Abstract
UAV imaging provides an efficient and non-destructive tool for characterizing farm information, but the quality of the UAV model is often affected by the image’s spatial resolution. In this paper, the predictability of models established using UAV multispectral images with different spatial resolutions for nitrogen content of winter wheat was evaluated during the critical growth stages of winter wheat over the period 2021–2022. Feature selection based on UAV image reflectance, vegetation indices, and texture was conducted using the competitive adaptive reweighted sampling, and the random forest machine learning method was used to construct the prediction model with the optimized features. Results showed that model performance increased with decreasing image spatial resolution with a R2, a RMSE, a MAE and a RPD of 0.84, 4.57 g m−2, 2.50 g m−2 and 2.34 (0.01 m spatial resolution image), 0.86, 4.15 g m−2, 2.82 g m−2 and 2.65 (0.02 m), and 0.92, 3.17 g m−2, 2.45 g m−2 and 2.86 (0.05 m), respectively. Further, the transferability of models differed when applied to images with coarser (upscaling) or finer (downscaling) resolutions. For upscaling, the model established with the 0.01 m images had a R2 of 0.84 and 0.89 when applied to images with 0.02 m and 0.05 m resolutions, respectively. For downscaling, the model established with the 0.05 m image features had a R2 of 0.86 and 0.83 when applied to images of 0.01 m and 0.02 m resolutions. Though the image spatial resolution affects image texture features more than the spectral features and the effects of image spatial resolution on model performance and transferability decrease with increasing plant wetness under irrigation treatment, it can be concluded that all the UAV images acquired in this study with different resolutions could achieve good predictions and transferability of the nitrogen content of winter wheat plants.
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 19
Claim · model-written summary
At 0.01 m resolution, nitrogen prediction R2 was 0.84.
- Taxon
- Winter Wheat
Triticum aestivumt0 - Outcome
- R2e0
- Value
- 0.84e0
- Qualifier
- 0.01 m spatial resolution imagee0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Results showed that model performance increased with decreasing image spatial resolution with a R2, a RMSE, a MAE and a RPD of 0.84, 4.57 g m−2, 2.50 g m−2 and 2.34 (0.01 m spatial resolution image)”
t0“Winter Wheat”
Claim · model-written summary
At 0.01 m resolution, RMSE was 4.57 g m−2.
- Taxon
- Winter WheatTriticum aestivumt0
- Outcome
- RMSEe0
- Value
- 4.57 g m−2e0
- Qualifier
- 0.01 m spatial resolution imagee0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“a R2, a RMSE, a MAE and a RPD of 0.84, 4.57 g m−2, 2.50 g m−2 and 2.34 (0.01 m spatial resolution image)”
t0“Winter Wheat”
Claim · model-written summary
At 0.01 m resolution, MAE was 2.50 g m−2.
- Taxon
- Winter WheatTriticum aestivumt0
- Outcome
- MAEe0
- Value
- 2.50 g m−2e0
- Qualifier
- 0.01 m spatial resolution imagee0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“a R2, a RMSE, a MAE and a RPD of 0.84, 4.57 g m−2, 2.50 g m−2 and 2.34 (0.01 m spatial resolution image)”
t0“Winter Wheat”
Claim · model-written summary
At 0.01 m resolution, RPD was 2.34.
- Taxon
- Winter WheatTriticum aestivumt0
- Outcome
- RPDe0
- Value
- 2.34e0
- Qualifier
- 0.01 m spatial resolution imagee0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“a R2, a RMSE, a MAE and a RPD of 0.84, 4.57 g m−2, 2.50 g m−2 and 2.34 (0.01 m spatial resolution image)”
t0“Winter Wheat”
Claim · model-written summary
At 0.02 m resolution, R2 was 0.86.
- Taxon
- Winter WheatTriticum aestivumt0
- Outcome
- R2e0
- Value
- 0.86e0
- Qualifier
- 0.02 me0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“a R2, a RMSE, a MAE and a RPD of 0.84, 4.57 g m−2, 2.50 g m−2 and 2.34 (0.01 m spatial resolution image), 0.86, 4.15 g m−2, 2.82 g m−2 and 2.65 (0.02 m)”
t0“Winter Wheat”
Claim · model-written summary
At 0.02 m resolution, RMSE was 4.15 g m−2.
- Taxon
- Winter WheatTriticum aestivumt0
- Outcome
- RMSEe0
- Value
- 4.15 g m−2e0
- Qualifier
- 0.02 me0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“a R2, a RMSE, a MAE and a RPD of 0.84, 4.57 g m−2, 2.50 g m−2 and 2.34 (0.01 m spatial resolution image), 0.86, 4.15 g m−2, 2.82 g m−2 and 2.65 (0.02 m)”
t0“Winter Wheat”
Claim · model-written summary
At 0.02 m resolution, MAE was 2.82 g m−2.
- Taxon
- Winter WheatTriticum aestivumt0
- Outcome
- MAEe0
- Value
- 2.82 g m−2e0
- Qualifier
- 0.02 me0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“a R2, a RMSE, a MAE and a RPD of 0.84, 4.57 g m−2, 2.50 g m−2 and 2.34 (0.01 m spatial resolution image), 0.86, 4.15 g m−2, 2.82 g m−2 and 2.65 (0.02 m)”
t0“Winter Wheat”
Claim · model-written summary
At 0.02 m resolution, RPD was 2.65.
- Taxon
- Winter WheatTriticum aestivumt0
- Outcome
- RPDe0
- Value
- 2.65e0
- Qualifier
- 0.02 me0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“a R2, a RMSE, a MAE and a RPD of 0.84, 4.57 g m−2, 2.50 g m−2 and 2.34 (0.01 m spatial resolution image), 0.86, 4.15 g m−2, 2.82 g m−2 and 2.65 (0.02 m)”
t0“Winter Wheat”
Claim · model-written summary
At 0.05 m resolution, R2 was 0.92.
