Claim · model-written summary
TabPFN had faster tuning time than the six ML models it was benchmarked against.
- Taxon
- maize, soybeans and sunflowers
Glycine max
Helianthus
Zea mayse0 - Outcome
- tuning timee4
- Direction
- fastere4
- Comparator
- six ML modelse1
Not reportedMaterialGeneCompoundOrgan / stageInteractorInteractor roleSecond interactorSecond interactor roleTreatmentSettingValueQualifier
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“we present an application of a foundation model for small- to medium-sized tabular data (TabPFN), to sub-national yield forecasting task in South Africa for maize, soybeans and sunflowers”
e1“We benchmarked the results of the TabPFN against six ML models and two baseline models”
e4“Nonetheless, TabPFN demonstrated practical utility due to its faster tuning time and reduced requirement for feature engineering”
Title
From rows to yields: how foundation models for tabular data simplify crop yield prediction
Filip Sabo; Michele Meroni; María Piles; et al. Scientific Reports 2026. doi:10.1038/s41598-026-50338-z
Other claims from this paper (6)
- Method / resource TabPFN and ML models showed comparable accuracy, both outperforming baseline approaches in sub-national yield forecasting.
- Method / resource The best-performing ML model achieved 6.8% rRMSEp for maize at the national level.
- Method / resource TabPFN achieved 8.8% rRMSEp for maize at the national level, higher than the best-performing ML model.
- Method / resource The best-performing ML model reached R² of 0.91 for maize at the national level.
- Method / resource TabPFN reached R² of 0.86 for maize at the national level.
- Method / resource TabPFN required reduced feature engineering compared with the six ML models it was benchmarked against.