Claim · model-written summary
Models using assessment-day and preceding 24-hour weather had the highest prediction success.
- Taxon
- Stylosanthes scabra
Stylosanthes scabrae1 - Outcome
- prediction successe0
- Direction
- higheste0
- Comparator
- higheste0
Not reportedMaterialGeneCompoundOrgan / stageInteractorInteractor roleSecond interactorSecond interactor roleTreatmentSettingValueQualifier
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“ANN models with weather for the day of disease assessment and the previous 24 h period had the highest prediction success”
e1“Stylosanthes scabra caused by Colletotrichum gloeosporioides”
Title
Weather‐based prediction of anthracnose severity using artificial neural network models
S. Chakraborty; R. Ghosh; M. Ghosh; et al. Plant Pathology 2004. doi:10.1111/j.1365-3059.2004.01044.x
Other claims from this paper (8)
- Method / resource Cross-continent predictions from all-site continental models succeeded on more than 75% of days.
- Method / resource The Australian model had 21·9% overall prediction error.
- Method / resource The South American model had 22·1% overall prediction error.
- Method / resource The model excluding Planaltina was the most accurate, exceeding 85% prediction success.
- Method / resource The model excluding Carimagua was least accurate, with 54% success.
- Method / resource Moisture-related weather variables were most important in all ANN models.
- Observation High and low anthracnose risk sites occurred on both continents.
- Association Weather at Brazilian and Colombian diversity centres appeared no more conducive to serious anthracnose than Australian conditions.