Method / resourcemodel-written summary

Integrating multispectral imagery and accumulated temperature in the CNN-Transformer phenology monitoring model for maize achieved an accuracy of 92.9%.

A claim from Monitoring Maize Phenology Using Multi-Source Data by Integrating Convolutional Neural Networks and Transformers · 2026

Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

Integrating multispectral imagery and accumulated temperature in the CNN-Transformer phenology monitoring model for maize achieved an accuracy of 92.9%.

Taxon
MaizeZea mayst0
Outcome
accuracye1
Value
92.9%e1
Qualifier
integration of multispectral imagery and accumulated temperaturee1

Not reportedMaterialGeneCompoundOrgan / stageInteractorInteractor roleSecond interactorSecond interactor roleTreatmentComparatorSettingDirection

Organisms pictured · Representative pictures of the matched species, not figures from the paper.

Zea mays
Zea mays · TaxonAkwugo · CC BY-SA 4.0 · Wikimedia Commons ↗

Verbatim

e1

“the integration of multispectral imagery and accumulated temperature achieved an accuracy of 92.9%”

✓ located verbatim in the source · abstract, characters 1452–1550
t0

“Maize Phenology”

✓ located verbatim in the source · title, characters 11–26

Title

Monitoring Maize Phenology Using Multi-Source Data by Integrating Convolutional Neural Networks and Transformers

Yugeng Guo; Wenzhi Zeng; Haoze Zhang; et al. Remote Sensing 2026. doi:10.3390/rs18020356

Other claims from this paper (1)

Record rev-7cdf3a86e4067074f6ccbef31468eb2252dce64675115dd6237547897d671f7e · schema claims-v0.9 · position 1 in the model’s answer