Pest infestations significantly impact rice production and threaten food security. Remote sensing offers a vital tool for the non-destructive, rapid detection of rice pests. Existing studies often focus on laboratory conditions at the leaf level, limiting their applicability for precise pesticide application. Therefore, this study aimed to develop a method for detecting rice pests (rice leaf folders) in paddy fields based on unmanned aerial vehicle (UAV) hyperspectral data. Firstly, a UAV imaging system collected hyperspectral images of rice plants in both the jointing and heading stages. A total of 222 field plots for investigating rice leaf folders was established during these two periods. Secondly, 23 vegetation indices were calculated as candidates for identifying rice pests. Then, hyperspectral data and field investigation data from the jointing stage were used to construct a machine learning (extreme gradient boosting, XGBoost) algorithm for detecting rice pests. The results showed that the XGBoost model exhibited the best performance when eight vegetation indices were considered as the selected input features for model construction: the Red-edge Normalized Difference Vegetation Index (red-edge NDVI), Structure Insensitive Pigment Index (SIPI), Enhanced Vegetation Index (EVI), Atmospherically Resistant Vegetation Index (ARVI), Soil-Adjusted Vegetation Index (SAVI), Red-edge Chlorophyll Index (CIred-edge), Pigment-Specific Simple Ratio₆₈₀ (PSSR₆₈₀), and Carotenoid Reflectance Index₇₀₀ (CPI₇₀₀). The training and testing accuracies reached 87.46% and 86%, respectively. Furthermore, the heading stage application confirmed the model’s feasibility. Thus, the XGBoost model with input features of eight vegetation indices provides an effective and reliable method for detecting rice leaf folders, supporting real-time, precise pesticide use in rice cultivation.

The morphology of the pollen grains of 18 species representing nine genera of Annonaceae from China is described and illustrated based on observations from scanning electron microscopy (SEM). The pollen grains are small, medium-sized, large or very large, elliptic, spherical or subspherical in monads (Artabotrys, Fissistigma, Miliusa, Trivalvaria, Uvaria and most Polyalthia), tetrads (Annona, Goniothalamus, Mitrephora and Polyalthia rumphii) or octads (Disepalum). Tetragonal, tetrahedral or rhomboidal tetrads were observed in Polyalthia rumphii. Ornamentation is psilate, foveolate, perforate, rugulate, reticulate or verrucate. Most species have no visible aperture, while Miliusa balansae, Polyalthia cerasoides, Polyalthia laui, Polyalthia oblique and Trivalvaria costata have one sulcus or 1–3 pores on proximal side or globally distributed. Disepalum lagioneurum (former Polyalthia lagioneurum) bearing octads confirms its isolation from Polyalthia, which so far has been observed monad. While the isolation of Trivalvaria costata (former Polyalthia nemoralis) from Polyalthia was not supported for the similarities of pollen characters.

Anther is thought to release either bicellular or tricellular pollen when mature. Though a few species had been found to shed both bicellular and tricellular pollen, due to their low frequency, they had been overlooked as special cases of bicellular or tricellular pollen in previous phylogenetic studies. In the present work, the pollen cytologies of 89 species from 26 genera of Annonaceae were observed using the overall transparency method and paraffin sectioning method. The results show that 73 species from 25 genera distribute bicellular pollen, while 16 species from 10 genera shed both bicellular and tricellular pollen. This is the first time that so many species with both types of pollen has been observed in the same family. Combined with reports from other families, the plants that were known to shed both types of pollen included 15 families, 40 genera, and 52 species. Our results indicate that the coexistence of bicellular and tricellular pollen might be the third type of pollen cell number. And the systematic relationship among them is needed to be reanalyzed.