Search claims · PlantClaims

Method / resourceobservedoriginal resultpositivesignificant (as stated)measured

Claim · model-written summary

Band correction significantly improved transferability between sensors, reducing RRMSE by 15.05–59.99%.

Taxon: riceOryza sativat0
Treatment: band correctione0
Outcome: Model transferabilitye0
Direction: improvede0
Value: 15.05–59.99%e0
Comparator: different sensorse0

Verbatim

e0
“Model transferability was improved significantly between different sensors after band correction with a decrease of 15.05–59.99% in RRMSE.”
✓ located verbatim in the source · abstract, characters 1525–1663

t0
“Rice Grain Yield”
✓ located verbatim in the source · title, characters 41–57

Title

Transferability of Models for Predicting Rice Grain Yield from Unmanned Aerial Vehicle (UAV) Multispectral Imagery across Years, Cultivars and Sensors

Hengbiao Zheng; Wenhan Ji; Wenhui Wang; et al. Drones 2022. doi:10.3390/drones6120423

Other claims from this paper (4)

Method / resource RENDTI was superior to other indices for regression with rice grain yield in most cases.
Method / resource GNDTI had the highest validation accuracy across rice cultivars and sensors.
Method / resource The Japonica yield model transferred to Indica rice with RMSE 1.16 t/ha, bias 0.08 and RRMSE 11.04%.
Method / resource Random forest improved transferability across years and cultivars and had the highest prediction accuracy with RMSE 0.94 t/ha, bias −0.21 and RRMSE 9.37%.

Method / resourceauthor interpretationoriginal resultpositivemeasured

Claim · model-written summary

The optical sensor algorithm can increase wheat yields.

Taxon: Cropt0
Outcome: yieldse0
Direction: increasee0
Value: 0.4 m2e0

Verbatim

t0
“Crop”
✓ located verbatim in the source · title, characters 35–39

e0
“Using our optical sensor‐based algorithm that employs yield prediction and N responsiveness by location (0.4 m2 resolution) can increase yields and decrease environmental contamination due to excessive N fertilization”
✓ located verbatim in the source · abstract, characters 1791–2008

Title

Optical Sensor‐Based Algorithm for Crop Nitrogen Fertilization

W. R. Raun; J. B. Solie; M. L. Stone; et al. Communications in Soil Science and Plant Analysis 2005. doi:10.1080/00103620500303988

Other claims from this paper (3)

Method / resourceauthor interpretationoriginal resultbasis n/a

Claim · model-written summary

An aerial photograph image analysis method was proposed for accessible decline diagnosis.

Taxon: grapevineVitist0
Outcome: image-analysis methodology using aerial photographse0

Not reportedComparator

Verbatim

e0
“an image-analysis methodology using aerial photographs were proposed as easy-to-obtain indicators of grapevine decline”
✓ located verbatim in the source · abstract, characters 1901–2019

t0
“grapevine”
✓ located verbatim in the source · title, characters 23–32

Title

A systemic approach to grapevine decline diagnosed using three key indicators: plant mortality, yield loss and vigour decrease

Anne MEROT; Guillaume Coulouma; Nathalie Smits; et al. OENO One 2023. doi:10.20870/oeno-one.2023.57.1.5575

Other claims from this paper (9)

Association Farmers’ perceptions agreed with field measures of decline.
Observation Vine mortality spread progressively over years.
Association The survey and historical analysis found no direct link between decline and yield loss.
Observation Yield fluctuated annually without systematically declining.
Method / resource Mortality rate was an earlier indicator of decline than yield loss.
Method / resource NDVI was an earlier indicator of decline than yield loss.
Method / resource Ground based NDVI indicators were proposed for accessible decline diagnosis.
Association NDVI indicators correlated linearly with yield achievement ratio.
Association NDVI indicators correlated linearly with mortality rate.

Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

RF feature selection reduced RMSE by 29.41%.

