Phenology-Dependent Sex Identification in Mature Ginkgo biloba Using Hyperspectral Imaging
Zhengnan Zhao, Jingyue Zhang, Tao Wang, Si Liu, Zeyang Yi, Xue Wang, Xiao Chen, Qun Sun, Hongyan Sun · 2026
Read Phenology-Dependent Sex Identification in Mature Ginkgo biloba Using Hyperspectral Imaging by Zhengnan Zhao, Jingyue Zhang, Tao Wang, Si Liu, Zeyang Yi, Xue Wang, Xiao Chen, Qun Sun, Hongyan Sun (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/PMC13468224.txt.
Description
Zhengnan Zhao and co-authors try in 2026 to sex ginkgo trees from leaf light spectra, and discover the answer changes with the season. Ginkgo is prized for landscaping and medicine, but males and females are hard to tell apart outside flowering and fruiting. The team collected hyperspectral images of leaves from mature trees at flowering, green-leaf, and yellow-leaf stages and trained machine learning classifiers on each.
Single-stage models performed very well, with test accuracies between 95.77 and 97.12 percent depending on the stage. The informative wavelengths, however, migrated from visible light in summer toward near-infrared in autumn, with almost no bands shared across all stages. A single year-round model collapsed to near chance when carried across stages. The result is a caution and a guide: spectral sexing works, but the calendar must be built into the model.
Catalog record
| CREATOR | Zhengnan Zhao, Jingyue Zhang, Tao Wang, Si Liu, Zeyang Yi, Xue Wang, Xiao Chen, Qun Sun, Hongyan Sun |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 38622 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |