“yield decrease”

Claim · model-written summary

The authors report that machine learning can improve agricultural efficiency and reduce risk in crop production.

Taxon

Cropt0

Outcome

agricultural efficiencye0

Direction

booste0

Not reportedComparatorValue

Verbatim

e0

“The results illustrate the ability of machine learning to boost agricultural efficiency, decrease risks, enhance food security, and encourage sustainable farming methods.”

t0

“Crop Yield Prediction”

Claim · model-written summary

Cloud-connected CNN robotic harvesting was reported to enhance agricultural productivity, decrease labor expenses and enhance operational efficiency for fruit and nut crops.

Taxon

fruit and nut cropse0

Treatment

cloud-connected robotic devices with convolutional neural network (CNN) based vision systemse2

Outcome

agricultural productivitye4

Direction

enhancinge4

Comparator

Conventional harvesting techniquese1

Schema note from the model: comparator is the conventional harvesting named in the background sentence; the abstract gives no explicit numeric comparison

Verbatim

e0

“improving the productivity of fruit and nut crops”

e1

“Conventional harvesting techniques often encounter inefficiencies”

e2

“utilizes cloud-connected robotic devices with convolutional neural network (CNN) based vision systems”

e4

“we provide evidence of the efficacy of our method in enhancing agricultural productivity, decreasing labor expenses, and enhancing overall operational efficiency”

Claim · model-written summary

With sufficient basal fertilizer, the THP method maintained winter wheat yield as much as the TLF method.

Taxon

Winter WheatTriticum aestivumt0

Outcome

yielde0

Direction

maintainede0

Comparator

TLF methode0

Verbatim

e0

“the THP method followed the TRL and TLZ methods to reduce NFT but maintained as much yield as the TLF method with a decrease of NFT by 4.20%”

t0

“Topdressing for Winter Wheat”

Claim · model-written summary

With sufficient basal fertilizer, the THP method decreased topdressing N (NFT) by 4.20% relative to the TLF method in winter wheat.

Taxon

Winter WheatTriticum aestivumt0

Outcome

NFTe0

Direction

decreasee0

Value

4.20%e0

Comparator

TLF methode0

Verbatim

e0

“the THP method followed the TRL and TLZ methods to reduce NFT but maintained as much yield as the TLF method with a decrease of NFT by 4.20%”

t0

“Topdressing for Winter Wheat”

Claim · model-written summary

Machine learning methods can reduce citrus yield-estimation error and field measurement needs, cost and time.

Taxon

citrusCitrust0

Outcome

estimation errore0

Direction

reducee0

Not reportedComparatorValue

Verbatim

e0

“Machine learning techniques were applied to predict yield; these methods can reduce the estimation error as well as decrease the need for in-field measuring, thus reducing both the cost and time of the process”

t0

“citrus”

Claim · model-written summary

The proposed multi-temporal model decreased RMSE by 0.020–0.080 relative to previous methods.

Taxon

ratoon ricet0

Treatment

our proposed multi- temporal methode0

Outcome

RMSEe0

Direction

decreasee0

Value

0.020–0.080e0

Comparator

previous multi-temporal UAV-based methodse0

Verbatim

e0

“compared with previous multi-temporal UAV-based methods, our proposed multi- temporal method (multi-temporal model VIs & Tex: R2 as 0.795, RMSE as 0.298, RRMSE as 0.072) can increase R2 by 0.020–0.111 and decrease RMSE by 0.020–0.080 in crop yield forecasting”

t0

“ratoon rice”

Claim · model-written summary

Adding Landsat TM data reduced classification standard error from 6% to 5%.

Taxon

Cropt0

Outcome

standard errore0

Direction

decreaseinferrede0

Value

5%e0

Qualifier

6%e0

Comparator

TM was ignorede0

Verbatim

e0

“The standard error was 5% when TM data were included, versus 6% when TM was ignored”

t0

“Crop yield prediction”

Claim · model-written summary

P700 oxidation did not directly detect drought responsible for lower grain yield.

Taxon

riceOryza sativae0

Outcome

detected by P700 oxidatione0

Direction

could not be directly detectede0

Not reportedComparatorValue

Verbatim

e0

“drought stress responsible for a decrease in grain yields could not be directly detected by P700 oxidation in paddy-field-grown rice plants”

Claim · model-written summary

Automatic irrigation did not significantly increase rice yield of about 8 ton hectare−1.

Taxon

riceOryza sativae0

Outcome

rice yielde0

Direction

increasee0

Value

8 ton hectare−1e0

Qualifier

has not provene1

Verbatim

e0

“a significant increase of rice yield (of about 8 ton hectare−1)”

e1

“the automatic system has not proven a decrease of water consumptions (ranging from 2000 to 3700 mm) or a significant increase of rice yield (of about 8 ton hectare−1)”

Claim · model-written summary

Independent sensing and treatment of each 1m2 area decreased large-area wheat nitrogen rates.

Taxon

winter wheatTriticum aestivume1

Outcome

large area N ratese0

Direction

decreasee0

Value

1m2e0

Qualifier

each 1m2 area was sensed and treated independentlye0

Verbatim

e0

“This method of determining in-season fertilizer need has been shown to decrease large area N rates while also increasing wheat grain yields when each 1m2 area was sensed and treated independently.”

e1

“winter wheat (Triticum aestivum L.)”