Abstract
• In estimating LAI, the combination of image types affects the accuracy. • EVI2 outperforms other indices for LAI estimation in a mono-regression. • Two or three image types provide more accurate estimates than a single image type. • Increasing the number of image types further does not appear to be effective. This study aims to evaluate whether the utilization of a broader array of image types and the extraction of plant canopy using RGB and multispectral cameras mounted on unmanned aerial vehicles (UAVs) can improve leaf area index (LAI) estimation accuracy. The accuracy of LAI estimation for sweet potato was compared across different model types—mono-regression models based on a single image, multivariate regression models based on a single type of image, and multivariate regression models based on multiple image types—by employing 10 types of images based on color, morphological indices, vegetation indices (VIs) from RGB cameras, reflectance, VIs from multispectral cameras, and each of their canopy part image. For each regression model, we compared the estimation accuracy based on the whole image with that based on the canopy part image. For the mono-regression model, EVI2 from the whole image exhibited the lowest test root mean squared error (RMSE) of 0.403, which is attributed to EVI2’s capacity to mitigate the effects of spectral saturation. Contrary to the models with multiple image types that demonstrated improved accuracy, the multivariate regression models based on a single image type did not enhance estimation accuracy; this shows that the use of multiple image types improves the LAI estimation accuracy owing to the synergy of different spectral information from various image types. Plant canopy extraction did not enhance the estimation accuracy in mono-regression models or multivariate regression models based on a single image type; however, it improved the accuracy of multivariate regression models based on multiple image types, provided the image types were appropriately combined. The highest estimation accuracy was achieved by a partial least squares regression model based on VI (from the RGB camera) and reflectance (from the multispectral camera) of the canopy part (test R 2 = 0.887, test RMSE = 0.351), suggesting that this is an effective approach for LAI estimation in sweet potato (cultivar Beniharuka ). Overall, this study demonstrates that an optimal combination of image type and plant canopy extraction can enhance LAI estimation accuracy in UAV-based monitoring.
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 7
Claim · model-written summary
In mono-regression, EVI2 from the whole image gave the lowest test RMSE (0.403) for sweet potato LAI estimation.
- Taxon
- sweet potato
_Flower.jpg?width=60)
Ipomoea batatast0 - Outcome
- lowest test root mean squared error (RMSE)e1
- Direction
- loweste1
- Value
- 0.403e1
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
_Flower.jpg?width=500)
Verbatim
t0“sweet potato”
e1“For the mono-regression model, EVI2 from the whole image exhibited the lowest test root mean squared error (RMSE) of 0.403”
Claim · model-written summary
EVI2 mitigating the effects of spectral saturation is given by the authors as the explanation for its lowest test RMSE in mono-regression.
- Taxon
- sweet potatoIpomoea batatast0
- Outcome
- lowest test root mean squared error (RMSE)e1
- Qualifier
- capacity to mitigate the effects of spectral saturatione2
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“sweet potato”
e1“For the mono-regression model, EVI2 from the whole image exhibited the lowest test root mean squared error (RMSE) of 0.403”
e2“which is attributed to EVI2’s capacity to mitigate the effects of spectral saturation”
Claim · model-written summary
Two or three image types gave more accurate LAI estimates than a single image type.
- Taxon
- sweet potatoIpomoea batatast0
- Outcome
- more accurate estimatese1
- Direction
- more accuratee1
- Comparator
- a single image typee1
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“sweet potato”
e1“Two or three image types provide more accurate estimates than a single image type”
Claim · model-written summary
Multivariate regression models based on a single image type did not enhance LAI estimation accuracy.
- Taxon
- sweet potatoIpomoea batatast0
- Outcome
- estimation accuracye1
- Direction
- did not enhancee1
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“sweet potato”
e1“the multivariate regression models based on a single image type did not enhance estimation accuracy”
Claim · model-written summary
Plant canopy extraction did not enhance LAI estimation accuracy in mono-regression models or in multivariate models based on a single image type, compared with the whole image.
- Taxon
- sweet potatoIpomoea batatast0
- Treatment
- Plant canopy extractione1
- Outcome
- estimation accuracye1
- Direction
- did not enhancee1
- Comparator
- whole imagee2
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“sweet potato”
e1“Plant canopy extraction did not enhance the estimation accuracy in mono-regression models or multivariate regression models based on a single image type”
e2“we compared the estimation accuracy based on the whole image with that based on the canopy part image”
Claim · model-written summary
Plant canopy extraction improved the accuracy of multivariate models based on multiple image types, provided the image types were appropriately combined.
- Taxon
- sweet potatoIpomoea batatast0
- Treatment
- Plant canopy extractione1
- Outcome
- accuracy of multivariate regression models based on multiple image typese1
- Direction
- improvede1
- Qualifier
- provided the image types were appropriately combinede1
- Comparator
- whole imagee2
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“sweet potato”
e1“Plant canopy extraction did not enhance the estimation accuracy in mono-regression models or multivariate regression models based on a single image type; however, it improved the accuracy of multivariate regression models based on multiple image types, provided the image types were appropriately combined”
e2“we compared the estimation accuracy based on the whole image with that based on the canopy part image”
Claim · model-written summary
A partial least squares model using RGB-camera VI and multispectral reflectance of the canopy part gave the highest LAI estimation accuracy (test R2 = 0.887, test RMSE = 0.351).
- Taxon
- sweet potatoIpomoea batatast0
- Outcome
- highest estimation accuracye1
- Value
- test R 2 = 0.887, test RMSE = 0.351e1
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“sweet potato”
e1“The highest estimation accuracy was achieved by a partial least squares regression model based on VI (from the RGB camera) and reflectance (from the multispectral camera) of the canopy part (test R 2 = 0.887, test RMSE = 0.351)”