Nitrogen （N） and phosphorus （P） additions can affect soil microbial carbon （C） accumulation. However, the mechanisms that drive the changes in residual microbial C that occur after N and P additions have not bee...Nitrogen （N） and phosphorus （P） additions can affect soil microbial carbon （C） accumulation. However, the mechanisms that drive the changes in residual microbial C that occur after N and P additions have not been well-defined for Chinese fir plantations in subtropical China. We set up six different treatments, viz. a control （CK）, two N treatments （NI： 50kgha-1 a-1; N2： 100 kg ha-1 a-1）, one P treatment （P： 50 kg ha-1 a-1）, and two combined N and P treatments （NIP： 50kgha-1a-1 of N ＋50kgha-1a-1 of P; N2P：100 kg ha-1 a-1 of N ＋ 50 kg ha-1 a-1 of P）. We then investigated the influences of N and P additions on residual microbial C. The results showed that soil pH and microbial biomass decreased after N additions, while microbial biomass increased after P additions. Soil organic carbon （SOC） and residual microbial C contents increased in the N and P treatments but not in the control. Residual microbial C accumulation varied according to treatment and declined in the order： N2P 〉 N1P 〉 N2 〉 N1 〉 P 〉 CK. Residual microbial C contents were positively correlated with available N, P, and SOC contents, but were negatively correlated with soil pH. The ratio of residual fungal C to residual bacterial C increased under P additions, but declined under combined N1P additions. The ratio of residual microbial C to SOC increased from 11 to 14% under the N1P and N2P treatments, respectively. Our results suggest that the concentrations of residual microbial C and the stability of SOC would increase under combined applications of N and P fertilizers in subtropical Chinese fir plantation soils.展开更多
Three types of molecular markers (SRAP, ISSR and RAPD) were used to identify four Tremella fuciformis strains, T6 (white), T7 (white), T8 (yellow) and T9 (light yellow). Twelve SRAP primer pairs, ten ISSR primers and ...Three types of molecular markers (SRAP, ISSR and RAPD) were used to identify four Tremella fuciformis strains, T6 (white), T7 (white), T8 (yellow) and T9 (light yellow). Twelve SRAP primer pairs, ten ISSR primers and eight RAPD primers were screened, and identification data obtained using the three molecular markers were consistent in that the four T. fuciformis strains were divided into three groups with T7 and T9 clustered together in a single group. Each RAPD primer generated a higher average number of polymorphic bands than either the SRAP or ISSR primers, and the average similarity between the four strains was 81.34%. SRAP markers reflected more genetic information compared with the two other markers, and the average similarity was 68.98%. Genetic information reflected by ISSR markers was intermediate between SRAP and RAPD, and the average similarity was 77.48%.展开更多
To obtain excellent regression results under the condition of small sample hyperspectral data,a deep neural network with simulated annealing(SA-DNN)is proposed.According to the characteristics of data,the attention me...To obtain excellent regression results under the condition of small sample hyperspectral data,a deep neural network with simulated annealing(SA-DNN)is proposed.According to the characteristics of data,the attention mechanism was applied to make the network pay more attention to effective features,thereby improving the operating efficiency.By introducing an improved activation function,the data correlation was reduced based on increasing the operation rate,and the problem of over-fitting was alleviated.By introducing simulated annealing,the network chose the optimal learning rate by itself,which avoided falling into the local optimum to the greatest extent.To evaluate the performance of the SA-DNN,the coefficient of determination(R^(2)),root mean square error(RMSE),and other metrics were used to evaluate the model.The results show that the performance of the SA-DNN is significantly better than other traditional methods.展开更多
This paper deals with the reflectance estimation model issue to improve the estimation accuracy. We propose a model containing two core procedures: dimensionality reduction and model mining. First, the dimensionality ...This paper deals with the reflectance estimation model issue to improve the estimation accuracy. We propose a model containing two core procedures: dimensionality reduction and model mining. First, the dimensionality reduction algorithm of hyperspectral data based on dependence degree(DRNDDD) is proposed to reduce the redundant hyperspectral band. DRND-DD solves the selection of suitable hyperspectral band via rough set theory. Furthermore, to improve the computation speed and accuracy of the model, based on DRND-DD, this paper proposes reflectance estimation model mining of leaf nitrogen concentration(LNC) for hyperspectral data by using hybrid gene expression programming(REMLNC-HGEP). Experimental results on three datasets demonstrate that the DRND-DD algorithm can obtain good results with a very short running time compared with principal component analysis(PCA), singular value decomposition(SVD), a dimensionality reduction algorithm based on the positive region(AR-PR) and a dimensionality reduction algorithm based on a discernable matrix(ARDM), and REMLNC-HGEP has low average time-consumption, high model mining success ratio and estimation accuracy. It was concluded that the REMLNC-HGEP performs better than the regression methods.展开更多
