Search claims · PlantClaims

Method / resourceobservedoriginal resultnegativemeasured

Claim · model-written summary

Application of both models outside prior temperature ranges showed limitations.

Outcome: application of both modelse0
Qualifier: limitationse0
Comparator: past temperature rangese0

Verbatim

e0
“limitations for the application of both models outside the past temperature ranges became apparent”
✓ located verbatim in the source · abstract, characters 1272–1370

Title

Comparing Apple and Pear Phenology and Model Performance: What Seven Decades of Observations Reveal

Bianca Drepper; Anne Gobin; Serge Remy; et al. Agronomy 2020. doi:10.3390/agronomy10010073

Other claims from this paper (8)

Association Apple flowering was 9.5 days earlier after warm dormancy periods.
Association Pear flowering was 11.5 days earlier after warm dormancy periods.
Association The bloom date and temperature relationship was nonlinear.
Observation After warm chilling, models predicted apple dormancy break 5.0 days later.
Observation After warm chilling, models predicted pear dormancy break 10.6 days later.
Method / resource PLSR gave mixed signals about flowering onset after warm chilling.
Method / resource A dynamic chill model with growing degree days had lower flowering prediction errors than a continuous chill-forcing model.
Method / resource Model performance was sensitive to parametrization method.

Method / resourceobservedoriginal resultmeasured

Claim · model-written summary

Both models describe whole cane budbreak as determined by temperature and dormancy breaking chemical application.

Taxon: kiwifruitActinidia deliciosat0
Outcome: overall amount of budbreak for whole canese0
Comparator: Both modelse0

Not reportedDirection

Verbatim

e0
“Both models describe how temperature, and application of a dormancy-breaking chemical, determine the overall amount of budbreak for whole canes”
✓ located verbatim in the source · abstract, characters 377–520

t0
“kiwifruit (Actinidia deliciosa)”
✓ located verbatim in the source · abstract, characters 65–96

Title

Modelling Kiwifruit Budbreak as a Function of Temperature and Bud Interactions

P. T. AUSTIN Annals of Botany 2002. doi:10.1093/aob/mcf113

Other claims from this paper (3)

Method / resource The LOP model describes budbreak patterns along canes.
Method / resource Fitted models explained 87 % of variation in budbreak amount.
Mechanism The chilling and budbreak correlation may reflect population based interactions among buds.

Method / resourceobservedoriginal resultnegativemeasured

Claim · model-written summary

Both models tended to overestimate low latent heat fluxes.

Taxon: alfalfaMedicago sativae1
Outcome: LE fluxese0
Direction: overestimatee0
Qualifier: low LE fluxese0
Comparator: Both modelse0

Verbatim

e0
“Both models tended to overestimate at low LE fluxes.”
✓ located verbatim in the source · abstract, characters 959–1011

e1
“large fields of naturally subirrigated alfalfa”
✓ located verbatim in the source · abstract, characters 102–148

Title

Application of remote sensing in estimating evapotranspiration in the Platte river basin

Blaine L. Blad; N. J. Rosenberg NASA Technical Reports Server (NASA) 1976

Other claims from this paper (4)

Method / resource Daily evapotranspiration estimates from the resistance model were within 10% of the BREB model estimates.
Method / resource Daily estimates by the mass transport model agreed less well with BREB estimates.
Method / resource Model performance was good on clear and cloudy days and under non-advection and strong sensible heat advection.
Method / resource Both models were less satisfactory for short-term latent heat flux estimates.

Method / resourceobservedoriginal resultpositivenot significant (as stated)measured

Claim · model-written summary

Both models generally fit pasture yield data well with nonsignificant lack-of-fit tests.

Outcome: fitted the data welle0

Not reportedValue

Verbatim

e0
“Generally, both models fitted the data well, with a test for ‘lack of fit’ being non-significant.”
✓ located verbatim in the source · abstract, characters 617–714

Title

Models for pasture yield in response to phosphate application

D. A. Ratkowsky; P. W. G. Sale; S. B. Tennakoon; et al. Australian Journal of Experimental Agriculture 1998. doi:10.1071/ea96106

Other claims from this paper (6)

Method / resource Mitscherlich and rational models gave closely equivalent pasture fits, with Mitscherlich better in two-thirds of cases.
Method / resource The models fit asymptotic, rapidly rising and near-linear response patterns.
Method / resource Mitscherlich was more stable for atypical responses and its parameters were easy to interpret.
Recommendation The authors recommend Mitscherlich to describe pasture yield as a function of phosphate application.
Method / resource A curved-area ratio to a soluble reference fertiliser was proposed as a relative performance index.
Method / resource Sites with reference fertiliser area below 10% of fitted curve area were classified as phosphate unresponsive.

Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

Both models performed well in 131 fruit categories after parameter adjustment.

Outcome: performed welle0
Value: 131 categoriese0

Not reportedTaxon

Verbatim

e0
“After adjusting some parameters, the two models performed well in 131 categories.”
✓ located verbatim in the source · abstract, characters 567–648

Title

Application and Analysis of Convolutional Neural Networks and Vision Transformer Models in Fruit Recognition

Shouzhe Liu 2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications (ICPECA) 2023. doi:10.1109/icpeca56706.2023.10076218

Other claims from this paper (3)

Method / resource ViT performed much better than CNN on challenging fruit recognition problems.
Recommendation The authors recommend a comprehensive robustness dataset containing all strange fruit photos.
Method / resource ViT had an incredibly low accuracy rate for an unidentified cause despite outstanding overall performance.

Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

Both NIR datasets supported strong prediction models for field nitrogen application rate.

Taxon: SWITCHGRASSPanicum virgatumt0
Outcome: predict non-structural carbohydrates content and the rate of nitrogen applied to the fielde0
Value: two near infrared data setse0

Verbatim

t0
“SWITCHGRASS”
✓ located verbatim in the source · title, characters 12–23

e0
“From the two near infrared data sets strong models were developed to predict non-structural carbohydrates content and the rate of nitrogen applied to the field”
✓ located verbatim in the source · abstract, characters 994–1153

Title

ANALYSIS OF SWITCHGRASS CHARACTERISTICS USING NEAR INFRARED TECHNIQUES

Nicole Labbé; Philip Ye; Jennifer Franklin; et al. BioResources 2008

Other claims from this paper (6)

Method / resource PCA of near infrared spectra discriminated switchgrass growth locations.
Method / resource Multivariable analysis separated switchgrass samples by ecotype.
Method / resource Multivariable analysis separated switchgrass samples by fertilizer rate.
Method / resource Dispersive and Fourier Transform NIR spectra gave similar switchgrass classification results.
Method / resource Both NIR datasets supported strong prediction models for switchgrass non-structural carbohydrate content.
Method / resource Dispersive spectrometer spectra yielded more accurate models for these switchgrass samples.

Method / resourceobservedoriginal resultno effectmeasured

Claim · model-written summary

Both models showed comparable performance with larger training datasets.

Outcome: performancee0
Direction: comparablee0
Comparator: baseline multiple linear regression modele1

Verbatim

e0
“both models exhibit comparable performance with larger training datasets”
✓ located verbatim in the source · abstract, characters 1018–1090

e1
“baseline multiple linear regression model”
✓ located verbatim in the source · abstract, characters 478–519

Title

Prediction of Rice Yields in a Changing Climate Using the Mobile Rice Yield Prediction Application

Mohamad Farhan Mohamad Mohsin; Mohamad Ghozali Hassan; Kamal Imran Mohd Sharif; et al. Journal of Information and Communication Technology 2025. doi:10.32890/jict2025.24.2.1

Other claims from this paper (3)

Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

Both X-ray image models distinguished germinated from non-germinated tomato seeds strongly.

Taxon: TomatoSolanum lycopersicumt0
Outcome: distinguishing germinated and non-germinated seedse0
Direction: strong performancee0

Not reportedComparatorValue

Verbatim

e0
“Both models showed strong performance in distinguishing germinated and non-germinated seeds”
✓ located verbatim in the source · abstract, characters 843–934

t0
“Tomato Seed Viability”
✓ located verbatim in the source · title, characters 84–105

Title

Application of X-Ray Imaging and Convolutional Neural Networks in the Prediction of Tomato Seed Viability

Suk-Ju Hong; Seongmin Park; Chang-Hyup Lee; et al. IEEE Access 2023. doi:10.1109/access.2023.3265998

Other claims from this paper (3)

Method / resource The CNN model predicted tomato seed viability more accurately than the image-processing model.
Method / resource The CNN model achieved 86.01% tomato seed viability prediction accuracy.
Method / resource The CNN model achieved a 92.11% F1 score for tomato seed viability prediction.

Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

In the generalization test the models achieved an average accuracy of over 79% for both cigar leaf varieties.

Outcome: average accuracye0
Value: over 79%e0

Verbatim

e0
“an average accuracy of over 79% for both varieties”
✓ located verbatim in the source · abstract, characters 813–863

Title

Establishment of an Application for Recognizing the Maturity of Cigar Leaf Using RGB Images

Shuhua Zeng; Hao Yang; Shiping Guo; et al. Open Access Journal of Physics and Science 2025. doi:10.61440/oajps.2025.v2.08

Other claims from this paper (7)

Method / resource Both ResNet_18 and AlexNet reached higher training accuracy with optimized structure 2 than with the classical structure and optimized structure 1.
Method / resource InitialLearnRate reached its highest accuracy at 0.001.
Method / resource MiniBatchSize reached its highest accuracy at 32.
Method / resource The improved ResNet_18 had higher precision than AlexNet, by 1.7%.
Method / resource The improved ResNet_18 had higher recall than AlexNet, by 3.3%.
Method / resource The improved ResNet_18 had a higher F1 score than AlexNet, by 0.026.
Method / resource The model reached a discrimination accuracy of 92% for the unripe variety Chuanxue 1.

Method / resourceauthor interpretationoriginal resultpositivemeasured

Claim · model-written summary

The authors found both models stable and suitable for sugar beet yield prediction.

Taxon: sugar beetBeta vulgaris subsp. vulgarise0
Outcome: stable and suitable for prediction of sugar beet yielde0
Comparator: CHAID and CART modelse0

Verbatim

e0
“CHAID and CART models were stable and suitable for prediction of sugar beet yield”
✓ located verbatim in the source · abstract, characters 1191–1272

Title

The Application of the CART and CHIAD Algorithms in Sugar Beet Yield Prediction

Nasim Monjezi Basrah Journal of Agricultural Sciences 2021. doi:10.37077/25200860.2021.34.1.01

Other claims from this paper (4)

Method / resource The CART training model achieved 95% precision for sugar beet yield prediction.
Method / resource The CART test model achieved 93% precision for sugar beet yield prediction.
Method / resource CART produced a nine-variable, 29-node decision tree.
Method / resource CHAID produced a nine-variable, 39-node decision tree.

“application of both models”

Claim types

Direction of the findings

Over time

Claim type

Research area

Polarity

Statistics