Fast and nondestructive discrimination of coal types based on spectral feature parameters.

Coal type identification is the basic work of coal quality inspection, which is of great significance to the normal operation of power generation, metallurgy, and other industries. The traditional coal-type identification method is complicated and requires comprehensive determination of various chemical parameters to obtain more accurate analysis results. Hyperspectral detection and analysis technology has the advantages of being simple, fast, nondestructive, and safe, and is widely used in a variety of fields. In this study, typical spectral feature parameters of coal samples were extracted based on hyperspectral data, and the parameters' sensitivity to coal types was explored using one-way ANOVA. The results showed that the coal spectral feature parameters of DI1-2µm and AD2.2µm significantly differed with coal species, indicating that the two parameters were class-sensitive features. When DI1-2µm and AD2.2µm were used to construct the Fisher discriminant model, the coal types could be discriminated with high accuracy. At the same time, the correlation between the extracted spectral feature parameters and the physicochemical parameters of bituminous coal and anthracite was analyzed. The results showed that there was a certain basis for using the extracted spectral feature parameters as the sensitive spectral characteristics of the model, and the application potential of the spectral characteristics of coal in the nondestructive prediction analysis of coal parameters was further discussed.

Dynamic prediction of displacement and deformation of any point on mining surface based on B-normal model.

The surface displacement and deformation of goaf caused by coal mining destroy the underground rock structure and surface ecological environment in the mining area and endanger the safety of human life and property. An accurate and efficient dynamic prediction system of mining subsidence is indispensable. Given the limited scope of the application of the probability integral model on the edge of the mobile basin, its poor prediction effect, and its low accuracy, a new mining subsidence prediction model based on the Boltzmann function is proposed. Combined with the transformed normal distribution time function, a B-normal prediction model that can predict the dynamic displacement and deformation of any point on the surface was constructed. The global optimal solution of the parameters of the dynamic prediction model was inversed by introducing particle swarm optimization shuffled frog leaping intelligent algorithm (PSO-SFLA), and then, the model was applied to the 8102 working face of the Guobei coal mine to dynamically predict the subsidence, inclination, curvature, horizontal displacement, and horizontal deformation of the goaf surface. The prediction results showed that on the strike and dip observation lines, the prediction accuracy of the dynamic subsidence and horizontal displacement of the surface could reach the centimeter level, the predicted root mean square error (RMSE) of dynamic tilt and horizontal deformation was less than 0.51 mm/m, and the predicted RMSE of dynamic curvature was within 0.020 mm/m2. The prediction results reflected the dynamic evolution law of surface displacement and deformation and verified the reliability of the B-normal dynamic prediction model, which can fully meet the needs of practical engineering applications.

Cotton aphid infestation monitoring using Sentinel-2 MSI imagery coupled with derivative of ratio spectroscopy and random forest algorithm.

Aphids are one of the main pests of cotton and have been an important disaster limiting cotton yield. It is important to use satellite multispectral data to monitor the severity of cotton aphids in a timely and accurate manner on regional scale. Based on the combination of derivative of ratio spectra (DRS) and random forest (RF) algorithm, this study researched the quantitative monitoring model of cotton aphid severity based on Sentinel-2 data. First, the cotton area was extracted by using a supervised classification algorithm and the vegetation index threshold method. Then, the DRS algorithm was used to analyze the spectral characteristics of cotton aphids from three scales, and the Pearson correlation analysis algorithm was used to extract the bands significantly related to aphid infestation. Finally, the RF model was trained by ground sampling points and its accuracy was evaluated. The optimal model results were selected by the cross-validation method, and the accuracy was compared with the four classical classification algorithms. The results showed that (1) the canopy spectral reflectance curves at different grades of cotton aphid infestation were significantly different, with a significant positive correlation between cotton aphid grade and spectral reflectance in the visible band range and a negative correlation in the near-infrared band range; (2) The DRS algorithm could effectively remove the interference of the background endmember of satellite multispectral image pixels and enhance the aphid spectral features. The analysis results from three different scales and the evaluation results demonstrate the effectiveness of the algorithm in processing satellite multispectral data; (3) After the DRS processing, Sentinel-2 multispectral images could effectively classify the severity of cotton aphid infestation by the RF model with an overall classification accuracy of 80% and a kappa coefficient of 0.73. Compared with the results of four classical classification algorithms, the proposed algorithm has the best accuracy, which proves the superiority of RF. Based on satellite multispectral data, the DRS and RF can be combined to monitor the severity of cotton aphids on a regional scale, and the accuracy can meet the actual need.

Research on the Impact of Absorption Feature Extraction on Spectral Difference Between Similar Minerals.

Diagnostic absorption features can indicate the existence of specific materials, which is the foundation of mineral analysis with optical remote sensing data. In hyperspectral data processing, the most commonly used method to extract absorption feature, is Continuum Removal (CR). As for multispectral data, Principle Component Analysis and other indirect methods were used to extract absorption information, and little research has been done on full-band absorption feature extraction. Classification of similar minerals is one of the major difficulties in mineral spectral analysis, while there is no valid index for spectral difference between similar mineral groups. Absorption feature extraction may improve the classification accuracy, but there is no research to investigate the impact of absorption feature extraction on spectral difference between similar minerals. This paper summarized the principle of mineral spectral difference, and proposed the concept of Class Separability Ratio (CSR), which was verified to be a valid index for spectral difference between similar mineral categories. Through comparison experiments on alunite and kaolinite spectra, including USGS spectral library spectra and resampled spectra in accordance with the band settings of HYPERION, ASTER and OLI, the impact of absorption feature extraction on spectral difference between similar minerals were investigated. Experimental results show that valid absorption feature extraction can greatly enhance the spectral difference between similar minerals, and the spectral difference is positively correlated with spectral resolution. Besides, the results of CR can be severely affected by spectral resolution and band center positions, and the absorption feature spectra extraction results for multispectral datasets need to be improved. This research laid the foundation of precise identification between similar mineral categories, and provided valuable reference for the band settings of future geology remote sensing sensors.

[Research on the model of spectral unmixing for minerals based on derivative of ratio spectroscopy].

The precise analysis of mineral abundance is a key difficulty in hyperspectral remote sensing research. In the present paper, based on linear spectral mixture model, the derivative of ratio spectroscopy (DRS) was introduced for spectral unmixing of visible to short-wave infrared (Vis-SWIR; 0.4 - 2.5 microm) reflectance data. The mixtures of different proportions of plaster and allochite were analyzed to estimate the accuracy of the spectral unmixing model based on DRS. For the best 5 strong linear bands, the Pearson correlation coefficient (PCC) of the abundances and the actual abundances were higher than 99.9%, while the root mean square error (RMSE) is less than 2.2%. The result shows that the new spectral unmixing model based on DRS is simple, of rigorous mathematical proof, and highly precise. It has a great potential in high-precision quantitative analysis of spectral mixture with fixed endmembers.