Search

Perovskite is a kind of promising class of materials nowadays because of its exciting performance in energy, catalysis, semiconductor, and many other areas. Machine learning is a potential method by using big data to mine the deep hidden laws of the data and make some predictions of the new data. Applying machine learning method in perovskite is a meaningful attempt to explore the new material with new properties and to predict the properties of new materials. This review shows recent progress of perovskite using machine learning, and these attempts show the success of combining big data technique and material science which give us the new direction to explore the application of machine learning method and the new tools for material science.

A binder-free 3D SnO2 nanosheet/holey graphene composite electrode with an areal capacity of 2.5 mA h cm−2 shows great potential for SIBs.

Substandard housing is considered a public health issue worldwide. Migrants are more likely than other individuals to experience poor housing conditions in urban China, and these challenges in housing conditions have deep effects on migrant health. This study characterizes the relationship between housing satisfaction and migrant health in Hangzhou, China. In particular, 17 indicators for assessing housing satisfaction, which include the indoor environment (IE), outdoor environment (OE) and safety (SE), are integrated. In order to reveal the physical health and mental health status of migrants, a physical component summary (PCS) and mental component summary (MCS) were assessed by using a Twelve-Item Short-Form Health Survey. Multivariate linear regression was further employed to quantify the associations between housing satisfaction and migrant health. The results showed that high satisfaction with the indoor environment, outdoor environment and safety can improve the physical health of migrants. High housing satisfaction, in addition to satisfaction with the outdoor environment, has a significant relationship with the mental health of migrants. Income is associated with migrant health since it plays a key role in determining migrants’ socioeconomic and demographic characteristics and subjective aspirations. However, per capita living space does not have a significant association with migrant health because most of the migrants live in small living spaces in the study area. According to the findings, implications for housing policies that can better integrate housing conditions and health are proposed.

Molecular properties play a crucial role in material discovery, protein interaction and drug development. The appearance of Graph Neural Network(GNN) significantly improved the performance of molecular property prediction. However, nodes in GNN only update the features of neighbor nodes, resulting in insufficient ability to encode global feature information. The self attention mechanism in transformer encodes the global information of molecules, while its spatial information is insufficient. Since molecules are three-dimensional spatial structures, spatial geometry information is an important attribute of molecules. Therefore, a transformer based geometric enhanced graph neural network (TG-GNN) is proposed to combine global and local molecule information with three-dimensional spatial structures to predict molecular properties. In this network, Graph neural network Geometric Feature Fusion Module (GGFF) and Transformer Geometric Feature Enhancement Module (TGF) are proposed to enhance the spatial geometry learning ability of the network. The GGFF module constructs a parallel graph neural network using bond and bond angle. The introduction of bond angle effectively complements the spatial information of the network. The TGF module introduces the coordinates and centrality degree features into the transformer to enhance the geometric expression ability of the module. GGFF module and TGF module encode local information and global information of molecules at the same time on the QM9 and OMDB dataset.

Wear particles produced by machines in the process of wear carry valuable information including wear mechanism and wear severity. Wear particle classification based on wear particle images provides predictive analysis for wear condition of machines. A novel wear particle recognition network based on feature fusion, FFWR-Net, is proposed in this research paper for wear particle images classification. In FFWR-Net, traditional feature extraction method by image processing technique (i.e. manually feature extracting) and deep learning convolutional neural network method (i.e. automatically feature extracting) is paralleled to extract the features of wear particle image. Then the features obtained by two different methods are fused together for building a wear particle classifier. In order to verify the effectiveness of the proposed classifier, it is compared with the previous convolutional neural network models on the same wear particle dataset. The comparison results show the accuracy and effectiveness of the proposed FFWR-Net classifier is better than the previous models.

Farmland property rights allocation such as farmland transfer has an important impact on economic development in rural areas and farmers’ livelihoods in developing countries. Examining the impacts of the external socioeconomic conditions helps realize the desired farmland transfer. This study attempts to analyze the underlying influencing factors of farmland transfer in urbanizing China. In particular, 18 underlying influencing factors are selected to describe urbanization and natural condition. Pearson correlation coefficients are computed to measure the linear relationships between underlying influencing factors and farmland transfer. The geographical detector method is further employed to quantify the individual effects of urbanization on farmland transfer and the interaction effects of urbanization on farmland transfer by assessing the degrees of spatial stratified heterogeneity. We discover that the effects of urban–rural basic living allowance gap, regional GDP per capita, urban population proportion on the proportion of transferred farmland area, proportion of farmland transferred to non-farmer users and proportion of transferred farmland cultivated non-grain crop are the strongest, respectively. The indices of urbanization level present have higher effects on farmland transfer than those of the urban–rural gap. Meanwhile, the interaction effect between two urbanization indices enhances the effect on the farmland transfer. Our study is believed to deepen the understanding of urbanization on farmland property rights allocation in rapidly urbanizing areas. It offers new insights into realizing the sustainable land use strategy in the socioeconomic transition in developing countries.