- Taxon
- Winter WheatTriticum aestivumt0
- Outcome
- R2e0
- Value
- 0.92e0
- Qualifier
- 0.05 me0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“a R2, a RMSE, a MAE and a RPD of 0.84, 4.57 g m−2, 2.50 g m−2 and 2.34 (0.01 m spatial resolution image), 0.86, 4.15 g m−2, 2.82 g m−2 and 2.65 (0.02 m), and 0.92, 3.17 g m−2, 2.45 g m−2 and 2.86 (0.05 m), respectively.”
t0“Winter Wheat”
Claim · model-written summary
At 0.05 m resolution, RMSE was 3.17 g m−2.
- Taxon
- Winter WheatTriticum aestivumt0
- Outcome
- RMSEe0
- Value
- 3.17 g m−2e0
- Qualifier
- 0.05 me0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“a R2, a RMSE, a MAE and a RPD of 0.84, 4.57 g m−2, 2.50 g m−2 and 2.34 (0.01 m spatial resolution image), 0.86, 4.15 g m−2, 2.82 g m−2 and 2.65 (0.02 m), and 0.92, 3.17 g m−2, 2.45 g m−2 and 2.86 (0.05 m), respectively.”
t0“Winter Wheat”
Claim · model-written summary
At 0.05 m resolution, MAE was 2.45 g m−2.
- Taxon
- Winter WheatTriticum aestivumt0
- Outcome
- MAEe0
- Value
- 2.45 g m−2e0
- Qualifier
- 0.05 me0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“a R2, a RMSE, a MAE and a RPD of 0.84, 4.57 g m−2, 2.50 g m−2 and 2.34 (0.01 m spatial resolution image), 0.86, 4.15 g m−2, 2.82 g m−2 and 2.65 (0.02 m), and 0.92, 3.17 g m−2, 2.45 g m−2 and 2.86 (0.05 m), respectively.”
t0“Winter Wheat”
Claim · model-written summary
At 0.05 m resolution, RPD was 2.86.
- Taxon
- Winter WheatTriticum aestivumt0
- Outcome
- RPDe0
- Value
- 2.86e0
- Qualifier
- 0.05 me0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“a R2, a RMSE, a MAE and a RPD of 0.84, 4.57 g m−2, 2.50 g m−2 and 2.34 (0.01 m spatial resolution image), 0.86, 4.15 g m−2, 2.82 g m−2 and 2.65 (0.02 m), and 0.92, 3.17 g m−2, 2.45 g m−2 and 2.86 (0.05 m), respectively.”
t0“Winter Wheat”
Claim · model-written summary
Upscaling the 0.01 m model to 0.02 m images gave R2 0.84.
- Taxon
- Winter WheatTriticum aestivumt0
- Outcome
- R2e0
- Value
- 0.84e0
- Qualifier
- 0.02 me0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“For upscaling, the model established with the 0.01 m images had a R2 of 0.84 and 0.89 when applied to images with 0.02 m and 0.05 m resolutions, respectively.”
t0“Winter Wheat”
Claim · model-written summary
Upscaling the 0.01 m model to 0.05 m images gave R2 0.89.
- Taxon
- Winter WheatTriticum aestivumt0
- Outcome
- R2e0
- Value
- 0.89e0
- Qualifier
- 0.05 me0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“For upscaling, the model established with the 0.01 m images had a R2 of 0.84 and 0.89 when applied to images with 0.02 m and 0.05 m resolutions, respectively.”
t0“Winter Wheat”
Claim · model-written summary
Downscaling the 0.05 m model to 0.01 m images gave R2 0.86.
- Taxon
- Winter WheatTriticum aestivumt0
- Outcome
- R2e0
- Value
- 0.86e0
- Qualifier
- 0.01 me0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“For downscaling, the model established with the 0.05 m image features had a R2 of 0.86 and 0.83 when applied to images of 0.01 m and 0.02 m resolutions.”
t0“Winter Wheat”
Claim · model-written summary
Downscaling the 0.05 m model to 0.02 m images gave R2 0.83.
- Taxon
- Winter WheatTriticum aestivumt0
- Outcome
- R2e0
- Value
- 0.83e0
- Qualifier
- 0.02 me0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“For downscaling, the model established with the 0.05 m image features had a R2 of 0.86 and 0.83 when applied to images of 0.01 m and 0.02 m resolutions.”
t0“Winter Wheat”
Claim · model-written summary
Spatial resolution affected texture features more than spectral features.
- Taxon
- Winter WheatTriticum aestivumt0
- Outcome
- image texture featurese0
- Direction
- moree0
- Comparator
- spectral featurese0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Though the image spatial resolution affects image texture features more than the spectral features”
t0“Winter Wheat”
Claim · model-written summary
Resolution effects on performance and transferability decreased as irrigated plant wetness increased.
- Taxon
- Winter WheatTriticum aestivumt0
- Treatment
- irrigation treatmente0
- Outcome
- effects of image spatial resolution on model performance and transferabilitye0
- Direction
- decreasee0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“the effects of image spatial resolution on model performance and transferability decrease with increasing plant wetness under irrigation treatment”
t0“Winter Wheat”
Claim · model-written summary
All tested resolutions achieved good winter wheat nitrogen prediction and transferability.
- Taxon
- winter wheatTriticum aestivume0
- Outcome
- predictions and transferability of the nitrogen contente0
- Qualifier
- different resolutionse0
Not reportedValue
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“all the UAV images acquired in this study with different resolutions could achieve good predictions and transferability of the nitrogen content of winter wheat plants.”