PDF
Full
Outline
The maize leaf area index (LAI) is a key parameter for reflecting growth and yield of maize, and the pollination stage being crucial for determining ear kernel number and yield. This study aimed to identify an effective inversion method to accurately estimate the LAI of Nanfan maize at pollination stage. Nanfan maize at pollination stage was used as the study subject. Canopy reflectance data were acquired using a ULTRIS X20 PLUS hyperspectral imager mounted on a Jingwei M300RTK quadrotor UAV platform. Based on correlation analysis, 28 LAI-sensitive vegetation indices were selected. Two traditional empirical models, univariate linear regression (ULR) and multiple stepwise regression (MSR), and four machine learning models, partial least squares regression (PLSR), random forest regression (RFR), support vector regression (SVR) and back propagation neural network (BPNN) were employed to construct LAI inversion models. The prediction accuracy of different vegetation indices and regression algorithms was compared, and the optimal inversion model was selected for accurately predicting the LAI status of Nanfan maize at pollination stage. Most vegetation indices exhibited highly significant correlations with LAI (P<0.01). Compared to univariate regression, multivariate regression models provided higher prediction accuracy. Among them, RFR, MSR and PLSR models achieved the highest R2 values, with coefficients of determination (R2) of 0.96, 0.85 and 0.80 and corresponding root mean square errors (RMSE) of 0.18, 0.35 and 0.41, respectively. By analyzing the correlation and sensitivity between hyperspectral data and maize LAI, and employing vegetation indices calculated based on hyperspectral information combined with regression algorithms, this study successfully developed a reliable LAI inversion model, and established a spatial distribution of Nanfan maize LAI at pollination stage based on the RFR model with the best inversion effect. The model would provide both theoretical support and technical guidance for LAI estimation and field monitoring of Nanfan maize growth and development.
PDF
125
67
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |
关闭全屏
No. 86 Xueyuan South Road, Haidian District, Beijing
010-62199257
qkjq@cast.org.cn
Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House
