Search claims · PlantClaims

Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

The crop models showed strong predictive accuracy.

Taxon: maizeZea mayst0
Outcome: strong predictive accuracye0

Not reportedComparatorValue

Verbatim

e0
“The models showed strong predictive accuracy”
✓ located verbatim in the source · abstract, characters 543–587

t0
“maize”
✓ located verbatim in the source · title, characters 10–15

Title

Customize maize production technology in Central Thailand using crop model

Supaporn Sukto; Chaiya Boonlert; Warakorn Ruankaew; et al. Agrica 2025. doi:10.5958/2394-448x.2025.00003.0

Other claims from this paper (5)

Method / resource Soil test based fertilization was identified as an effective practice.
Method / resource October to December was identified as the ideal planting period.
Method / resource Population density of 66,663 to 88,888 plants per hectare was identified as effective.
Intervention effect Field trials increased maize yield by 12.3%–18.72% relative to traditional practices.
Intervention effect Field trials raised profit by 22.41%–42.34% relative to traditional practices.

Observationobservedoriginal resultmeasured

Claim · model-written summary

Spatial predictive accuracy varied by site and year.

Taxon: peaLathyrus oleraceust0
Outcome: predictive accuracye0
Direction: variede0

Verbatim

e0
“predictive accuracy varied by site and year”
✓ located verbatim in the source · abstract, characters 1245–1288

t0
“pea”
✓ located verbatim in the source · title, characters 45–48

Title

Combining phenomic and genomic selection for pea breeding improvement

Anthony Klein; Virgilio Freitas; Abdou Wade; et al. The Plant Phenome Journal 2026. doi:10.1002/ppj2.70076

Other claims from this paper (4)

Method / resource Phenomic selection predicted yield as effectively as genomic selection.
Method / resource The integrative model had the highest accuracy for most traits, including seed yield and seed protein yield.
Method / resource Same-year spectral data gave the most accurate temporal predictions.
Method / resource Combined phenomic-genomic models outperformed univariate models in spatial predictions.

Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

Neural Network had the highest predictive accuracy.

Outcome: predictive accuracye0
Direction: higheste0
Comparator: Neural Networke0

Not reportedTaxon

Verbatim

e0
“the Neural Network showing the highest predictive accuracy”
✓ located verbatim in the source · abstract, characters 1402–1460

Title

Image-based modeling in the selection of cowpea genotypes for aluminum tolerance1

Uasley Caldas de Oliveira; Janderson do Carmo Lima; Robson de Jesus Santos; et al. Pesquisa Agropecuária Tropical 2025. doi:10.1590/1983-40632025v5582693

Other claims from this paper (8)

Observation Aluminum tolerance varied significantly among cowpea genotypes.
Observation MNC06-908-39 and MNC06-895-1 were classified as most sensitive.
Observation MNC06-907-29 and MNC06-901-14 showed higher tolerance.
Observation CB-27 was the most tolerant overall.
Observation MNC06-909-54, MNC06-909-55, MNC06-907-35, MNC06-908-39 and MNC06-909-76 were rated most sensitive.
Method / resource Quantitative dye analysis confirmed greater tolerance of MNC06-907-29 and MNC06-901-14.
Method / resource Quantitative dye analysis confirmed MNC06-908-39 and MNC06-895-1 as most sensitive.
Method / resource Predictive algorithms showed genetic variability in aluminum response.

Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

The models had reliable predictive accuracy across populations.

Taxon: maizeZea mayst0
Outcome: predictive accuracye0
Comparator: different populationse0

Verbatim

e0
“The models show reliable predictive accuracy on different populations”
✓ located verbatim in the source · abstract, characters 1996–2065

t0
“maize genomic selection”
✓ located verbatim in the source · title, characters 55–78

Title

AutoGP: An intelligent breeding platform for enhancing maize genomic selection

Hao Wu; Rui Han; Liang Zhao; et al. Plant Communications 2025. doi:10.1016/j.xplc.2025.101240

Other claims from this paper (2)

Method / resource AutoGP provides genotype extraction, phenotype extraction and genomic selection models in a web interface.
Method / resource The genotype chips extracted high-quality SNPs associated with days to tasseling and plant height.

Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

Certification found 94.2% predictive accuracy against an 87% target.