Outcome: Root Mean Square Error (RMSE)e0
Direction: reductione0
Value: 29.41%e0

Verbatim

e0
“resulting in a 29.41% reduction in Root Mean Square Error (RMSE) and a 67% decrease in bias”
✓ located verbatim in the source · abstract, characters 1626–1717

e1
“The RF model explained 44% of the variance in the data”
✓ located verbatim in the source · abstract, characters 1570–1624

Title

Estimating paddy rice yield using PlanetScope imagery and machine learning

Sa’ad Ibrahim; Heiko Balzter; Mohammed S. Ozigis Smart Agricultural Technology 2025. doi:10.1016/j.atech.2025.101447

Other claims from this paper (14)

Method / resource All tested machine-learning algorithms performed best with RFE and MIR feature selection.
Method / resource k-NN was the best yield model, with R² of 0.61.
Method / resource k-NN yielded RMSE of 578.43 kg/ha.
Method / resource ANN yield prediction had R² of 0.58.
Method / resource ANN yield prediction had RMSE of 601.29 kg/ha.
Method / resource RF yield prediction had R² of 0.44.
Method / resource RF yield prediction had RMSE of 694.48 kg/ha.
Method / resource XGBoost yield prediction had R² of 0.34.
Method / resource XGBoost yield prediction had RMSE of 756.48 kg/ha.
Method / resource ANN performed optimally with only a few spectral features.
Method / resource RF explained 44% of yield variance.
Method / resource RF feature selection reduced bias by 67%.
Method / resource XGBoost explained 13.33% more yield variance than the previous model.
Method / resource XGBoost reduced RMSE by 3.25% against the previous model.

Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

Eight named stress indices distinguished the genotype clusters.

Taxon: wheatTriticum aestivumt0
Outcome: effectively distinguished the genotypic clusterse0
Value: eight drought tolerance indicese0

Verbatim

e0
“eight drought tolerance indices, viz. stress tolerance index (STI), modified stress tolerance index (mSTI), mean productivity (MP), geometric mean productivity (GMP), harmonic mean index (HMI), relative efficiency index (REI), relative decrease in yield (RDY), and superiority index (Pi) effectively distinguished the genotypic clusters”
✓ located verbatim in the source · abstract, characters 1254–1590

t0
“wheat”
✓ located verbatim in the source · title, characters 33–38

Title

Screening drought-tolerant bread wheat genotypes using yield-based stress indices

Sheikh Faruk Ahmed; Anika Nazran; Totan Kumar Ghosh; et al. Annals of Bangladesh Agriculture 2023. doi:10.3329/aba.v27i2.72517

Other claims from this paper (6)

Intervention effect Drought significantly reduced wheat grain yield across genotype and season.
Association Yield and drought tolerance indices were strongly correlated, mostly positively under both regimes.
Method / resource Clustering distinguished six tolerant high-yield wheat genotypes.
Method / resource Clustering distinguished 31 mid-tolerant wheat genotypes.
Method / resource Clustering distinguished 19 susceptible low-yield wheat genotypes.
Observation Six named genotypes protected yield better under drought than other genotypes.

Method / resourceobservedoriginal resultsimulated

Claim · model-written summary

Only three of eight life cycle parameters were of minor importance for Striga hermonthica seedbank dynamics and millet yield

Taxon: millete1
Interactor: S. hermonthicaStriga hermonthicae1parasite
Outcome: importance for seedbank dynamics and millet yielde5
Value: three out of eighte5

Verbatim

e1
“Spatial expansion of S. hermonthica and decrease in millet yield in a field was slower, on average, when stochasticity of attachment of seedlings to the host was included and compared to the deterministic model”
✓ located verbatim in the source · abstract, characters 476–686

e5
“Sensitivity analysis showed that only three out of eight life cycle parameters were of minor importance for seedbank dynamics and millet yield”
✓ located verbatim in the source · abstract, characters 903–1045

Title

Long‐term management of Striga hermonthica: strategy evaluation with a spatio‐temporal population model

T A VAN MOURIK; F J J A BIANCHI; W VAN DER WERF; et al. Weed Research 2008. doi:10.1111/j.1365-3180.2008.00638.x

Other claims from this paper (7)

Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

The stacked ensemble model notably enhances accuracy compared with traditional machine learning models.

Taxon: crope0
Outcome: accuracye1
Direction: enhancemente1
Comparator: traditional machine learning modelse1

Verbatim

e0
“Predicting crop yields remains a crucial challenge in agriculture”
✓ located verbatim in the source · abstract, characters 9–74

e1
“The proposed stacked ensemble model achieves superior crop yield prediction performance, evidenced by a notable enhancement in accuracy and a significant decrease in RMSE, surpassing the predictive capabilities of traditional machine learning models”
✓ located verbatim in the source · abstract, characters 1125–1374

Title

Stacked ensemble model for accurate crop yield prediction using machine learning techniques

