
High Quality Ramie Resource Screening Based on UAV Remote Sensing Phenotype Monitoring
FU Hongyu, WANG Wei, LIAO Ao, YUE Yunkai, XU Mingzhi, WANG Ziwei, CHEN Jianfu, SHE Wei, CUI Guoxian
High Quality Ramie Resource Screening Based on UAV Remote Sensing Phenotype Monitoring
Ramie is an important fiber crop. Due to the shortage of land resources and the promotion of excellent varieties, the genetic variation and diversity of ramie decreased, which increased the need for investigation and protection of the ramie germplasm resources diversity. The crop phenotype measurement method based on UAV remote sensing can conduct frequent, rapid, non-destructive and accurate monitoring of different genotypes, which can fulfill the investigation of crop germplasm resources and screen specific and high-quality varieties. In order to realize efficient comprehensive evaluation of ramie germplasm phenotype and assist in screening of dominant ramie varieties, a method for monitoring and screening ramie germplasm phenotype was proposed based on UAV remote sensing images. Firstly, based on UAV remote sensing images, the digital surface model (DSM) and orthophoto of the test area were generated by Pix4dmapper. Then, the key phenotypic parameters (plant height, plant number, leaf area index, leaf chlorophyll content and water content) of ramie germplasm resources were estimated. The subtraction method was used to extract ramie plant height based on DSM, while the target detection algorithm was applied to extract ramie plant number based on orthographic images, and four machine learning methods were used to estimate the leaf area index (LAI), leaf chlorophyll content (SPAD value) and water content. Finally, according to the extracted remote sensing phenotypic parameters, the genetic diversity of ramie germplasm was analyzed by using variability analysis and principal component analysis. The results showed that: (1) The ramie phenotype estimation based on UAV remote sensing was effective, with the fitting accuracy of plant height 0.93, and the root mean square error (RMSE) 5.654 cm. The fitting indexes of SPAD value, water content and LAI were 0.66, 0.79 and 0.74, respectively, and RMSE were 2.03, 2.21 and 0.63, respectively; (2) The remote sensing phenotypes of ramie germplasm were significantly different, as the coefficients of variation of LAI, plant height and plant number reached 20.82%, 24.61% and 35.48%, respectively; (3) Principal component analysis was used to cluster the remote sensing phenotypes into factor 1 (plant height and LAI) and factor 2 (LAI and SPAD value), factor 1 can be used to evaluate the structural characteristics of ramie germplasm resources, and factor 2 can be used as the screening index of high-light efficiency ramie resources. This study could provide references for crop germplasm phenotypic monitoring and breeding correlation analysis.
ramie / diversity of germplasm resources / phenotype / UAV remote sensing / digital surface model / machine learning {{custom_keyword}} /
Table 1 The calculation formula of remote sensing index表1 遥感特征值的计算公式 |
类型 | 遥感指数 | 计算公式 |
---|---|---|
纹理特征值 | 灰度共生矩阵均值(Mean) | Mean = |
对比度(Contrast) | Contrast = | |
差异(Dissimilarity) | Dissimilarity = | |
同质性(Homogeneity) | Homogeneity = | |
能量(Energy) | Energy = | |
相关性(Correlation) | Correlation = | |
角二阶矩(Angular Second Moment,ASM) | ASM = | |
熵(Entropy) | Entropy = | |
光谱特征值 | 归一化植被指数(Normalized Difference Vegetation Index,NDVI) | NDVI = (NIR-R)/( NIR+R) (9) |
绿色归一化差异植被指数(Green Normalized Differential Vegetation Index,GNDVI) | GNDVI = (G-R)/(G+R) (10) | |
土壤调节植被指数(Soil Adjusted Vegetation Index,SAVI) | SAVI = 1.5(NIR-R)/(NIR+R+0.5) (11) | |
增强植被指数(Enhanced Vegetation Index,EVI) | EVI=2.5(NIR-R)/( NIR+6R-7.5B+1) (12) | |
超绿指数(Exceed Green Index,ExG) | ExG = 2×g-r-b (13) | |
超红指数(Exceed Red Index,ExR) | ExR = 1.4r-g (14) | |
