Abstract
Introduction: Rapid and accurate estimation of leaf area index (LAI) is of great significance for the precision agriculture because LAI is an important parameter to evaluate crop canopy structure and growth status. Methods: In this study, 20 vegetation indices were constructed by using cotton canopy spectra. Then, cotton LAI estimation models were constructed based on multiple machine learning (ML) methods extreme learning machine (ELM), random forest (RF), back propagation (BP), multivariable linear regression (MLR), support vector machine (SVM)], and the optimal modeling strategy (RF) was selected. Finally, the vegetation indices with a high correlation with LAI were fused to construct the VI-fusion RF model, to explore the potential of multi-vegetation index fusion in the estimation of cotton LAI. Results: The RF model had the highest estimation accuracy among the LAI estimation models, and the estimation accuracy of models constructed by fusing multiple VIs was higher than that of models constructed based on single VIs. Among the multi-VI fusion models, the RF model constructed based on the fusion of seven vegetation indices (MNDSI, SRI, GRVI, REP, CIred-edge, MSR, and NVI) had the highest estimation accuracy, with coefficient of determination (R2), rootmean square error (RMSE), normalized rootmean square error (NRMSE), and mean absolute error (MAE) of 0.90, 0.50, 0.14, and 0.26, respectively. Discussion: Appropriate fusion of vegetation indices can include more spectral features in modeling and significantly improve the cotton LAI estimation accuracy. This study will provide a technical reference for improving the cotton LAI estimation accuracy, and the proposed method has great potential for crop growth monitoring applications.
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 6
Claim · model-written summary
The random forest model had the highest cotton LAI estimation accuracy among the LAI estimation models tested.
- Taxon
- cotton
Gossypium hirsutumt0 - Outcome
- estimation accuracye0
- Direction
- higheste0
- Comparator
- among the LAI estimation modelse0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“cotton leaf area prediction”
e0“The RF model had the highest estimation accuracy among the LAI estimation models”
Claim · model-written summary
The RF model fusing seven vegetation indices had the highest estimation accuracy among multi-VI fusion models, with R2 of 0.90.
- Taxon
- cottonGossypium hirsutumt0
- Outcome
- coefficient of determination (R2)e1
- Direction
- higheste1
- Value
- 0.90e1
- Comparator
- the multi-VI fusion modelse1
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“cotton leaf area prediction”
e1“Among the multi-VI fusion models, the RF model constructed based on the fusion of seven vegetation indices (MNDSI, SRI, GRVI, REP, CIred-edge, MSR, and NVI) had the highest estimation accuracy, with coefficient of determination (R2), rootmean square error (RMSE), normalized rootmean square error (NRMSE), and mean absolute error (MAE) of 0.90, 0.50, 0.14, and 0.26, respectively”
Claim · model-written summary
The RF model fusing seven vegetation indices had an RMSE of 0.50 for cotton LAI estimation.
- Taxon
- cottonGossypium hirsutumt0
- Outcome
- rootmean square error (RMSE)e1
- Value
- 0.50e1
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“cotton leaf area prediction”
e1“Among the multi-VI fusion models, the RF model constructed based on the fusion of seven vegetation indices (MNDSI, SRI, GRVI, REP, CIred-edge, MSR, and NVI) had the highest estimation accuracy, with coefficient of determination (R2), rootmean square error (RMSE), normalized rootmean square error (NRMSE), and mean absolute error (MAE) of 0.90, 0.50, 0.14, and 0.26, respectively”
Claim · model-written summary
The RF model fusing seven vegetation indices had an NRMSE of 0.14 for cotton LAI estimation.
- Taxon
- cottonGossypium hirsutumt0
- Outcome
- normalized rootmean square error (NRMSE)e1
- Value
- 0.14e1
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“cotton leaf area prediction”
e1“Among the multi-VI fusion models, the RF model constructed based on the fusion of seven vegetation indices (MNDSI, SRI, GRVI, REP, CIred-edge, MSR, and NVI) had the highest estimation accuracy, with coefficient of determination (R2), rootmean square error (RMSE), normalized rootmean square error (NRMSE), and mean absolute error (MAE) of 0.90, 0.50, 0.14, and 0.26, respectively”
Claim · model-written summary
The RF model fusing seven vegetation indices had an MAE of 0.26 for cotton LAI estimation.
- Taxon
- cottonGossypium hirsutumt0
- Outcome
- mean absolute error (MAE)e1
- Value
- 0.26e1
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“cotton leaf area prediction”
e1“Among the multi-VI fusion models, the RF model constructed based on the fusion of seven vegetation indices (MNDSI, SRI, GRVI, REP, CIred-edge, MSR, and NVI) had the highest estimation accuracy, with coefficient of determination (R2), rootmean square error (RMSE), normalized rootmean square error (NRMSE), and mean absolute error (MAE) of 0.90, 0.50, 0.14, and 0.26, respectively”
Claim · model-written summary
Models fusing multiple vegetation indices had higher cotton LAI estimation accuracy than models based on single indices.
- Taxon
- cottonGossypium hirsutumt0
- Outcome
- estimation accuracye2
- Direction
- highere2
- Comparator
- models constructed based on single VIse2
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“cotton leaf area prediction”
e2“the estimation accuracy of models constructed by fusing multiple VIs was higher than that of models constructed based on single VIs”