Rice is one of the three primary staple crops worldwide. The accurate monitoring of its key growth stages is crucial for agricultural management, disaster early warning, and ensuring food security. The effective collection of ground reference data is a critical step for monitoring rice growth stages using satellite imagery, traditionally achieved through labor-intensive field surveys. Here, we propose utilizing UAVs as an alternative means to collect spatially continuous ground reference data across larger areas, thereby enhancing the efficiency and scalability of training and validation processes for rice growth stage mapping products. The UAV data collection involved the Nanchuan, Yongchuan, Tongnan, and Kaizhou districts of Chongqing City, encompassing a total area of 377.5 hectares. After visual interpretation, centimeter-level high-resolution labels of the key rice growth stages were constructed. These labels were then mapped to Sentinel-2 imagery through spatiotemporal matching and scale conversion, resulting in a reference dataset of Sentinel 2 data that covered growth stages such as jointing and heading. Furthermore, we employed 30 vegetation index calculation methods to explore 48,600 spectral band combinations derived from 10 Sentinel-2 spectral bands, thereby constructing a series of novel vegetation indices. Based on the maximum relevance minimum redundancy (mRMR) algorithm, we identified an optimal subset of features that were both highly correlated with rice growth stages and mutually complementary. The results demonstrate that multi-feature modeling significantly enhanced classification performance. The optimal model, incorporating 300 features, achieved an F1 score of 0.864, representing a 2.5% improvement over models based on original spectral bands and a 38.8% improvement over models using a single feature. Notably, a model utilizing only 12 features maintained a high classification accuracy (F1 = 0.855) while substantially reducing computational costs. Compared with existing methods, this study constructed a large-scale ground-truth reference dataset for satellite imagery based on UAV observations, demonstrating its potential as an effective technical framework and providing an effective technical framework for the large-scale mapping of rice growth stages using satellite data.

The accurate identification of rice growth stages is critical for precision agriculture, crop management, and yield estimation. Remote sensing technologies, particularly multimodal approaches that integrate high spatial and hyperspectral resolution imagery, have demonstrated great potential in large-scale crop monitoring. Multimodal data fusion offers complementary and enriched spectral–spatial information, providing novel pathways for crop growth stage recognition in complex agricultural scenarios. However, the lack of publicly available multimodal datasets specifically designed for rice growth stage identification remains a significant bottleneck that limits the development and evaluation of relevant methods. To address this gap, we present RiceStageSeg, a multimodal benchmark dataset captured by unmanned aerial vehicles (UAVs), designed to support the development and assessment of segmentation models for rice growth monitoring. RiceStageSeg contains paired centimeter-level RGB and 10-band multispectral (MS) images acquired during several critical rice growth stages, including jointing and heading. Each image is accompanied by fine-grained, pixel-level annotations that distinguish between the different growth stages. We establish baseline experiments using several state-of-the-art semantic segmentation models under both unimodal (RGB-only, MS-only) and multimodal (RGB + MS fusion) settings. The experimental results demonstrate that multimodal feature-level fusion outperforms unimodal approaches in segmentation accuracy. RiceStageSeg offers a standardized benchmark to advance future research in multimodal semantic segmentation for agricultural remote sensing. The dataset will be made publicly available on GitHub v0.11.0 (accessed on 1 August 2025).

Stripe rust, caused by Puccinia striiformis f. sp. tritici, and leaf rust, caused by Puccinia triticina, are among the most damaging wheat diseases worldwide, and their urediniospores serve as the primary inoculum for airborne dispersal. Accurate discrimination of these spores is important for disease forecasting, yet the two spore types are highly similar under light microscopy. For field-monitoring scenarios in which chemical preprocessing is impractical, we developed RustSporeSeg, a deep learning-based semantic segmentation model for direct pixel-level discrimination of stripe rust and leaf rust urediniospores in untreated microscopic images acquired under standardized laboratory conditions. The model integrates attention-based foreground enhancement with multilevel feature refinement and achieved an mIoU of 80.32% and a mean F1-score of 88.45% on the held-out untreated test set. We further evaluated hydrochloric acid (HCl) treatment as a separate laboratory reference condition. Under this condition, several conventional convolutional models achieved mIoU values above 91% and mean F1-scores above 95%, with the best-performing model reaching an mIoU of 95.70% and a mean F1-score of 97.78%. To support further research, a fine-grained urediniospore image dataset encompassing both pathogens, together with the model code, has been made publicly available.These results demonstrate the feasibility of pathogen-specific urediniospore segmentation under the tested acquisition conditions and provide a basis for future validation in automated spore-monitoring workflows.