过绿红指数(Exceed Green And Red Index,ExGR) | ExGR = ExG-1.4R-G (15) | |
可见大气抗性指数(Visible Atmospheric Resistance Index,VARI) | VARI = (g-r)/(g+r-b) (16) | |
HDSM | 提取的高程数据(HDSM) | HDSM = DSMi-DTM (17) |
Table 2 Statistical description of ramie phenotypic characters表2 苎麻种质资源表型性状统计描述 |
指标 | 生育期 | 最小值 | 最大值 | 平均值 | 标准差 |
---|---|---|---|---|---|
SPAD值 | 苗期 | 25.50 | 46.51 | 37.01 | 4.02 |
封行期 | 24.70 | 44.52 | 36.76 | 3.39 | |
旺长期 | 26.80 | 44.60 | 35.49 | 3.36 | |
全生育期 | 24.70 | 46.51 | 36.55 | 3.66 | |
含水量/% | 苗期 | 79.69 | 95.84 | 87.73 | 2.36 |
封行期 | 71.31 | 93.49 | 79.17 | 2.53 | |
旺长期 | 60.81 | 85.06 | 76.96 | 3.07 | |
全生育期 | 60.81 | 95.86 | 80.23 | 4.89 | |
LAI | 苗期 | 0.91 | 5.03 | 2.77 | 0.76 |
封行期 | 1.05 | 7.25 | 3.60 | 1.03 | |
旺长期 | 2.24 | 7.64 | 4.64 | 0.91 | |
全生育期 | 0.91 | 7.64 | 3.65 | 1.19 | |
株高/cm | 苗期 | 14.50 | 71.60 | 31.72 | 10.28 |
封行期 | 21.70 | 178.90 | 58.07 | 20.38 | |
旺长期 | 49.60 | 252.10 | 92.49 | 22.42 | |
全生育期 | 14.50 | 252.10 | 58.27 | 30.51 | |
株数/株 | —— | 11 | 140 | 67 | 24 |
Table 3 Plant height fitting model of ramie germplasm resources表3 苎麻种质资源株高拟合模型 |
生育期 | R 2 | RMSE /cm | ||
---|---|---|---|---|
线性回归 | 指数回归 | 多项式回归 | ||
苗期 | 0.77 | 0.70 | 0.77 | 4.59 |
封行期 | 0.81 | 0.79 | 0.82 | 6.39 |
旺长期 | 0.86 | 0.83 | 0.86 | 6.86 |
全生育期 | —— | —— | 0.93 | 5.65 |
Table 4 Effect of ramie height correction model表4 苎麻株高校正模型的校正效果 |
生育期 | 校正前 | 校正后 | ||
---|---|---|---|---|
R 2 | RMSE/cm | R 2 | RMSE/cm | |
苗期 | 0.85 | 5.10 | 0.98 | 1.14 |
封行期 | 0.77 | 6.06 | 1.00 | 4.85 |
旺长期 | 0.90 | 7.01 | 0.10 | 3.18 |
Table 5 Monitoring results of physiological parameters of ramie germplasm resources表5 苎麻种质资源生理参数监测结果 |
指标 | 模型 | 训练集 | 测试集 | ||
---|---|---|---|---|---|
R 2 | RMSE | R 2 | RMSE | ||
SPAD值 | LR | 0.69 | 2.05 | 0.66 | 2.09 |
RF | 0.93 | 0.97 | 0.59 | 2.30 | |
SVM | 0.61 | 2.28 | 0.66 | 2.09 | |
PLSR | 0.62 | 2.27 | 0.64 | 2.14 | |
含水量 | LR | 0.78 | 2.29 | 0.79 | 2.21 |
RF | 0.96 | 0.93 | 0.77 | 2.33 | |
SVM | 0.76 | 2.40 | 0.78 | 2.30 | |
PLSR | 0.77 | 2.36 | 0.79 | 2.20 | |
LAI | LR | 0.77 | 0.56 | 0.70 | 0.67 |
RF | 0.96 | 0.24 | 0.71 | 0.66 | |
SVM | 0.74 | 0.60 | 0.74 | 0.63 | |
PLSR | 0.74 | 0.60 | 0.73 | 0.62 |
1 |
朱爱国, 喻春明, 唐守伟, 等. 苎麻主要品质性状研究进展 [J]. 中国麻业, 2002(6): 8-12, 26.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
2 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
3 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
4 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
5 |
杨进, 明博, 杨飞, 等. 利用无人机影像监测不同生育阶段玉米群体株高的精度差异分析[J]. 智慧农业(中英文), 2021, 3(3): 129-138.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
6 |
李婕, 李毅, 张瑞杰, 等. 无人机遥感影像在油菜品种识别中的应用[J].江苏农业学报, 2022, 38(3):675-684.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
7 |
牛庆林, 冯海宽, 周新国, 等. 冬小麦SPAD值无人机可见光和多光谱植被指数结合估算[J]. 农业机械学报, 2021, 52(8):183-194.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
8 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
9 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
10 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
11 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
12 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
13 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
14 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
15 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
16 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
17 |
芮婷婷, 徐云飞, 程琦, 等. 基于无人机多光谱遥感的冬小麦叶片含水量反演[J]. 麦类作物学报, 2022, 42(10): 1291-1300.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
18 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
19 |
熊和平, 蒋金根, 喻春明, 等.苎麻产量构成因素与产量的关系[J]. 作物学报, 1998(2): 155-160.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
20 |
高林, 杨贵军, 王宝山, 等. 基于无人机遥感影像的大豆叶面积指数反演研究[J]. 中国生态农业学报, 2015, 23(7): 868-876.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_ref.label}} |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
/
〈 |
|
〉 |