Heavy metal concentration is an important index for evaluating soil pollution. It is of great significance to measure the trace element content accurately for green agriculture development. In order to detect the trace element content accurately, a new prediction framework including pre-processing, signal extraction, feature selection and decision-making was proposed. The energy dispersive X-ray fluorescence (ED-XRF) spectra of 57 national standard soil samples were investigated based on the proposed methods. Firstly, an innovative background deduction method called iterative adaptive window empirical wavelet transform (IAWEWT) was introduced to extract effective counts of characteristic peaks, and the proposed approach was validated by the coefficient of determination (R²) of the instrumental calibration curve compared with two other conventional methods. Secondly, principal component analysis (PCA) was combined with the analysis of variance (ANOVA) for variable selection optimization of the ED-XRF spectrum. After PCA feature extraction and ANOVA variable selection treatment, the optimum number of principal components for V, Cr, Cu, Zn, Mo, Cd and Pb were determined to be 7, 15, 4, 4, 4, 5 and 12 respectively. Furthermore, the support vector regression (SVR) model was adopted for heavy metal estimation. The evaluation indices included R² and root mean square error (RMSE). It was demonstrated that the predictive capabilities of seven heavy metal elements were improved substantially for elemental analysis by the proposed PCA–ANOVA–SVR model, with excellent results for V, Cr, Cu, Zn, Mo, Cd and Pb estimates, and the R² values were 0.993, 0.996, 0.999, 0.999, 0.997, 0.998 and 0.998 respectively. Therefore, the new framework proposed in this paper can effectively eliminate redundant features and determine the concentration of trace elements in soil. It provides an effective alternative for the quantitative analysis of X-ray fluorescence spectrometry.

Soil is an important source of potentially toxic metal intake for humans through the food chain. Accurate determination of elemental concentrations in soil is of great significance to safeguard human health, thereby requiring reliable detection techniques. This work aimed to propose a new quantitative analysis method that combines pre-processing and concentration prediction. A total of 59 soil samples were collected and subjected to laboratory analyses and energy dispersive X-ray fluorescence (ED-XRF) scans. Firstly, a novel pre-processing method based on iterative adaptive window empirical wavelet transform and Gaussian convolution (IAWEWT-GC) was proposed, which can identify and remove spectral background. Secondly, the instrument calibration curves of peak counts and elemental concentrations were established and the pre-treatment effect was verified by comparison with other common methods. The instrument calibration curves' coefficient of determination (R²) was enhanced to 0.988, 0.962, and 0.980 for Cr, Mn, and Cu, respectively. Finally, to accurately detect the elemental concentration, a hierarchical deep neural network (HDNN) was designed for estimating potentially toxic metals, enabling quantitative regression of multiple elements simultaneously. The proposed method was evaluated and compared with conventional algorithms (DNN, BPNN, and PLSR). The HDNN model achieved the highest R² of 0.943, 0.983, and 0.979 for Cr, Mn, and Cu, respectively, with the lowest RMSEP of 5.74, 84.45, and 29.17, and lowest MAE of 4.51, 78.51, and 16.35, indicating its ability to enable simple, rapid, and effective quantitative analysis of multiple elements. Overall, our proposed method provides a new option for the elemental analysis of samples rich in potentially toxic metals.

An accurate and effective analytical method to measure the concentration of heavy metal elements (HMEs) in soil is of great significance for combating soil pollution, repairing ecosystems, and guiding agricultural cropland. Nondestructive, rapid, and in situ measurements make X-ray fluorescence spectroscopy (XRF) a popular tool for analyzing HMEs in soil. However, due to complex matrix effects and spectral line interference, the analytical accuracy is limited. In this study, an effective deep learning method is proposed to accurately determine the concentration of HMEs in soil by combining with XRF. Firstly, soil spectra are acquired based on a handheld energy-dispersive X-ray fluorescence spectrometer (ED-XRF). Secondly, depending on the spectral continuity, cross-space correlation, and local correlation of XRF, a feature mining coordination (FMC) module is proposed. The FMC module is composed of a global spectral attention (GSA) module and a local multiscale feature extraction (LMSFE) module, and it can simultaneously pay overall attention to the spectrogram and local feature modeling. Finally, a deep spectral prediction network (DSPFormer) is proposed based on the FMC module to achieve an accurate estimation of the concentration of five HMEs (Ti, Mn, Cu, Zn, and Pb). The effectiveness of the method is demonstrated by comparing it with other advanced soil analysis algorithms. The coefficients of determination of DSPFormer for five HMEs (Ti, Mn, Cu, Zn, and Pb) are 0.9559, 0.9627, 0.9658, 0.9584, and 0.9664, respectively. The results indicate that DSPFormer effectively mitigates the matrix effect and spectral line interference present in XRF. In summary, the deep learning method based on self-attention and convolutional neural networks (CNNs) provides new theoretical guidance for soil HME analysis.

Poisonous elements such as lead (Pb), arsenic (As), cadmium (Cd), and chromium (Cr) are commonly observed in polluted soil but hard to detect due to low concentration. Currently, the quantitative content of elements can be determined by an x-ray fluorescence (XRF) analyzer if the limit of detection (LOD) is known. However, to ensure that elements with extremely low content can be detected, the LOD needs to be reduced and determined. Firstly, the authors utilized the traditional method detection limit (MDL) formula to calculate the LOD for benchmark purposes. Secondly, in order to improve the signal to noise ratios of the characteristic peaks, the wavelet threshold denoising method and iterative discrete wavelet transform algorithm were utilized for spectral denoising and background noises deduction of XRF spectra based on 57 certified reference soil samples. Thirdly, a novel Adaboost back propagation neural network model was proposed to reduce and determine the values of LOD. The results showed that the LODs of trace elements determined from the proposed algorithm decreased greatly compared to the traditional MDL method. Finally, the calibration curve of elemental concentration versus counting rate was established and regressed using the proposed multivariate partial least squares model. The goodness of fit ( R ² ) was significantly increased. Therefore, the proposed algorithm is effective to determine the LOD and can yield optimal performance in instrument calibration of trace elements in soil.

This letter introduces a novel reconfigurable modular aerial robot capable of in-air self-disassembly and achieving full-actuation control. The proposed robot utilizes a unique modular design, each module incorporates a vector tilting structure and an active undocking mechanism. The design of the vector tilting structure amplifies the possibilities of control, allowing the introduced control algorithms to realize full-actuation control of the robot. The active undocking mechanism employs electromagnets for active and controllable reconfiguration. We redesigned the feedforward angle calculation and control assignment to enable the full-actuation controller in reconfigurable modular robots. Furthermore, we proposed a distributed framework to alleviate the burden on the communication system. Real-world experiments demonstrate that the reconfiguration process' ability to control maximum Euler angle oscillation within $\boldsymbol {4\mathrm{^{\circ }}}$ and reduce in-air reconfiguration time to under $\boldsymbol {{\text{3}} \,\mathrm{s}}$ . Additionally, experiments on full DoF hovering for both a single module and a reconfigurable robot confirm the stability of the proposed controller.