Search claims · PlantClaims

Associationobservedoriginal resultno effectmeasured

Claim · model-written summary

Tangerine size did not affect segmentation volume estimation accuracy.

Taxon: tangerinesCitrus reticulatae0
Outcome: accuracy of volume estimation by segmentation methode0
Direction: no effecte0
Qualifier: size of tangerinese0

Not reportedOrgan / stage

Verbatim

e0
“the size of tangerines has no effect on the accuracy of volume estimation by segmentation method.”
✓ located verbatim in the source · abstract, characters 607–704

Title

Determination of Tangerine Volume Using Image Processing Methods

Mostafa Khojastehnazhand; Mahmoud Omid; Ahmad Tabatabaeefar International Journal of Food Properties 2010. doi:10.1080/10942910902894062

Other claims from this paper (2)

Method / resource Segmentation volume estimates did not differ significantly from water displacement measurements.
Method / resource Ellipsoid approximation volume estimates differed significantly from water displacement.

Method / resourceobservedoriginal resultno effectmeasured

Claim · model-written summary

Comparable accuracy of yield estimation was achieved with GS NDVI and UAV NDVI.

Taxon: wheatTriticum aestivume0
Outcome: accuracy of yield estimatione5
Comparator: UAV NDVIe5

Verbatim

e0
“to estimate wheat ( Triticum aestivum L.) yield and protein”
✓ located verbatim in the source · abstract, characters 471–530

e5
“Comparable accuracy of yield estimation was achieved with GS NDVI and UAV NDVI”
✓ located verbatim in the source · abstract, characters 1456–1534

Title

Wheat yield and protein estimation with handheld‐ and UAV‐based reflectance measurements

Olga S. Walsh; Juliet Marshall; Chad Jackson; et al. Agrosystems Geosciences & Environment 2022. doi:10.1002/agg2.20309

Other claims from this paper (7)

Association All in-season parameters were linearly correlated with yield, except for the two parameters below.
Association SPAD at Feekes 5 was not linearly correlated with yield.
Association Biomass weight at Feekes 10 was not linearly correlated with yield.
Association NDVI was strongly correlated with yield, especially at Feekes 5.
Observation Estimation of in-season grain protein remains a challenge.
Association The accuracy of yield prediction was similar for all wheat classes.
Recommendation Hand-held and aerial spectral measurements could be used to prescribe N rates to be applied during tiller formation.

Method / resourceobservedoriginal resultno effectnot significant (as stated)measured

Claim · model-written summary

Adding color and texture to CWT spectra did not significantly improve estimation accuracy.

Taxon: cottonGossypium hirsutumt0
Outcome: estimation accuracye0
Direction: cannot significantly improvee0
Comparator: “CWT spectra + color + texture”e0

Verbatim

e0
““CWT spectra + color + texture” cannot significantly improve the estimation accuracy of the model”
✓ located verbatim in the source · abstract, characters 1887–1984

t0
“Cotton”
✓ located verbatim in the source · title, characters 41–47

Title

Estimation Model of Potassium Content in Cotton Leaves Based on Wavelet Decomposition Spectra and Image Combination Features

Qiushuang Yao; Ze Zhang; Xin Lv; et al. Frontiers in Plant Science 2022. doi:10.3389/fpls.2022.920532

Other claims from this paper (5)

Method / resource Best wavelet decomposition scales at budding, flowering and boll setting were CWT-1, 3 and 9.
Method / resource Boll setting was the best stage for estimating leaf potassium.
Method / resource CWT-9 spectra plus texture achieved R2 0.90 and RMSE 0.20.
Method / resource The combined model increased R2 by 0.24 versus the single R model.
Method / resource Texture features improved performance more than color features.

Method / resourceobservedoriginal resultno effectmeasured

Claim · model-written summary

The MultiCam system achieved accuracy in fruit diameter estimation comparable to the handheld approach.

