No abstract

Rhizosphere microbiome adapts their structural compositions to water scarcity and have the potential to mitigate drought stress of plants. To unlock this potential, it is crucial to understand community responses to drought in the interplay between soil properties, water management and exogenous microbes interference. Inoculation with dark septate endophytes (DSE) (Acrocalymma vagum, Paraboeremia putaminum) and Trichoderma viride on Astragalus mongholicus grown in the non-sterile soil was exposed to drought. Rhizosphere microbiome were assessed by Illumina MiSeq sequencing of the 16S and ITS2 rRNA genes. Inoculation positively affected plant growth depending on DSE species and water regime. Ascomycota, Proteobacteria, Actinobacteria, Chloroflexi and Firmicutes were the dominant phyla. The effects of dual inoculation on bacterial community were greater than those on fungal community, and combination of P. putaminum and T. viride exerted a stronger impact on the microbiome under drought stress. The observed changes in soil factors caused by inoculation could be explained by the variations in microbiome composition. Rhizosphere microbiome mediated by inoculation exhibited distinct preferences for various growth parameters. These findings suggest that dual inoculation of DSE and T. viride enriched beneficial microbiota, altered soil nutrient status and might contribute to enhance the cultivation of medicinal plants in dryland agriculture.

We investigate the statistical behaviors of Chinese stock market fluctuations by independent component analysis. The independent component analysis (ICA) method is integrated into the neural network model. The proposed approach uses ICA method to analyze the input data of neural network and can obtain the latent independent components (ICs). After analyzing and removing the IC that represents noise, the rest of ICs are used as the input of neural network. In order to forect the fluctuations of Chinese stock market, the data of Shanghai Composite Index is selected and analyzed, and we compare the forecasting performance of the proposed model with those of common BP model integrating principal component analysis (PCA) and single BP model. Experimental results show that the proposed model outperforms the other two models no matter in relatively small or relatively large sample, and the performance of BP model integrating PCA is closer to that of the proposed model in relatively large sample. Further, the prediction results on the points where the prices fluctuate violently by the above three models relatively deviate from the corresponding real market data.

No abstract