Northeast Agricultural University

About: Northeast Agricultural University is a education organization based out in Harbin, China. It is known for research contribution in the topics: Gene & Population. The organization has 14428 authors who have published 9850 publications receiving 126705 citations. The organization is also known as: Dōngběi Nóngyè Dàxué.

Development of a national VNIR soil-spectral library for soil classification and prediction of organic matter concentrations

Abstract: Soil visible-near infrared diffuse reflectance spectroscopy (vis-NIR DRS) has become an important area of research in the fields of remote and proximal soil sensing. The technique is considered to be particularly useful for acquiring data for soil digital mapping, precision agriculture and soil survey. In this study, 1581 soil samples were collected from 14 provinces in China, including Tibet, Xinjiang, Heilongjiang, and Hainan. The samples represent 16 soil groups of the Genetic Soil Classification of China. After air-drying and sieving, the diffuse reflectance spectra of the samples were measured under laboratory conditions in the range between 350 and 2500 nm using a portable vis-NIR spectrometer. All the soil spectra were smoothed using the Savitzky-Golay method with first derivatives before performing multivariate data analyses. The spectra were compressed using principal components analysis and the fuzzy k-means method was used to calculate the optimal soil spectral classification. The scores of the principal component analyses were classified into five clusters that describe the mineral and organic composition of the soils. The results on the classification of the spectra are comparable to the results of other similar research. Spectroscopic predictions of soil organic matter concentrations used a combination of the soil spectral classification with multivariate calibration using partial least squares regression (PLSR). This combination significantly improved the predictions of soil organic matter (R 2 = 0.899; RPD = 3.158) compared with using PLSR alone (R 2 = 0.697; RPD = 1.817).

Can Deep Learning Identify Tomato Leaf Disease

Abstract: This paper applies deep convolutional neural network (CNN) to identify tomato leaf disease by transfer learning. AlexNet, GoogLeNet, and ResNet were used as backbone of the CNN. The best combined model was utilized to change the structure, aiming at exploring the performance of full training and fine-tuning of CNN. The highest accuracy of 97.28% for identifying tomato leaf disease is achieved by the optimal model ResNet with stochastic gradient descent (SGD), the number of batch size of 16, the number of iterations of 4992, and the training layers from the 37 layer to the fully connected layer (denote as “fc”). The experimental results show that the proposed technique is effective in identifying tomato leaf disease and could be generalized to identify other plant diseases.

Effects of continuous cucumber cropping and alternative rotations under protected cultivation on soil microbial community diversity

Abstract: The diversity of soil microbial communities as affected by continuous cucumber cropping and alternative rotations under protected cultivation were evaluated using community level physiological profiles (CLPP) and random amplified polymorphic DNA (RAPD) analysis. The soils were selected from six cucumber cropping systems, which cover two cropping practices (rotation and continuous cropping) and a wide spectrum for cucumber cropping history under protected cultivation. Shannon–Weaver index and multivariate analysis were performed to characterize variations in soil microbial communities. Both CLPP and RAPD techniques demonstrated that cropping systems and plastic-greenhouse cultivation could considerably affect soil microbial functional diversity and DNA sequence diversity. The open-field soil had the highest Shannon–Weaver index (3.27 for CLPP and 1.50 for RAPD), whereas the lowest value occurred in the 7-year continuous protected cultivation soil (3.27 for CLPP and 1.50 for RAPD). The results demonstrated that continuous plastic-greenhouse cultivation and management can cause the reduction in the species diversity of the biota. Higher Shannon–Weaver index and coefficients of DNA sequence similarity were found in soils under rotation than those under continuous cropping. Cluster analysis also indicated that microbial community profiles of continuous cultivation soils were different from profiles of rotation soils. The reduction in diversity of microbial communities found in continuous cultivation soils as compared with rotation soils might be due to the differences in the quantity, quality and distribution of soil organic matter.