Hyperspectral imaging acquired from unmanned aerial vehicles (UAVs) offers detailed spectral and spatial data that holds transformative potential for precision agriculture applications, such as crop classification, health monitoring, and yield estimation. However, traditional methods struggle to effectively capture both local and global features, particularly in complex agricultural environments with diverse crop types, varying growth stages, and imbalanced data distributions. To address these challenges, we propose CMTNet, an innovative deep learning framework that integrates convolutional neural networks (CNNs) and Transformers for hyperspectral crop classification. The model combines a spectral-spatial feature extraction module to capture shallow features, a dual-branch architecture that extracts both local and global features simultaneously, and a multi-output constraint module to enhance classification accuracy through cross-constraints among multiple feature levels. Extensive experiments were conducted on three UAV-acquired datasets: WHU-Hi-LongKou, WHU-Hi-HanChuan, and WHU-Hi-HongHu. The experimental results demonstrate that CMTNet achieved overall accuracy (OA) values of 99.58%, 97.29%, and 98.31% on these three datasets, surpassing the current state-of-the-art method (CTMixer) by 0.19% (LongKou), 1.75% (HanChuan), and 2.52% (HongHu) in OA values, respectively. These findings indicate its superior potential for UAV-based agricultural monitoring in complex environments. These results advance the precision and reliability of hyperspectral crop classification, offering a valuable solution for precision agriculture challenges.

Potato canopy nitrogen content (CNC) is an imperative metric for assessing potato growth status and guiding field management. While the spectral index can be utilized to estimate CNC, its efficacy is influenced by the environment and crop type. To address this issue, we utilized hyperspectral indices (HIs) optimization for CNC estimation. Using the inverse and first-order differential (FD) transformations of the original data (OD), HIs comprising two-band combinations in 400–1000 nm, such as RSI, DSI, NDSI, SASI, and PSI, were constructed to analyze the correlation between CNC and HIs. Based on this analysis, prediction models for potato CNC were created using the most optimal HIs. The results showed that FD transformation significantly improved the correlations between CNC and HIs, among which FD−PSI_{(R654, R565)} had the highest correlation with CNC. We further employed the optimal HIs as variables to establish univariate and multivariate regression models to estimate the potato CNC. Among the univariate models, the accuracy of the OD−DSI model was the highest, with an R² of 0.79 and RMSE of 0.22. Meanwhile, the FD−MLR model demonstrated the highest accuracy compared to the other multivariate models, with an R² of 0.84, an RMSE of 0.20 during validation, and a greater prediction accuracy than the OD−DSI model. FD−MLR can be used to map the CNC distribution map of monitored potato planting plots to guide precision fertilization.

Leaf chlorophyll content (LCC), leaf area index (LAI), and above-ground biomass (AGB) are important growth parameters for characterizing potato growth and predicting yield. While deep learning has demonstrated remarkable advancements in estimating crop growth parameters, the limited availability of field data often compromises model accuracy and generalizability, impeding large-scale regional applications. This study proposes a novel deep learning model that integrates multi-task learning and few-shot learning to address the challenge of low data in growth parameter prediction. Two multi-task learning architectures, MTL-DCNN and MTL-MMOE, were designed based on deep convolutional neural networks (DCNNs) and multi-gate mixture-of-experts (MMOE) for the simultaneous estimation of LCC, LAI, and AGB from Sentinel-2 imagery. Building on this, a few-shot learning framework for growth prediction (FSLGP) was developed by integrating simulated spectral generation, model-agnostic meta-learning (MAML), and meta-transfer learning strategies, enabling accurate prediction of multiple growth parameters under limited data availability. The results demonstrated that the incorporation of calibrated simulated spectral data significantly improved the estimation accuracy of LCC, LAI, and AGB (R² = 0.62~0.73). Under scenarios with limited field measurement data, the multi-task deep learning model based on few-shot learning outperformed traditional mixed inversion methods in predicting potato growth parameters (R² = 0.69~0.73; rRMSE = 16.68%~28.13%). Among the two architectures, the MTL-MMOE model exhibited superior stability and robustness in multi-task learning. Independent spatiotemporal validation further confirmed the potential of MTL-MMOE in estimating LAI and AGB across different years and locations (R² = 0.37~0.52). These results collectively demonstrated that the proposed FSLGP framework could achieve reliable estimation of crop growth parameters using only a very limited number of in-field samples (approximately 80 samples). This study can provide a valuable technical reference for monitoring and predicting growth parameters in other crops.