Taxon: appleMalus domesticae0
Outcome: accuracy in fruit diameter estimatione2
Comparator: handheld approache2

Verbatim

e0
“scan apple trees in an experimental orchard”
✓ located verbatim in the source · abstract, characters 711–754

e2
“the system achieved comparable accuracy in fruit diameter estimation to the handheld approach”
✓ located verbatim in the source · abstract, characters 1164–1257

Title

Mobile Multi-Camera System for 3D Fruit Tree Scanning and Apple Size Estimation

Jordi Gené-Mola; Jochen Hemming; Eduard Gregorio 2025 IEEE International Workshop on Metrology for Agriculture and Forestry (MetroAgriFor) 2025. doi:10.1109/metroagrifor66923.2025.11512577

Other claims from this paper (4)

Observationobservedoriginal resultno effectmeasured

Claim · model-written summary

Multivariate regression models based on a single image type did not enhance LAI estimation accuracy.

Taxon: sweet potatoIpomoea batatast0
Outcome: estimation accuracye1
Direction: did not enhancee1

Verbatim

t0
“sweet potato”
✓ located verbatim in the source · title, characters 95–107

e1
“the multivariate regression models based on a single image type did not enhance estimation accuracy”
✓ located verbatim in the source · abstract, characters 1458–1557

Title

Comparative analysis of RGB and multispectral UAV image data for leaf area index estimation of sweet potato

Shoki Ochiai; Erika Kamada; Ryo Sugiura Smart Agricultural Technology 2024. doi:10.1016/j.atech.2024.100579

Other claims from this paper (6)

Associationobservedoriginal resultno effectnot significant (as stated)measured

Claim · model-written summary

Input groups did not significantly affect corn grain moisture estimation accuracy.

Taxon: CornZea mays subsp. mayst0
Outcome: CGM estimation accuracye0
Comparator: input groupse0

Not reportedDirection

Verbatim

e0
“The CGM estimation accuracy was impacted by the ML model and train-test data split ratio. However, the impact was not significant for the input groups.”
✓ located verbatim in the source · abstract, characters 1786–1937

t0
“Corn Grain Moisture”
✓ located verbatim in the source · title, characters 12–31

Title

Pre-Harvest Corn Grain Moisture Estimation Using Aerial Multispectral Imagery and Machine Learning Techniques

Pius Jjagwe; Abhilash K. Chandel; David Langston Land 2023. doi:10.3390/land12122188

Other claims from this paper (9)

Association Six vegetation indices had the highest correlations with corn grain moisture, with r from 0.68 to 0.80.
Association Corn grain moisture estimation accuracy depended on model and train–test split ratio.
Method / resource RF with REFs+VIs and a 95:5 split performed best on training and entire data.
Method / resource Increasing the train–test split ratio decreased test performance of other models.
Method / resource SVM performed best on test data with a 50:50 split and REFs+VIs inputs.
Method / resource The 95:5 train–test ratio performed best across models.
Method / resource RF was the most stable and consistent model.
Recommendation The authors suggest a 95:5 ratio for smaller or medium-sized datasets.
Recommendation The authors conclude that aerial remote sensing with machine learning could reliably predict pre-harvest corn grain moisture for harvest management.

Method / resourceobservedoriginal resultno effectmeasured

Claim · model-written summary

ASRI (ANDI) had similar LCC estimation accuracy to the range-ASRIs or range-ANDIs.

Outcome: LCC estimation accuracye3
Comparator: range-ASRIs or range-ANDIse3

Verbatim

e3
“We also found the ASRI (ANDI) had similar LCC estimation accuracy as the range-ASRIs or range-ANDIs”
✓ located verbatim in the source · abstract, characters 989–1088

Title

A New Method to Estimate the Leaf Chlorophyll Content From Multiangular Measurements: Anisotropy Index

Zhongqiu Sun; Shan Lu; Kenji Omasa IEEE Transactions on Geoscience and Remote Sensing 2023. doi:10.1109/tgrs.2023.3260308

Other claims from this paper (4)

Method / resource ASRI and ANDI indices have strong linear relationships with leaf chlorophyll content (R2 = 0.88 and 0.89).
Method / resource ASRI gave an independent-dataset estimation error of RMSE 6.39 μg/cm2 for leaf chlorophyll content.
Method / resource ANDI gave an independent-dataset estimation error of RMSE 6.10 μg/cm2 for leaf chlorophyll content.
Association The leaf spectral anisotropy index (ANIX) depended on leaf chlorophyll content.