In this paper, a feature fusion method with guiding training (FGT-Net) is constructed to fuse image data and numerical data for some specific recognition tasks which cannot be classified accurately only according to images. The proposed structure is divided into the shared weight network part, the feature fused layer part, and the classification layer part. First, the guided training method is proposed to optimize the training process, the representative images and training images are input into the shared weight network to learn the ability that extracts the image features better, and then the image features and numerical features are fused together in the feature fused layer to input into the classification layer for the classification task. Experiments are carried out to verify the effectiveness of the proposed model. Loss is calculated by the output of both the shared weight network and classification layer. The results of experiments show that the proposed FGT-Net achieves the accuracy of 87.8%, which is 15% higher than the CNN model of ShuffleNetv2 (which can process image data only) and 9.8% higher than the DNN method (which processes structured data only).

Wear particle image analysis is an effective method to detect wear condition of mechanical devices. However, the recognition accuracy and recognition efficiency for online wear particle automatic recognition are always mutual restricted because the online wear particle images have almost no texture information and lack clarity. Especially for confusing fatigue wear particles and sliding wear particles, the online recognition is a challenging task. Based on this requirement, a super-resolution reconstruct technique and partial hierarchical convolutional neural network, SR-PHnet, is proposed to classify wear particles in one step. The structure of this network is composed by three modules, one is super-resolution layer module, the second is convolutional neural network classifier module, and the third is support vector machine (SVM) classifier module. The classification result of the second module is partial input to the third module for precision classification of fatigue and sliding particles. In addition, a new feature of radial edge factor (REF) is put forward to target fatigue and sliding wear particles. The test result shows that the new feature has the capability to distinguish fatigue and sliding particles well and time saving. The comparison experiments of the convolution neural network (CNN) method, support vector machine method (SVM) with and without REF feature, and integrated model of back-propagation (BP) and CNN are produced. The comparison results show that the online recognition speed and online recognition rate of the proposed SR-PHnet model in this paper are both improved markedly, especially for fatigue and sliding wear particles.

Social and economic factors relate to the prevention and control of infectious diseases. The purpose of this paper was to assess the distribution of COVID-19 morbidity rate in association with social and economic factors and discuss the implications for urban development that help to control infectious diseases. This study was a cross-sectional study. In this study, social and economic factors were classified into three dimensions: built environment, economic activities, and public service status. The method applied in this study was the spatial regression analysis. In the 13 districts in Wuhan, the spatial regression analysis was applied. The results showed that: 1) increasing population density, construction land area proportion, value-added of tertiary industry per unit of land area, total retail sales of consumer goods per unit of land area, public green space density, aged population density were associated with an increased COVID-19 morbidity rate due to the positive characteristics of estimated coefficients of these variables. 2) increasing average building scale, GDP per unit of land area, and hospital density were associated with a decreased COVID-19 morbidity rate due to the negative characteristics of estimated coefficients of these variables. It was concluded that it is possible to control infectious diseases, such as COVID-19, by adjusting social and economic factors. We should guide urban development to improve human health.

Environmental noise has a major negative impact, causing interference for people to communicate, rest, sleep, and general annoyance. In order to control urban environmental noise, simulation-based optimisation for urban environmental noise is conducted. On the basis of the current acoustic environment of Zhaohui Campus of Zhejiang University of Technology, three optimisation plans that include noise barrier optimisation, greenbelt optimisation, and a combination optimisation of noise barrier and greenbelt are proposed. These scenarios are simulated using NoiseSystem software to obtain their ability to reduce noise and determine auditory perception by using different control measures. To determine the visual perception of the optimisation plan, 100 people of different age groups were randomly selected, and each person scored the noise barrier and the greenbelt in the simulated scenarios. Results of the comprehensive evaluation of auditory and visual perception show that noise barriers can provide better auditory feelings, but greenbelts can provide a better auditory and visual subjective experience. Therefore, in addition to the application of noise control measures, their visual design must be fully considered. Moreover, the visual perception of plants is stronger than that of others.

Biomedical degradable polyester materials are widely used in medical field because of their excellent mechanical properties and degradation properties. Analysis of the degradation process and strength change of biomedical degradable materials is essential for clinical use. The evolution of structure from micro to mesoscale is critical for chain broken, recrystallization and macro strength performance during polymer degradation. A structure pattern dynamic interaction method coupled with multi-scale model is proposed in this paper to simulate the degradation process. In the process of status evolution, Blocked Cavity structure pattern (BC pattern) and Blocked Amorphous pattern (BA pattern) are denoted as the interaction of different phases due to their influence on chain scission and oligomer diffusion. In strength structure, Crystalline Island pattern, Amorphous Island pattern and Vacancy Marsh pattern are defined as the interaction to model the strength support. An algorithm named Boundary Encirclement Algorithm (BEA) is designed for the interaction pattern recognition. With the evolution of different phase patterns and the interaction of different phases, chain broken, recrystallization and oligomer diffusion are reconsidered in local area. And strength model is constructed which is based on the interaction of strength patterns. The coupled multiscale model is denoted as Structure Dynamic Interaction-Multiscale Degradation Model (SDI-MSDM). Calculated examples are compared with the experimental data. The simulation value and the experimental value are well fitted, which indicates that the patterns recognition affect the model calculation.