Abstract
The monitoring of winter wheat Fusarium head blight via rapid and non-destructive measures is important for agricultural production and disease control. Images of unmanned aerial vehicles (UAVs) are particularly suitable for the monitoring of wheat diseases because they feature high spatial resolution and flexible acquisition time. This study evaluated the potential to monitor Fusarium head blight via UAV hyperspectral imagery. The field site investigated by this study is located in Lujiang County, Anhui Province, China. The hyperspectral UAV images were acquired on 3 and 8 May 2019, when wheat was at the grain filling stage. Several features, including original spectral bands, vegetation indexes, and texture features, were extracted from these hyperspectral images. Based on these extracted features, univariate Fusarium monitoring models were developed, and backward feature selection was applied to filter these features. The backpropagation (BP) neural network was improved by integrating a simulated annealing algorithm in the experiment. A multivariate Fusarium head blight monitoring model was developed using the improved BP neural network. The results showed that bands in the red region provide important information for discriminating between wheat canopies that are either slightly or severely Fusarium-head-blight-infected. The modified chlorophyll absorption reflectance index performed best among all features, with an area under the curve and standard deviation of 1.0 and 0.0, respectively. Five commonly used methods were compared with this improved BP neural network. The results showed that the developed Fusarium head blight monitoring model achieved the highest overall accuracy of 98%. In addition, the difference between the producer accuracy and user accuracy of the improved BP neural network was smallest among all models, indicating that this model achieved better stability. These results demonstrate that hyperspectral images of UAVs can be used to monitor Fusarium head blight in winter wheat.
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 5
Claim · model-written summary
Red bands distinguished slight from severe Fusarium head blight infection in wheat canopies.
- Taxon
- wheat
Triticum aestivume0 - Outcome
- discriminating between wheat canopies that are either slightly or severely Fusarium-head-blight-infectede0
- Comparator
- slightly or severely Fusarium-head-blight-infectede0
FusariumOrganisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“bands in the red region provide important information for discriminating between wheat canopies that are either slightly or severely Fusarium-head-blight-infected”
Claim · model-written summary
The modified chlorophyll absorption reflectance index was the best feature, with AUC 1.0 and standard deviation 0.0.
- Taxon
- WheatTriticum aestivumt0
- Outcome
- area under the curve and standard deviatione0
- Direction
- beste0
- Value
- 1.0 and 0.0e0
- Comparator
- all featurese0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“The modified chlorophyll absorption reflectance index performed best among all features, with an area under the curve and standard deviation of 1.0 and 0.0, respectively”
t0“Wheat”
Claim · model-written summary
The developed monitoring model had the highest overall accuracy, 98%, among the compared methods.
- Taxon
- WheatTriticum aestivumt0
- Outcome
- overall accuracye0
- Direction
- higheste0
- Value
- 98%e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“The results showed that the developed Fusarium head blight monitoring model achieved the highest overall accuracy of 98%”
t0“Wheat”
Claim · model-written summary
The improved BP neural network had the smallest difference between producer and user accuracy, indicating better stability.
- Taxon
- WheatTriticum aestivumt0
- Outcome
- difference between the producer accuracy and user accuracye0
- Direction
- smalleste0
- Comparator
- all modelse0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“the difference between the producer accuracy and user accuracy of the improved BP neural network was smallest among all models, indicating that this model achieved better stability”
t0“Wheat”
Claim · model-written summary
UAV hyperspectral images can monitor Fusarium head blight in winter wheat.
- Taxon
- wheatTriticum aestivume0
- Outcome
- monitor Fusarium head blighte0
Not reportedComparatorValue
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“hyperspectral images of UAVs can be used to monitor Fusarium head blight in winter wheat”