Non-destructive testing (NDT) methods are increasingly applied in modern agriculture to enable the rapid, efficient, and non-invasive evaluation of crops and agricultural products. Among these, polarization spectroscopy analysis (PSA) combines polarization information with spectral data to provide detailed insights into plant and soil properties. This review summarizes the principles and key parameters of polarimetry and highlights PSA applications, including crop health monitoring, pest and disease detection, chlorophyll and nutrient estimation, seed quality assessment, and soil moisture and pollution evaluation. PSA demonstrates advantages over conventional spectroscopy by revealing structural information and maintaining robustness in complex environments. Its ability to support precision agriculture through the real-time monitoring and early detection of stress factors underscores its potential for smart agricultural systems. Future efforts should focus on data fusion, model optimization, equipment miniaturization, and enhanced adaptability to fully realize PSA’s role in intelligent agriculture.

Litchi (Litchi chinensis Sonn.) is an economically important tropical and subtropical fruit crop, but frequent outbreaks of diseases and pests severely threaten yield and quality. Traditional field monitoring is inefficient and cannot meet requirements for early and accurate detection over large areas. Although various sensing technologies and artificial intelligence (AI)-based methods have been developed, the literature remains fragmented and lacks systematic comparison across different monitoring scales and technological approaches. This review summarizes recent advances in intelligent detection technologies for litchi diseases and pests across scales ranging from individual fruits to entire orchards. First, biological and spectral response mechanisms of infected tissues are introduced as a theoretical basis. Then, fruit-level sensing technologies, including near-infrared spectroscopy, multispectral and hyperspectral imaging, RGB imaging, fluorescence sensing, and data fusion, are reviewed. Orchard-scale monitoring using unmanned aerial vehicles (UAVs) and Internet of Things (IoT) is further analyzed. Machine learning and deep learning methods for feature extraction, recognition, and risk prediction are also summarized. Finally, advantages, limitations, and application scenarios of different technologies are compared in terms of their advantages, limitations, and suitable application scenarios. This review highlights the transition toward multimodal and intelligent monitoring systems and discusses future directions including edge intelligence, multimodal fusion, and collaborative monitoring for precision agriculture.

Nitrogen (N), phosphorus pentoxide (P₂O₅), and potassium oxide (K₂O) are key quality indicators of compound fertilizers. This study evaluated the sample-level predictive performance and applicability of compact near-infrared (NIR) spectroscopy for rapid screening of these nutrients in unground granular compound fertilizers. A total of 143 samples were measured using two independent loadings per sample, yielding 286 spectra over 900–1700 nm. Candidate modeling strategies were compared using sample-ID-grouped repeated nested cross-validation. Model stability was examined by loading-repeatability sensitivity analysis and leave-one-acquisition-date-out validation, while nutrient covariation was assessed using nutrient-only linear reference models. The selected procedures were analyte-specific ensemble models for N, P₂O₅, and K₂O. Internal coefficients of determination (R²) were 0.9005, 0.8279, and 0.8034, with root-mean-square error (RMSE) values of 0.8392, 1.0884, and 1.5724 percentage points, respectively.. Relative to nutrient-only linear reference models, RMSE decreased by 32.7% for P₂O₅ and 31.9% for K₂O. Without refitting, the finalized models were applied to 29 subsequent production-batch samples from the same source, yielding R² values of 0.7147, 0.7496, and −2.2911 for N, P₂O₅, and K₂O, respectively. N and P₂O₅ retained potential for rapid preliminary screening under the evaluated conditions, whereas the K₂O relationship did not transfer reliably, indicating the need for broader calibration coverage across production batches and formulations.