| Popis: |
Timely and accurate mapping of rice distribution is crucial to estimate yield, optimize agriculture spatial patterns, and ensure global food security. Feature selection (FS) methods have significantly improved computational efficiency by reducing redundancy in spectral and temporal feature sets, playing a vital role in identifying and mapping paddy rice. However, the optimal feature sets selected by existing methods suffer from issues such as information redundancy or local optimality, limiting their accuracy in rice identification. Moreover, the effects of these FS methods on rice recognition in various machine learning classifiers and regions with different climatic conditions and planting structures is still unclear. To overcome these limitations, we conducted a comprehensive evaluation of the potential applications of major FS methods, including the wrapper method, embedded method, and filter method for rice mapping. A novel hierarchical lustering sequential forward selection (HCSFS) method for precisely extracting the optimal feature set for rice identification is proposed. The accuracy of the HCSFS and other FS methods for rice identification was tested with nine common machine learning classifiers. The results indicated that, among the three FS methods, the wrapper method achieved the best rice mapping performance, followed by the embedded method, and lastly, the filter method. The new HCSFS significantly reduced redundant features compared with eleven typical FS methods, demonstrating higher precision and stability, with user accuracy and producer accuracy exceeding 0.9548 and 0.9487, respectively. Additionally, the spatial distribution of rice maps generated using the optimal feature set selected by HCSFS closely aligned with actual planting patterns, markedly outperforming existing rice products. This research confirms the effectiveness and transferability of the HCSFS method for rice mapping across different climates and cultivation structures, suggesting its enormous potential for classifying other crops using time-series remote sensing images. |
