PDF
Full
Outline
Addressing the challenges of inadequate utilization of spectral feature variations among wheat cultivars and the limited generalization capacity of conventional ensemble learning methods for yield prediction, this study proposed a novel Extreme Stacked Generalization (ESG) algorithm. The ESG method was designed to enhance prediction accuracy and stability across multiple cultivars and years by dynamically optimizing feature selection and model integration, thereby resolving micrometer-level spectral discrepancies among cultivars. The study utilized canopy hyperspectral reflectance and yield data collected over two wheat growing seasons (2018—2020), containing the early and middle grain-filling stages. A dual-validation framework was employed, comprising independent cross-year validation (Framework 1) and multi-period data fusion validation (Framework 2). The performance of the ESG algorithm was benchmarked against Ridge Regression (RR), K-Nearest Neighbors (KNN), Random Forest (RF), and a standard Stacked Generalization (SG) algorithm, using Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) as evaluation metrics. Results demonstrated that the ESG algorithm significantly outperformed all other models, reducing the prediction RMSE to a range of 1.01-1.31 t·hm-2. The stability of cross-year predictions was notably improved, with the range of error fluctuation decreasing by 18.9%, indicating strong environmental adaptability and cultivar-discriminating capabilities. Furthermore, the middle grain-filling stage was identified as the optimal prediction window, achieving a RMSE of 1.01 t·hm-2. This study concludes that the ESG algorithm can effectively adapt to the specific spectral characteristics of different wheat cultivars and environmental variations, enabling robust and stable yield prediction across diverse cultivars and growing years.
PDF
27
9
| 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
