Numerical Simulation of Uniaxial Compressive Strength and Failure Characteristics of Non-Uniform Water-Bearing Sandstone.

As complex and heterogeneous materials, the mechanical properties of rocks are still in need of further investigation regarding the mechanisms of the effects of water. In engineering projects such as goaf foundation treatment and ecological restoration, it is particularly important to describe the fracturing process of non-uniform water-containing sandstone media. The study utilized the theory of continuum mechanics to adopt an elastoplastic strain-softening constitutive relationship and develop a numerical model for analyzing the uniaxial compressive strength and failure characteristics of non-uniform water-containing sandstone. The results indicate that, compared with the reference rock sample, the shorter the capillary path of water entering the rock sample's internal pores or the larger the contact area with water, the shorter the time required for the rock sample to be saturated. Increasing the water content causes a rapid decline in the rock sample's elastic modulus and intensifies its brittleness. Group D2 and D3 samples exhibited a decrease in average peak strength to 70.4% and 62.1%, respectively, along with a corresponding decrease in the elastic modulus to 90.78% and 76.55%, indicating significant strain softening. While the failure mode of the rock sample remains consistent across different water contents, the homogeneity of failure shows significant variation. Increasing volumetric water content raises the likelihood of interconnecting cracks between rock samples, resulting in a progressive decline in macroscopic mechanical properties such as peak strength, critical strain, and elastic modulus. This research is significant in advancing the theory and construction technology for ecological restoration in goaf areas.

Composite Kernel of Mutual Learning on Mid-Level Features for Hyperspectral Image Classification.

By training different models and averaging their predictions, the performance of the machine-learning algorithm can be improved. The performance optimization of multiple models is supposed to generalize further data well. This requires the knowledge transfer of generalization information between models. In this article, a multiple kernel mutual learning method based on transfer learning of combined mid-level features is proposed for hyperspectral classification. Three-layer homogenous superpixels are computed on the image formed by PCA, which is used for computing mid-level features. The three mid-level features include: 1) the sparse reconstructed feature; 2) combined mean feature; and 3) uniqueness. The sparse reconstruction feature is obtained by a joint sparse representation model under the constraint of three-scale superpixels' boundaries and regions. The combined mean features are computed with average values of spectra in multilayer superpixels, and the uniqueness is obtained by the superposed manifold ranking values of multilayer superpixels. Next, three kernels of samples in different feature spaces are computed for mutual learning by minimizing the divergence. Then, a combined kernel is constructed to optimize the sample distance measurement and applied by employing SVM training to build classifiers. Experiments are performed on real hyperspectral datasets, and the corresponding results demonstrated that the proposed method can perform significantly better than several state-of-the-art competitive algorithms based on MKL and deep learning.

Crop Classification Based on Red Edge Features Analysis of GF-6 WFV Data.

A red edge band is a sensitive spectral band of crops, which helps to improve the accuracy of crop classification. In view of the characteristics of GF-6 WFV data with multiple red edge bands, this paper took Hengshui City, Hebei Province, China, as the study area to carry out red edge feature analysis and crop classification, and analyzed the influence of different red edge features on crop classification. On the basis of GF-6 WFV red edge band spectral analysis, different red edge feature extraction and red edge indices feature importance evaluation, 12 classification schemes were designed based on GF-6 WFV of four bands (only including red, green, blue and near-infrared bands), stepwise discriminant analysis (SDA) and random forest (RF) method were used for feature selection and importance evaluation, and RF classification algorithm was used for crop classification. The results show the following: (1) The red edge 750 band of GF-6 WFV data contains more information content than the red edge 710 band. Compared with the red edge 750 band, the red edge 710 band is more conducive to improving the separability between different crops, which can improve the classification accuracy; (2) According to the classification results of different red edge indices, compared with the SDA method, the RF method is more accurate in the feature importance evaluation; (3) Red edge spectral features, red edge texture features and red edge indices can improve the accuracy of crop classification in different degrees, and the red edge features based on red edge 710 band can improve the accuracy of crop classification more effectively. This study improves the accuracy of remote sensing classification of crops, and can provide reference for the application of GF-6 WFV data and its red edge bands in agricultural remote sensing.

Impact of spring phenology variation on GPP and its lag feedback for winter wheat over the North China Plain.

Spring green-up date (GUD) is a sensitive indicator of climate change, and of great significance to winter wheat production. However, our knowledge of the chain relationships among them is relatively weak. In this study, based on 8-day Enhanced Vegetation Index (EVI) data from Moderate Resolution Imaging Spectroradiometer (MODIS) from 2001 to 2015, we first assessed the performance of four algorithms for extracting winter wheat GUD in the North China Plain (NCP). A multiple linear regression model was then established to quantitatively determine the contributions of the time lag effects of hydrothermal variation on GUD. We further investigated the interactions between GUD and gross primary production (GPP) comprehensively. Our results showed that the rate of change in curvature algorithm (RCCmax) had better performance in capturing the spatiotemporal variation of winter wheat GUD relative to the other three methods (Kmax, CRmax, and cumCRmax). Regarding the non-identical lag time effects of hydrothermal factors, hydrothermal variations could explain winter wheat GUD variations for 82.05% of all pixels, 36.78% higher than that without considering the time lag effects. Variation in GUD negatively correlated with winter wheat GPP after green up in most parts of the NCP, significantly in 35.75% of all pixels with a mean rate of 1.89 g C m-2 yr-1 day-1. Meanwhile, winter wheat GPP exerted a strongly positive feedback on GUD in >82.42% of all pixels (significant in 28.01% of all pixels), characterized by a humped-shape pattern along the long-term average plant productivity. This finding highlights the complex interaction between spring phenology and plant productivity, and also suggests the importance of preseason climate factors on spring phenology.