Method / resourceobservedoriginal resultno effectnot significant (as stated)measured

Claim · model-written summary

Multi-angle and single-camera vertical imaging did not differ significantly in rapeseed biomass estimation accuracy.

Taxon: rapeseede0
Outcome: accuracy of rapeseed biomass estimatione0
Direction: no significant differencee0
Comparator: single-camera vertical imaginge0

Verbatim

e0
“There was no significant difference in the accuracy of rapeseed biomass estimation between multi-angle imaging and single-camera vertical imaging”
✓ located verbatim in the source · abstract, characters 1701–1846

Title

Estimation of feed rapeseed biomass based on multi-angle oblique imaging technique of unmanned aerial vehicle

Jian ZHANG; Tian-Jin XIE; Xiao-Nan WEI; et al. ACTA AGRONOMICA SINICA 2021. doi:10.3724/sp.j.1006.2021.04211

Other claims from this paper (6)

Method / resource Biomass prediction accuracy rose as UAV flight height decreased.
Method / resource At 40 meters, rapeseed biomass estimation performed best in calibration, with r 0.792, RMSE 125.0 g m -2 and RE 13.2%.
Method / resource At 40 meters, validation r was 0.752, RMSE 139.1 g m -2 and RE 15.3%.
Association Higher rapeseed planting density corresponded to smaller actual biomass.
Method / resource Higher rapeseed planting density improved volume-model biomass prediction.
Method / resource At 40 meters the imaging approaches had correlation coefficients 0.772 and 0.742, respectively.

Observationobservedoriginal resultno effectmeasured

Claim · model-written summary

The accuracy of the berry-number estimation models did not depend on increasing the number of canopy features used.

Taxon: grapevineVitist0
Outcome: accuracy of the estimation modelse0
Qualifier: increasing the number of vineyard canopy features usede0

Not reportedDirection

Verbatim

t0
“grapevine”
✓ located verbatim in the source · title, characters 31–40

e0
“The accuracy of the estimation models did not depend on increasing the number of vineyard canopy features used”
✓ located verbatim in the source · abstract, characters 1048–1158

Title

19. Assessing actual number of grapevine berries using linear methods and machine learning

F. Palacios; P. Melo-Pinto; M.P. Diago; et al. Precision agriculture '21 2021. doi:10.3920/978-90-8686-916-9_19

Other claims from this paper (2)

Method / resourceobservedoriginal resultno effectnot significant (as stated)measured

Claim · model-written summary

Dual-angle images did not significantly improve LNA and PNA estimation accuracy over single-angle images.

Taxon: Winter WheatTriticum aestivumt0
Outcome: estimation accuracy for LNA and PNAe0
Direction: did not significantly increasee0
Comparator: single-angle imagese0

Verbatim

e0
“the use of dual-angle images did not significantly increase the estimation accuracy for LNA and PNA compared to the use of single-angle images”
✓ located verbatim in the source · abstract, characters 1734–1876

t0
“Winter Wheat”
✓ located verbatim in the source · title, characters 43–55

Title

Estimation of Nitrogen Nutrition Status in Winter Wheat From Unmanned Aerial Vehicle Based Multi-Angular Multispectral Imagery

Ning Lu; Wenhui Wang; Qiaofeng Zhang; et al. Frontiers in Plant Science 2019. doi:10.3389/fpls.2019.01601

Other claims from this paper (4)

Method / resource CIgreen at -60° gave the best single-angle LNC estimate, R2 0.71 and RMSE 0.34%.
Method / resource CIgreen at -40° gave the best single-angle PNC estimate, R2 0.36 and RMSE 0.29%.
Method / resource Combining -40° and nadir images improved PNC estimation to R2 0.52 and RMSE 0.28%.
Recommendation The authors recommend oblique UAV images for improved wheat nitrogen monitoring.

“estimation accuracy”

Claim types

Direction of the findings

Over time

Claim type

Research area

Polarity

Statistics