Taxon: PeachPrunus persicat0
Outcome: predictive accuracye0
Value: 94.2 %e0
Comparator: ≥87%e0

Verbatim

e0
“including≥87% predictive accuracy (achieved at 94.2 %)”
✓ located verbatim in the source · abstract, characters 1040–1094

t0
“Peach”
✓ located verbatim in the source · title, characters 10–15

Title

Proactive Peach Pest Control: Image Analysis and Real-Time Environmental Method

Hyunwook Kim; Hyun Sim International Journal on Advanced Science Engineering and Information Technology 2025. doi:10.18517/ijaseit.15.4.21218

Other claims from this paper (6)

Method / resource The CNN classified peach pests and diseases with 92% accuracy.
Method / resource The integrated system increased early detection by 10% over image-only baselines.
Method / resource The system warned an average of three days before visible symptoms.
Intervention effect Targeted interventions reduced chemical use and damage.
Method / resource Certified image analysis completed within 20 seconds.
Method / resource Certified sensor processing completed within one minute.

Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

The crop recommendation model showed high predictive accuracy.

Taxon: crope1
Outcome: predictive accuracye0

Not reportedComparatorValue

Verbatim

e0
“Our model demonstrates both high predictive accuracy”
✓ located verbatim in the source · abstract, characters 616–668

e1
“smart crop recommendation system”
✓ located verbatim in the source · abstract, characters 134–166

Title

Optimizing Crop Recommendations for Sustainable Agriculture: Leveraging Bayesian Networks in a Smart Crop Recommendation System

Nazia Sharmin; Christopher Kiekintveld 2023 20th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON) 2023. doi:10.1109/secon58729.2023.10287510

Other claims from this paper (1)

Method / resource The crop recommendation model adapted to existing structures and learning algorithms.

Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

Predictive analytics forecast environmental conditions with 92% accuracy.

Outcome: accuracye0
Value: 92%e0

Not reportedTaxonDirection

Verbatim

e0
“the predictive analytics component achieves an accuracy of 92% in forecasting environmental conditions”
✓ located verbatim in the source · abstract, characters 844–946

Title

IoT-Based Smart Agricultural Monitoring Using WSN and Predictive Analytics with Artificial Intelligence (AI)

K. K.; Senior Manager, TVR Consulting Services Private Limited Gajularamaram, Medchal Malkangiri district, Hyderabad - 500055, Telegana, India; Tatiraju V. Rajani Kanth; et al. International Journal of BIM and Engineering Science 2024. doi:10.54216/ijbes.100104

Other claims from this paper (2)

Method / resource The system enhanced resource usage by 40% relative to traditional farming methods.
Method / resource The system increased crop yield by 30% relative to traditional farming methods.

Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

Model validation found high predictive accuracy, especially for droplet size.

Outcome: predictive accuracye0

Not reportedComparatorValue

Verbatim

e0
“Model validation confirmed high predictive accuracy, particularly for droplet size”
✓ located verbatim in the source · abstract, characters 731–813

Title

Nanoemulsion design of Cynara cardunculus leaves extract rich in sesquiterpene lactones

Daniela Rosa; Carlos Rial; Miguel Palma; et al. Pest Management Science 2026. doi:10.1002/ps.70541

Other claims from this paper (6)

Method / resource Droplet-size modeling identified ultrasound amplitude as significant.
Method / resource Zeta-potential modeling identified Tween®80 content as significant.
Intervention effect The nanoemulsion increased phytotoxic activity against three weed species at least threefold versus crude extract, especially root inhibition.
Observation P. oleracea was the most sensitive species and the nanoemulsion outperformed commercial herbicide at 400–800 ppm.
Observation The nanoemulsion was physically stable for 90 days at 4 and 25 °C.
Observation The nanoemulsion degraded significantly at 45 °C.

Method / resourceobservedoriginal resultpositivesignificant (as stated)measured

Claim · model-written summary

AI models significantly improved predictive accuracy for legume crop yields compared with conventional models.

Taxon: Legumet0
Outcome: predictive accuracye0
Direction: enhancemente0
Comparator: conventional modelse0

Verbatim

e0
“significant enhancement in predictive accuracy compared to conventional models”
✓ located verbatim in the source · abstract, characters 731–809

t0
“Legume Crop Yields”
✓ located verbatim in the source · title, characters 35–53

Title

AI-Powered Predictive Modelling of Legume Crop Yields in a Changing Climate

Myung Hwan Na; In Seop Na Legume Research - An International Journal 2024. doi:10.18805/lrf-790

Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

CentriVision achieved high predictive accuracy when applied to representative plant species.

Taxon: representative plant speciese0
Outcome: predictive accuracye0
Value: highe0

Verbatim

e0
“When applied to representative plant species, CentriVision achieved high predictive accuracy”
✓ located verbatim in the source · abstract, characters 877–969

Title

CentriVision: An integrated platform for multiscale centromere analysis in plants

Mei-Fang Lan; Xi-Yin Wang; Xian-Chun Zhang Plant Communications 2025. doi:10.1016/j.xplc.2025.101689

Other claims from this paper (7)

“predictive accuracy”

Claim types

Direction of the findings

Over time

Claim type

Research area

Polarity

Statistics