[Study on estimation of fall dormancy in alfalfa by near infrared reflectance spectroscopy and support vector machine model].

The present study proposes a new approach to producing accurate estimates of fall dormancy (FD) in alfalfa in a rapid manner. Using near infrared spectroscopy, the approach produces results fast without causing damage to samples. Near infrared reflectance spectroscopy was applied to measuring the spectra of samples. Then principal component analysis (PCA) was conducted on the measurements. The top ten principal components were selected based on their cumulative contribution rates to build a support vector machine (SVM) model. Detailed analysis and discussions were conducted over their parameter and kernel classifications. The experiment found that when c = 0.339 2 and g = 32, the accuracy of the predictions of the test set can reach 98.182%. Therefore the approach can estimate the FD in alfalfa in a rapid and accurate manner. Moreover, it was compared with other approaches such as principal component regression, partial least squares regression, BP neural networks, and LVQ neural networks. The comparisons have shown that the PCA-SVM model can effectively address the small-sample-size problem and avoid local minimum.

[Responses of soil fauna to environment degeneration in the process of wind erosion desertification of Hulunbeir steppe].

To reveal the relationships between soil fauna and soil environmental factors in the process of steppe desertification, field survey combined with laboratory analysis was made to study the community structure, population density and biodiversity of soil fauna, and their relationships with the changes of soil organic matter, hydrolysable nitrogen, available phosphorus and moisture contents and soil pH at different stages of desertification of Hulunbeir steppe. The soil faunal specimens collected belonged to 4 phyla, 6 classes and 12 orders. Nematoda was the only dominant group of medium- and small-sized soil fauna, occupying 94.3% of the total, while Coleoptera and Hemiptera were the dominant groups of large-sized soil fauna, with the amount of 79.7%. The group amount, population density, diversity, and evenness of soil fauna had an obvious decreasing trend with the aggravation of steppe desertification. At serious stage of desertification, soil fauna vanished completely. The population density of soil fauna in 0-20 cm soil layer had significant linear correlations with soil nutrients and moisture contents, soil pH, and litter mass, indicating that soil fauna had stronger sensibility to the changes of soil environmental factors in the process of wind erosion desertification of Hulunbeir steppe.