基金jointly financed by the Programs of the National Natural Science Foundation of China(Nos.41571251,41571130043)the Major State Basic Research Development Program of China(No.2012CB416903)
文摘Nitrogen （N） and phosphorus （P） additions can affect soil microbial carbon （C） accumulation. However, the mechanisms that drive the changes in residual microbial C that occur after N and P additions have not been well-defined for Chinese fir plantations in subtropical China. We set up six different treatments, viz. a control （CK）, two N treatments （NI： 50kgha-1 a-1; N2： 100 kg ha-1 a-1）, one P treatment （P： 50 kg ha-1 a-1）, and two combined N and P treatments （NIP： 50kgha-1a-1 of N ＋50kgha-1a-1 of P; N2P：100 kg ha-1 a-1 of N ＋ 50 kg ha-1 a-1 of P）. We then investigated the influences of N and P additions on residual microbial C. The results showed that soil pH and microbial biomass decreased after N additions, while microbial biomass increased after P additions. Soil organic carbon （SOC） and residual microbial C contents increased in the N and P treatments but not in the control. Residual microbial C accumulation varied according to treatment and declined in the order： N2P 〉 N1P 〉 N2 〉 N1 〉 P 〉 CK. Residual microbial C contents were positively correlated with available N, P, and SOC contents, but were negatively correlated with soil pH. The ratio of residual fungal C to residual bacterial C increased under P additions, but declined under combined N1P additions. The ratio of residual microbial C to SOC increased from 11 to 14% under the N1P and N2P treatments, respectively. Our results suggest that the concentrations of residual microbial C and the stability of SOC would increase under combined applications of N and P fertilizers in subtropical Chinese fir plantation soils.
基金Sponsored by the Foundation for the Structural Opti mization of the Agricultural Industry (No .06-11-01B)
文摘Three types of molecular markers (SRAP, ISSR and RAPD) were used to identify four Tremella fuciformis strains, T6 (white), T7 (white), T8 (yellow) and T9 (light yellow). Twelve SRAP primer pairs, ten ISSR primers and eight RAPD primers were screened, and identification data obtained using the three molecular markers were consistent in that the four T. fuciformis strains were divided into three groups with T7 and T9 clustered together in a single group. Each RAPD primer generated a higher average number of polymorphic bands than either the SRAP or ISSR primers, and the average similarity between the four strains was 81.34%. SRAP markers reflected more genetic information compared with the two other markers, and the average similarity was 68.98%. Genetic information reflected by ISSR markers was intermediate between SRAP and RAPD, and the average similarity was 77.48%.
基金supported by the National Natural Science Foundation of China(Nos.62001023,61922013)Beijing Natural Science Foundation(No.4232013).
文摘To obtain excellent regression results under the condition of small sample hyperspectral data,a deep neural network with simulated annealing(SA-DNN)is proposed.According to the characteristics of data,the attention mechanism was applied to make the network pay more attention to effective features,thereby improving the operating efficiency.By introducing an improved activation function,the data correlation was reduced based on increasing the operation rate,and the problem of over-fitting was alleviated.By introducing simulated annealing,the network chose the optimal learning rate by itself,which avoided falling into the local optimum to the greatest extent.To evaluate the performance of the SA-DNN,the coefficient of determination(R^(2)),root mean square error(RMSE),and other metrics were used to evaluate the model.The results show that the performance of the SA-DNN is significantly better than other traditional methods.
基金supported in part by the National Natural Science Foundation of China (11&zd167, 51507084, 61572262)NSF of Jiangsu Province (BK20141427)+2 种基金NUPT (NY214097)Open research fund of Key Lab of Broadband Wireless Communication and Sensor Network Technology (NUPT), Ministry of Education (NYKL201507)Qinlan Project of Jiangsu Province and the General Project of National Natural Science Found of China under Grant 41471300
文摘This paper deals with the reflectance estimation model issue to improve the estimation accuracy. We propose a model containing two core procedures: dimensionality reduction and model mining. First, the dimensionality reduction algorithm of hyperspectral data based on dependence degree(DRNDDD) is proposed to reduce the redundant hyperspectral band. DRND-DD solves the selection of suitable hyperspectral band via rough set theory. Furthermore, to improve the computation speed and accuracy of the model, based on DRND-DD, this paper proposes reflectance estimation model mining of leaf nitrogen concentration(LNC) for hyperspectral data by using hybrid gene expression programming(REMLNC-HGEP). Experimental results on three datasets demonstrate that the DRND-DD algorithm can obtain good results with a very short running time compared with principal component analysis(PCA), singular value decomposition(SVD), a dimensionality reduction algorithm based on the positive region(AR-PR) and a dimensionality reduction algorithm based on a discernable matrix(ARDM), and REMLNC-HGEP has low average time-consumption, high model mining success ratio and estimation accuracy. It was concluded that the REMLNC-HGEP performs better than the regression methods.