Ramesh V; Kumaresan P Environmental Research Communications 2025. doi:10.1088/2515-7620/adb9c0

Other claims from this paper (6)

Method / resource The stacked ensemble model achieves superior crop yield prediction performance compared with traditional machine learning models.
Method / resource The stacked ensemble model significantly decreases RMSE compared with traditional machine learning models.
Method / resource Mean Absolute Error of the stacked ensemble model is 7.20 tons/hectare.
Method / resource Mean Square Error of the stacked ensemble model is 15570.32 tons 2 /hectare 2.
Method / resource Root Mean Square Error of the stacked ensemble model is 124.78 tons/hectare.
Method / resource Coefficient of determination (R2) of the stacked ensemble model is 0.98.

Method / resourceauthor interpretationoriginal resultbasis n/a

Claim · model-written summary

Ground based NDVI indicators were proposed for accessible decline diagnosis.

Taxon: grapevineVitist0
Outcome: ground-based NDVI indicatorse0
Value: twoe0

Verbatim

e0
“two ground-based NDVI indicators and an image-analysis methodology using aerial photographs were proposed as easy-to-obtain indicators of grapevine decline”
✓ located verbatim in the source · abstract, characters 1864–2019

t0
“grapevine”
✓ located verbatim in the source · title, characters 23–32

Title

A systemic approach to grapevine decline diagnosed using three key indicators: plant mortality, yield loss and vigour decrease

Anne MEROT; Guillaume Coulouma; Nathalie Smits; et al. OENO One 2023. doi:10.20870/oeno-one.2023.57.1.5575

Other claims from this paper (9)

Association Farmers’ perceptions agreed with field measures of decline.
Observation Vine mortality spread progressively over years.
Association The survey and historical analysis found no direct link between decline and yield loss.
Observation Yield fluctuated annually without systematically declining.
Method / resource Mortality rate was an earlier indicator of decline than yield loss.
Method / resource NDVI was an earlier indicator of decline than yield loss.
Method / resource An aerial photograph image analysis method was proposed for accessible decline diagnosis.
Association NDVI indicators correlated linearly with yield achievement ratio.
Association NDVI indicators correlated linearly with mortality rate.

Method / resourceobservedoriginal resultsimulated

Claim · model-written summary

The model showed a large range of overwatering before crop production declined.

Taxon: cropt0
Outcome: decline affect in crop productione0
Comparator: over wateringe0

Not reportedValue

Verbatim

t0
“crop”
✓ located verbatim in the source · title, characters 72–76

e0
“the model shows that there is a large range of over watering that can occur before a decline affect in crop production can be seen”
✓ located verbatim in the source · abstract, characters 716–846

Title

Helpful Farming Model: How to decrease your water foot while maximizing crop yield.

Paige Morgan Digital Commons - USU (Utah State University) 2017

Other claims from this paper (2)

Method / resource AquaCrop predictions came within 10% of historical crop yields.
Recommendation The authors conclude that AquaCrop can provide environmental and financial savings to farmers.

Method / resourceobservedoriginal resultmeasured

Claim · model-written summary

NDVI plus days to heading raised prediction accuracy by 50% when NDVI saturated.

Taxon: wheatTriticum aestivumt0
Outcome: prediction accuracye0
Direction: increasee0
Value: 50%e0

Not reportedComparator

Verbatim

e0
“models including NDVI and days to heading providing a 50% increase in the prediction accuracy and a 10% decrease in the root mean square error.”
✓ located verbatim in the source · abstract, characters 1064–1207

t0
“wheat”
✓ located verbatim in the source · title, characters 20–25

Title

Improving in-season wheat yield prediction using remote sensing and additional agronomic traits as predictors

Adrian Gracia-Romero; Rubén Rufo; David Gómez-Candón; et al. Frontiers in Plant Science 2023. doi:10.3389/fpls.2023.1063983

Other claims from this paper (6)

Method / resource Larger training sets moderately improved grain yield predictions.
Method / resource Adding days to heading, ear density or height generally lowered BIC relative to NDVI alone.
Method / resource NDVI plus days to heading reduced prediction RMSE by 10%.
Method / resource NDVI and added traits were unreliable yield predictors in wheat landraces.
Recommendation Conventional yield quantification was recommended for wheat landraces.
Mechanism NDVI saturation and underestimation may reflect yield component differences it cannot detect.

“yield decrease”

Claim types

Direction of the findings

Over time

Claim type

Research area

Polarity

Statistics