Abstract
With the increasing environmental awareness and the demand for sustainable agriculture, herbicide reduction has become an important goal. Accurate and efficient weed detection in soybean fields is the key to test the effectiveness of herbicide application, but current technologies and methods still have some problems in terms of accuracy and efficiency, such as relying on manual detection and poor adaptability to some complex environments. Therefore, in this study, weeding experiments in soybean fields with reduced herbicide application, including four levels, were carried out, and an unmanned aerial vehicle (UAV) was utilized to obtain field images. We proposed a weed detection model—YOLOv7-FWeed—based on improved YOLOv7, adopted F-ReLU as the activation function of the convolution module, and added the MaxPool multihead self-attention (M-MHSA) module to enhance the recognition accuracy of weeds. We continuously monitored changes in soybean leaf area and dry matter weight after herbicide reduction as a reflection of soybean growth at optimal herbicide application levels. The results showed that the herbicide application level of electrostatic spraying + 10% reduction could be used for weeding in soybean fields, and YOLOv7-FWeed was higher than YOLOv7 and YOLOv7-enhanced in all the evaluation indexes. The precision of the model was 0.9496, the recall was 0.9125, the F 1 was 0.9307, and the mAP was 0.9662. The results of continuous monitoring of soybean leaf area and dry matter weight showed that herbicide reduction could effectively control weed growth and would not hinder soybean growth. This study can provide a more accurate, efficient, and intelligent solution for weed detection in soybean fields, thus promoting herbicide reduction and providing guidance for exploring efficient herbicide application techniques.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 8
Claim · model-written summary
YOLOv7-FWeed outperformed YOLOv7 and YOLOv7-enhanced in all evaluation indexes for weed detection in soybean fields.
- Taxon
- soybean
Glycine maxe1 - Outcome
- evaluation indexese2
- Direction
- highere2
- Comparator
- YOLOv7 and YOLOv7-enhancede2
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e1“weeding experiments in soybean fields”
e2“YOLOv7-FWeed was higher than YOLOv7 and YOLOv7-enhanced in all the evaluation indexes”
Claim · model-written summary
YOLOv7-FWeed precision was 0.9496 in soybean fields.
- Taxon
- soybeanGlycine maxe1
- Outcome
- precisione3
- Value
- 0.9496e3
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e1“weeding experiments in soybean fields”
e3“The precision of the model was 0.9496, the recall was 0.9125, the F 1 was 0.9307, and the mAP was 0.9662”
Claim · model-written summary
YOLOv7-FWeed recall was 0.9125 in soybean fields.
- Taxon
- soybeanGlycine maxe1
- Outcome
- recalle3
- Value
- 0.9125e3
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e1“weeding experiments in soybean fields”
e3“The precision of the model was 0.9496, the recall was 0.9125, the F 1 was 0.9307, and the mAP was 0.9662”
Claim · model-written summary
YOLOv7-FWeed F1 score was 0.9307 in soybean fields.
- Taxon
- soybeanGlycine maxe1
- Outcome
- F 1e3
- Value
- 0.9307e3
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e1“weeding experiments in soybean fields”
e3“The precision of the model was 0.9496, the recall was 0.9125, the F 1 was 0.9307, and the mAP was 0.9662”
Claim · model-written summary
YOLOv7-FWeed mAP was 0.9662 in soybean fields.
- Taxon
- soybeanGlycine maxe1
- Outcome
- mAPe3
- Value
- 0.9662e3
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e1“weeding experiments in soybean fields”
e3“The precision of the model was 0.9496, the recall was 0.9125, the F 1 was 0.9307, and the mAP was 0.9662”
Claim · model-written summary
Electrostatic spraying with a 10% herbicide reduction could be used for weeding in soybean fields.
- Taxon
- soybeanGlycine maxe4
- Treatment
- electrostatic spraying + 10% reductione4
- Outcome
- herbicide application levele4
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e4“the herbicide application level of electrostatic spraying + 10% reduction could be used for weeding in soybean fields”
Claim · model-written summary
Herbicide reduction effectively controlled weed growth in soybean fields.
- Taxon
- soybeanGlycine maxe5
- Treatment
- herbicide reductione5
- Interactor
- weede5weed
- Outcome
- weed growthe5
- Direction
- effectively controle5
Not reportedComparator
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e5“herbicide reduction could effectively control weed growth and would not hinder soybean growth”
Claim · model-written summary
Herbicide reduction did not hinder soybean growth.
- Taxon
- soybeanGlycine maxe5
- Treatment
- herbicide reductione5
- Outcome
- soybean growthe5
- Direction
- not hindere5
Not reportedComparator
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e5“herbicide reduction could effectively control weed growth and would not hinder soybean growth”
The same questions in other papers
herbicide · growth · Glycine max (soybean)Positive and negative results
61 papers in the same direction as this paper · 60 in the opposite direction
- positive
- positive
- positive
118 papers more in this group
See all 122 papers →herbicide · weed · Glycine max (soybean)Positive and negative results
257 papers in the same direction as this paper · 26 in the opposite direction · 13 reporting no difference from an alternative
- negative
- negative
- negative
293 papers more in this group
See all 297 papers →Claims are grouped by organism, treatment and what was measured or targeted. A paper counts as positive when any of its claims in the group is positive.