted non-destructive prediction of root architecture in early-stage tomato rootstocks by Hatice Şeyma Yücel (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13471257.txt.

Description

Hatice Şeyma Yücel tests in 2026 whether machine learning can predict tomato root shape from measurements taken above ground, sparing young plants from destruction. Root architecture drives how well a rootstock feeds and waters the plant grafted onto it, but digging roots up kills the specimen. Nineteen hybrid rootstock candidates, bred from cultivated tomato crossed with a wild relative, were grown alongside two commercial rootstocks and one scion variety.

Plants were measured at four points across their first month, with roots imaged at each stage. Simple inputs such as genotype, plant height, and stem thickness fed several predictive models. A gradient boosting model and plain linear regression performed best, explaining up to ninety five percent of variation in root length, surface, and volume. Root thickness proved harder to forecast.

Catalog record

CREATORHatice Şeyma Yücel
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE77825
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13471257

Browse the full library · About the Tower of Babel