Non-destructive identification of closely related japonica rice seeds using hyperspectral imaging combined with HHO-optimized XGBoost

Chunxu Jiang, Shixue Gu, Gang Liu, Yang Liu, Rongjie Huang, Shaozhong Song · 2026

Read Non-destructive identification of closely related japonica rice seeds using hyperspectral imaging combined with HHO-optimized XGBoost by Chunxu Jiang, Shixue Gu, Gang Liu, Yang Liu, Rongjie Huang, Shaozhong Song (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/pmc-13627093.txt.

Description

Chunxu Jiang and co-authors present a 2026 method to tell apart closely related rice seed types without destroying the seeds. Japonica rice varieties that are near kin look alike, and standard tests are slow, complex, and consume the sample. Imaging that reads reflected light across many wavelengths offers a gentler option.

Raw imaging signals suffer from instrument noise and high data volume. The team paired the imaging with a boosted decision-tree model tuned by an optimization method. The result is a fast screen for seed collections that keeps each seed intact, which matters when samples are rare or needed for planting.

Catalog record

CREATORChunxu Jiang, Shixue Gu, Gang Liu, Yang Liu, Rongjie Huang, Shaozhong Song
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE77 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13627093

Browse the full library · About the Tower of Babel