Soil organic matter (SOM) is one of the most important indicators of soil quality. Accurate spatial information about SOM is critical for sustainable soil utilization and management and environmental protection. Spatially correlated auxiliary information was widely used to improve spatial prediction accuracy. However, the qualitative variables such as soil type, land use type are not being used often as auxiliary variables. In this paper we proposed a spatial prediction method (ST+RBFNN) based on radial basis functional neural network model, using both qualitative and quantitative variables as auxiliary information, to predict the spatial distribution of soil organic matter in Santai County in Sichuan Province, located in the hilly region of mid Sichuan Basin. To establish and validate this method, 2346 soil samples were collected and randomly divided into two groups, as modeling points (1877) and validation points (469). With the modeling points, a radial basis function neural network model was trained using the average content of SOM of each soil genus, topographical factors and vegetation index as auxiliary information to predict the spatial distribution of SOM content within each soil genus. Results showed that, the SOM content ranged from 4.20 to 47.60 g kg^-1, with an average value of 17.97 g kg^-1, a moderate variability. The nugget/sill ratio was 0.742, indicating a weak spatial dependence for SOM. Elevation and slope showed significantly negative correlation with SOM content while topographic wetness index and vegetation index showed significantly positive correlation with SOM. Analysis of variance indicated that there were significant differences in average content of SOM among the different soil types (P<0.01), suggesting that soil types also had significant impact on the spatial distribution of SOM, and soil genus types were better predictors than soil groups. Slope, topographic wetness index and vegetation index showed significant correction with the residuals of average content of SOM (computed by subtracting the average SOM content of the relative soil genus from the original value of each soil sample), indicating that the above three quantitative factors further resulted in the spatial variation of SOM besides soil types. The prediction map obtained by the proposed method was more consistent with the true geographical information than ordinary Kriging (OK), regression Kriging (RK) and neural network combined with ordinary Kriging (RBFNN+OK). Moreover, ST+RBFNN method significantly reduced the prediction errors. Compared to OK, RK and RBFNN+OK, the mean absolute error (MAE) of ST+ RBFNN method was reduced by 31.76%, 28.45% and 26.68%, the mean relative error (MRE) was reduced by 35.90%, 32.55% and 30.75%, and the root mean squared error (RMSE) was reduced by 22.60%, 19.88% and 18.43%. Moreover, this method also showed better capability of predicting the extremum of the validation data. The prediction errors were reduced by 6.88% to 43.70% than the other three methods in predicting the extremum of the validation points (10% of normal distribution of the data). This result suggested that it is helpful for improving the prediction accuracy to employ both qualitative and quantitative variables as auxiliary information in spatial prediction of soil properties, and this proposed method provides a useful research idea for digital soil mapping.

Soil salinization is a process of global land degradation, which hazards the environment. It is caused by inefficient irrigation and the excessive use of water. It reduces the productivity of land. Xinjiang is the typical area of arid and semi-arid region. The monitoring of soil salinization timely and effectively is not only beneficial to the production of agriculture, but also in favor of sustainable development of agricultural land. The purpose of this study is how to improve the classification accuracy. In this paper, the author uses Spectral Angle Mapper method extracting the information of soil salinaztion. In order to improve the accuracy of classification, the author determines the appropriate soil and vegetation spectral library. The appropriate soil and vegetation spectral library decide the accuracy. The use of field measurements of soil spectral reflectance is used to study the soil spectral characteristics. It is combined with hyperspectral data of the Chinese environmental and disaster monitoring and forecasting of small satellites and classified soil salinization based on hyperspectral image. In the first part of this paper, according to the definition of degree of soil salinaztion, four classed of soil are classified, namely non-salined soil, slight-salined soil, moderate-salined soil and heavy-salined soil. The data from four classes of soil can be converted to fourteen transforms of soil spectral reflectance. There are fifteen transforms of soil spectral reflectance. They are the original and the converted fourteen transforms of soil spectral reflectance. According to the findings of the correlation analysis of fifteen transforms of soil spectral reflectance with soil salt content, regression analysis are done. The equations are chosen to estimate soil salt content. And root mean square error (RMSE) is employed to verify the accuracy of the equations. The best equations of estimating soil salt content are decided. In the second part of this paper, the author decides the soil spectral library according to the result of spectral characteristics. The vegetation spectral library is based on field measurements and actual survey. In the final part of this paper, the author uses the SAM method to classify the hyperspectral image based on the soil spectral library and vegetation spectral library. Such a classification is proved good, laying the foundation for the region's hyperspectral applications, giving warning to regional farmers for appropriate farming methods, provided the data for the region's sustainable development. This article identifies the soil and vegetation spectral library of the study area. This helps to further study on spectral characteristics in this region. Environmental and disaster monitoring and forecasting of small satellite is designed and developed by our country. China centre for resources satellite data and application provided for our researchers free. HSI hyperspectral data is also China's the only hyperspectral remote sensing images. This study attempts to contribute to our development of hyperspectral remote sensing images. To speed up the satellite for the applications of environmental monitoring. It is better for the country's environmental monitoring services. The development of hyperspectral remote sensing images will bring a new opportunity and challenge to remote sensing technology. Our researchers should strive for the development of hyperspectral remote sensing technology. The development of hyperspectral remote sensing will promise a better future.