Nitrogen (N) is one of the main factors affecting environmental pollution. In recent years, non-point source pollution and water body eutrophication have become increasing concerns for both scientists and the policy-makers. In order to assess the environmental hazard of soil total N pollution, a typical ecological unit was selected as the experimental site. This paper showed that Box-Cox transformation achieved normality in the data set, and dampened the effect of outliers. The best theoretical model of soil total N was a Gaussian model. Spatial variability of soil total N at NE60° and NE150° directions showed that it had a strip anisotropic structure. The ordinary kriging estimate of soil total N concentration was mapped. The spatial distribution pattern of soil total N in the direction of NE150° displayed a strip-shaped structure. Kriging standard deviations (KSD) provided valuable information that will increase the accuracy of total N mapping. The probability kriging method is useful to assess the hazard of N pollution by providing the conditional probability of N concentration exceeding the threshold value, where we found soil total N>2.0g/kg. The probability distribution of soil total N will be helpful to conduct hazard assessment, optimal fertilization, and develop management practices to control the non-point sources of N pollution.
To meet the demand of large-scale agricultural monitoring system with remote sensing, extracting crop area planted must
be rapid, precise and reliable. In this paper, winter wheat identification with MODIS data in 2004 is taken as example in
North China. Applying spectral analysis and integrating genetic algorithm with neural network (GA-BP) is proposed,
which gives attention to two optimization algorithm, genetic algorithm and back propagation algorithm. According to the
spectral and biological characteristics of winter wheat, Red, Blue, NIR, ESWIR, LSWI, EVI are selected as characteristic
parameters. Then GA-BP algorithm is used for winter wheat identification. Results show that compared with maximum
likelihood and back propagation neural network classification algorithm, the GA-BP algorithm can not only run with
better efficiency, but also achieve best accuracy of identification. Therefore, it is the operational method for agricultural
condition monitoring with remote sensing and information service system at national level.