Plant-Dependent Soil Bacterial Responses Following Amendment With a Multispecies Microbial Biostimulant Compared to Rock Mineral and Chemical Fertilizers

Biostimulants are gaining momentum as potential soil amendments to increase plant health and productivity. Plant growth responses to some biostimulants and poorly soluble fertilizers could increase soil microbial diversity and provide greater plant access to less soluble nutrients. We assessed an agricultural soil amended with a multispecies microbial biostimulant in comparison with two fertilizers that differed in elemental solubilities to identify effects on soil bacterial communities associated with two annual pasture species (subterranean clover and Wimmera ryegrass). The treatments applied were: a multispecies microbial biostimulant, a poorly soluble rock mineral fertilizer at a rate of 5.6 kg P ha–1, a chemical fertilizer at a rate of 5.6 kg P ha–1, and a negative control with no fertilizer or microbial biostimulant. The two annual pasture species were grown separately for 10 weeks in a glasshouse with soil maintained at 70% of field capacity. Soil bacteria were studied using 16S rRNA with 27F and 519R bacterial primers on the Mi-seq platform. The microbial biostimulant had no effect on growth of either of the pasture species. However, it did influence soil biodiversity in a way that was dependent on the plant species. While application of the fertilizers increased plant growth, they were both associated with the lowest diversity of the soil bacterial community based on Fisher and Inverse Simpson indices. Additionally, these responses were plant-dependent; soil bacterial richness was highly correlated with soil pH for subterranean clover but not for Wimmera ryegrass. Soil bacterial richness was lowest following application of each fertilizer when subterranean clover was grown. In contrast, for Wimmera ryegrass, soil bacterial richness was lowest for the control and rock mineral fertilizer. Beta diversity at the bacterial OTU level of resolution by permanova demonstrated a significant impact of soil amendments, plant species and an interaction between plant type and soil amendments. This experiment highlights the complexity of how soil amendments, including microbial biostimulants, may influence soil bacterial communities associated with different plant species, and shows that caution is required when linking soil biodiversity to plant growth. In this case, the microbial biostimulant influenced soil biodiversity without influencing plant growth.

Intelligent Identification for Rock-Mineral Microscopic Images Using Ensemble Machine Learning Algorithms

It is significant to identify rock-mineral microscopic images in geological engineering. The task of microscopic mineral image identification, which is often conducted in the lab, is tedious and time-consuming. Deep learning and convolutional neural networks (CNNs) provide a method to analyze mineral microscopic images efficiently and smartly. In this research, the transfer learning model of mineral microscopic images is established based on Inception-v3 architecture. The four mineral image features, including K-feldspar (Kf), perthite (Pe), plagioclase (Pl), and quartz (Qz or Q), are extracted using Inception-v3. Based on the features, the machine learning methods, logistic regression (LR), support vector machine (SVM), random forest (RF), k-nearest neighbors (KNN), multilayer perceptron (MLP), and gaussian naive Bayes (GNB), are adopted to establish the identification models. The results are evaluated using 10-fold cross-validation. LR, SVM, and MLP have a significant performance among all the models, with accuracy of about 90.0%. The evaluation result shows LR, SVM, and MLP are the outstanding single models in high-dimensional feature analysis. The three models are also selected as the base models in model stacking. The LR model is also set as the meta classifier in the final prediction. The stacking model can achieve 90.9% accuracy, which is higher than all the single models. The result also shows that model stacking effectively improves model performance.

An Enhanced Rock Mineral Recognition Method Integrating a Deep Learning Model and Clustering Algorithm

Rock mineral recognition is a costly and time-consuming task when using traditional methods, during which physical and chemical properties are tested at micro- and macro-scale in the laboratory. As a solution, a comprehensive recognition model of 12 kinds of rock minerals can be utilized, based upon the deep learning and transfer learning algorithms. In the process, the texture features of images are extracted and a color model for rock mineral identification can also be established by the K-means algorithm. Finally, a comprehensive identification model is made by combining the deep learning model and color model. The test results of the comprehensive model reveal that color and texture are important features in rock mineral identification, and that deep learning methods can effectively improve identification accuracy. To prove that the comprehensive model could extract effective features of mineral images, we also established a support vector machine (SVM) model and a random forest (RF) model based on Histogram of Oriented Gradient (HOG) features. The comparison indicates that the comprehensive model has the best performance of all.