Tracking of free proline (FP)—an indicative substance of heavy metal stress in rice leaf—is conducive to improve plant phenotype detection, which has important guiding significance for precise management of rice production. Hyperspectral imaging was used for high-throughput screening FP in rice leaves under cadmium (Cd) stress with five concentrations and four periods. The average spectral of rice leaves were used to show differences in optical properties. Partial least squares (PLS), least-squares support vector machine (LS-SVM) and extreme learning machine (ELM) models based on full spectra and effective wavelengths were established to detect FP content. Genetic algorithm (GA), competitive adaptive weighted sampling (CARS) and PLS weighting regression coefficient (Bw) were compared to screen the most effective wavelengths. Distribution map of the FP content in rice leaves were obtained to display the changes in the FP of leaves visually. The results illustrated that spectral differences increased with Cd stress time and FP content increased with Cd stress concentration. The best result for FP detection is the ELM model based on 27 wavelengths selected by CARS and R_p is 0.9426. Undoubtedly, hyperspectral imaging combined with chemometrics was a rapid, cost effective and non-destructive technique to excavate changes of FP in rice leaves under Cd stress.

Panax notoginseng (P. notoginseng) is a valuable herbal medicine, as well as a dietary food supplement known for its satisfactory clinical efficacy in alleviating blood stasis, reducing swelling, and relieving pain. However, the ability of P. notoginseng to absorb and accumulate cadmium (Cd) poses a significant environmental pollution risk and potential health hazards to humans. In this study, we employed laser-induced breakdown spectroscopy (LIBS) for the rapid detection of Cd. It is important to note that signal uncertainty can impact the quantification performance of LIBS. Hence, we proposed the crater–spectrum feature fusion method, which comprises ablation crater morphology compensation and characteristic peak ratio correction (CPRC), to explore the feasibility of signal uncertainty reduction. The crater morphology compensation method, namely, adding variables using multiple linear regression (MLR) analysis, decreased the root-mean-square error of the prediction set (RMSEP) from 7.0233 μg/g to 5.4043 μg/g. The prediction results were achieved after CPRC pretreatment using the calibration curve model with an RMSEP of 3.4980 μg/g, a limit of detection of 1.92 μg/g, and a limit of quantification of 6.41 μg/g. The crater–spectrum feature fusion method reached the lowest RMSEP of 2.8556 μg/g, based on a least-squares support vector machine (LSSVM) model. The preliminary results suggest the effectiveness of the crater–spectrum feature fusion method for detecting Cd. Furthermore, this method has the potential to be extended to detect other toxic metals in addition to Cd, which significantly contributes to ensuring the quality and safety of agricultural production.

Visible near-infrared (Vis-NIR) spectroscopy is widely used for rapid soil element detection, but calibration models are often limited by instrument-specific constraints, including varying laboratory conditions and sensor configurations. To address this, we propose a novel calibration transfer method that eliminates the conventional requirement of designating ‘master’ and ‘slave’ devices. Instead, spectral data from two spectrometers are fused to create a master spectrum, while independent spectral data serve as slave spectra. We developed an ensemble stacking model, incorporating partial least squares regression (PLSR), support vector regression (SVR), and ridge regression (Ridge) in the first layer, with BoostForest (BF) as the second layer, trained on the fused master spectrum. This model was further integrated with three calibration transfer methods: direct standardization (DS), piecewise direct standardization (PDS), and spectral space transfer (SST), to enable seamless application across slave spectra. Applied to soil total nitrogen (TN) detection, the method achieved an R²_P of 0.842, RMSEP of 0.017, and RPD of 2.544 on the first slave spectrometer, and an R²_P of 0.830, RMSEP of 0.018, and RPD of 2.452 on the second. These results demonstrate the method’s ability to simplify calibration processes while enhancing cross-instrument prediction accuracy, supporting robust and generalizable cross-instrument applications.

Phytoremediation is an eco-friendly and in situ solution for remediating heavy metal-contaminated soils, yet practical application requires timely and accurate effectiveness evaluation. However, conventional chemical analysis of plant parts and soils is labor-intensive, time-consuming and limited for large-scale monitoring. This study proposed a rapid sensing framework integrating laser-induced breakdown spectroscopy (LIBS) with deep transfer learning and spectral indices to assess phytoremediation effectiveness of Sedum alfredii (a Cd/Zn co-hyperaccumulator). LIBS spectra were collected from plant tissues and diverse soil matrices. To overcome strong matrix effects, fine-tuned convolutional neural networks were developed for simultaneous multi-matrix quantification, achieving high-accuracy prediction for Cd and Zn (R²_test > 0.99). These predicted concentrations enabled calculating conventional phytoremediation indicators like bioconcentration factor (BCF), translocation factor (TF), plant effective number (PEN), and removal efficiency (RE), yielding recovery rates near 100% for TF and PEN. Additionally, novel spectral indices (SIs)—directly derived from characteristic wavelength combinations—were constructed to bypass intermediate quantification. SIs significantly improved the direct evaluation of Zn removal and translocation. Finally, a decision-level fusion strategy combining concentration predictions and SIs enhanced Cd removal assessment accuracy. This study validates LIBS combined with intelligent algorithms as a rapid sensor tool for monitoring phytoremediation performance, facilitating sustainable environmental management.