Estimation Model of Potassium Content in Cotton Leaves Based on Wavelet Decomposition Spectra and Image Combination Features
Potassium (K) is one of the most important elements influencing cotton metabolism, quality, and yield. Due to the characteristics of strong fluidity and fast redistribution of the K in plants, it leads to rapid transformation of the K lack or abundance in plant leaves; therefore, rapid and accurate...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-07-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2022.920532/full |
| _version_ | 1811292158369464320 |
|---|---|
| author | Qiushuang Yao Ze Zhang Xin Lv Xiangyu Chen Lulu Ma Cong Sun |
| author_facet | Qiushuang Yao Ze Zhang Xin Lv Xiangyu Chen Lulu Ma Cong Sun |
| author_sort | Qiushuang Yao |
| collection | DOAJ |
| description | Potassium (K) is one of the most important elements influencing cotton metabolism, quality, and yield. Due to the characteristics of strong fluidity and fast redistribution of the K in plants, it leads to rapid transformation of the K lack or abundance in plant leaves; therefore, rapid and accurate estimation of potassium content in leaves (LKC, %) is a necessary prerequisite to solve the regulation of plant potassium. In this study, we concentrated on the LKC of cotton in different growth stages, an estimation model based on the combined characteristics of wavelet decomposition spectra and image was proposed, and discussed the potential of different combined features in accurate estimation of the LKC. We collected hyperspectral imaging data of 60 main-stem leaves at the budding, flowering, and boll setting stages of cotton, respectively. The original spectrum (R) is decomposed by continuous wavelet transform (CWT). The competitive adaptive reweighted sampling (CARS) and random frog (RF) algorithms combined with partial least squares regression (PLSR) model were used to determine the optimal decomposition scale and characteristic wavelengths at three growth stages. Based on the best “CWT spectra” model, the grayscale image databases were constructed, and the image features were extracted by using color moment and gray level co-occurrence matrix (GLCM). The results showed that the best decomposition scales of the three growth stages were CWT-1, 3, and 9. The best growth stage for estimating LKC in cotton was the boll setting stage, with the feature combination of “CWT-9 spectra + texture,” and its determination coefficients (R2val) and root mean squared error (RMSEval) values were 0.90 and 0.20. Compared with the single R model (R2val = 0.66, RMSEval = 0.34), the R2val increased by 0.24. Different from our hypothesis, the combined feature based on “CWT spectra + color + texture” cannot significantly improve the estimation accuracy of the model, it means that the performance of the estimation model established with more feature information is not correspondingly better. Moreover, the texture features contributed more to the improvement of model performance than color features did. These results provide a reference for rapid and non-destructive monitoring of the LKC in cotton. |
| first_indexed | 2024-04-13T04:41:14Z |
| format | Article |
| id | doaj.art-2ec0da1775764851957605c28cdd2a98 |
| institution | Directory Open Access Journal |
| issn | 1664-462X |
| language | English |
| last_indexed | 2024-04-13T04:41:14Z |
| publishDate | 2022-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj.art-2ec0da1775764851957605c28cdd2a982022-12-22T03:01:59ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2022-07-011310.3389/fpls.2022.920532920532Estimation Model of Potassium Content in Cotton Leaves Based on Wavelet Decomposition Spectra and Image Combination FeaturesQiushuang YaoZe ZhangXin LvXiangyu ChenLulu MaCong SunPotassium (K) is one of the most important elements influencing cotton metabolism, quality, and yield. Due to the characteristics of strong fluidity and fast redistribution of the K in plants, it leads to rapid transformation of the K lack or abundance in plant leaves; therefore, rapid and accurate estimation of potassium content in leaves (LKC, %) is a necessary prerequisite to solve the regulation of plant potassium. In this study, we concentrated on the LKC of cotton in different growth stages, an estimation model based on the combined characteristics of wavelet decomposition spectra and image was proposed, and discussed the potential of different combined features in accurate estimation of the LKC. We collected hyperspectral imaging data of 60 main-stem leaves at the budding, flowering, and boll setting stages of cotton, respectively. The original spectrum (R) is decomposed by continuous wavelet transform (CWT). The competitive adaptive reweighted sampling (CARS) and random frog (RF) algorithms combined with partial least squares regression (PLSR) model were used to determine the optimal decomposition scale and characteristic wavelengths at three growth stages. Based on the best “CWT spectra” model, the grayscale image databases were constructed, and the image features were extracted by using color moment and gray level co-occurrence matrix (GLCM). The results showed that the best decomposition scales of the three growth stages were CWT-1, 3, and 9. The best growth stage for estimating LKC in cotton was the boll setting stage, with the feature combination of “CWT-9 spectra + texture,” and its determination coefficients (R2val) and root mean squared error (RMSEval) values were 0.90 and 0.20. Compared with the single R model (R2val = 0.66, RMSEval = 0.34), the R2val increased by 0.24. Different from our hypothesis, the combined feature based on “CWT spectra + color + texture” cannot significantly improve the estimation accuracy of the model, it means that the performance of the estimation model established with more feature information is not correspondingly better. Moreover, the texture features contributed more to the improvement of model performance than color features did. These results provide a reference for rapid and non-destructive monitoring of the LKC in cotton.https://www.frontiersin.org/articles/10.3389/fpls.2022.920532/fullhyperspectral imagingpotassium content in leavescontinuous wavelet transformgray level co-occurrence matrixcottongrowth stage |
| spellingShingle | Qiushuang Yao Ze Zhang Xin Lv Xiangyu Chen Lulu Ma Cong Sun Estimation Model of Potassium Content in Cotton Leaves Based on Wavelet Decomposition Spectra and Image Combination Features Frontiers in Plant Science hyperspectral imaging potassium content in leaves continuous wavelet transform gray level co-occurrence matrix cotton growth stage |
| title | Estimation Model of Potassium Content in Cotton Leaves Based on Wavelet Decomposition Spectra and Image Combination Features |
| title_full | Estimation Model of Potassium Content in Cotton Leaves Based on Wavelet Decomposition Spectra and Image Combination Features |
| title_fullStr | Estimation Model of Potassium Content in Cotton Leaves Based on Wavelet Decomposition Spectra and Image Combination Features |
| title_full_unstemmed | Estimation Model of Potassium Content in Cotton Leaves Based on Wavelet Decomposition Spectra and Image Combination Features |
| title_short | Estimation Model of Potassium Content in Cotton Leaves Based on Wavelet Decomposition Spectra and Image Combination Features |
| title_sort | estimation model of potassium content in cotton leaves based on wavelet decomposition spectra and image combination features |
| topic | hyperspectral imaging potassium content in leaves continuous wavelet transform gray level co-occurrence matrix cotton growth stage |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2022.920532/full |
| work_keys_str_mv | AT qiushuangyao estimationmodelofpotassiumcontentincottonleavesbasedonwaveletdecompositionspectraandimagecombinationfeatures AT zezhang estimationmodelofpotassiumcontentincottonleavesbasedonwaveletdecompositionspectraandimagecombinationfeatures AT xinlv estimationmodelofpotassiumcontentincottonleavesbasedonwaveletdecompositionspectraandimagecombinationfeatures AT xiangyuchen estimationmodelofpotassiumcontentincottonleavesbasedonwaveletdecompositionspectraandimagecombinationfeatures AT luluma estimationmodelofpotassiumcontentincottonleavesbasedonwaveletdecompositionspectraandimagecombinationfeatures AT congsun estimationmodelofpotassiumcontentincottonleavesbasedonwaveletdecompositionspectraandimagecombinationfeatures |