Properly selecting electrode materials for antimony telluride (Sb 2 Te 3 ) thermoelectric (TE) thin film enhances the power factor. This study analyzed the compositional variation and measured the TE properties of pristine antimony telluride (Sb 2 Te 3 ), Ni/Sb 2 Te 3 / Ni, and Cu/Sb 2 Te 3 /Cu thin films that were aged to simulate real applications. The rapid diffusion of Cu in the Cu/Sb 2 Te 3 /Cu film resulted in the massive growth of the CuTe intermetallic compound (IMC), which led to Te deficiency. Te deficiency causes the formation of antisite Sb Te ′ and reduces the power factor. Antisite Te Sb• increases the power factor because the growth of Sb 2 O 3 on the pristine Sb 2 Te 3 and Ni/Sb 2 Te 3 /Ni films, in which almost no Ni diffusion occurs, results in Sb deficiency. The formation of oxides and IMCs alters the stoichiometry of the films. The formation of the NiTe reaction layer at the interface becomes a self-barrier that inhibits Ni diffusion to the Sb 2 Te 3 film. Herein, a defect reaction is proposed to explain the effects of such changes on the TE properties and the relationship between the stoichiometry of the films and the concentrations of the antisites.
The UN 2030 Agenda sets poverty eradication as the primary goal of sustainable development. An accurate measurement of poverty is a critical input to the quality and efficiency of poverty alleviation in rural areas. However, poverty, as a geographical phenomenon, inevitably has a spatial correlation. Neglecting the spatial correlation between areas in poverty measurements will hamper efforts to improve the accuracy of poverty identification and to design policies in truly poor areas. To capture this spatial correlation, this paper proposes a new poverty measurement model based on a neural network, namely, the spatial vector deep neural network (SVDNN), which combines the spatial vector neural network model (SVNN) and the deep neural network (DNN). The SVNN was applied to measure spatial correlation, while the DNN used the SVNN output vector and explanatory variables dataset to measure the multidimensional poverty index (MPI). To determine the optimal spatial correlation structure of SVDNN, this paper compares the model performance of the spatial distance matrix, spatial adjacent matrix and spatial weighted adjacent matrix, selecting the optimal performing spatial distance matrix as the input data set of SVNN. Then, the SVDNN model was used for the MPI measurement of the Yangtze River Economic Belt, after which the results were compared with three baseline models of DNN, the back propagation neural network (BPNN), and artificial neural network (ANN). Experiments demonstrate that the SVDNN model can obtain spatial correlation from the spatial distance dataset between counties and its poverty identification accuracy is better than other baseline models. The spatio-temporal characteristics of MPI measured by SVDNN were also highly consistent with the distribution of urban aggregations and national-level poverty counties in the Yangtze River Economic Belt. The SVDNN model proposed in this paper could effectively improve the accuracy of poverty identification, thus reducing the misallocation of resources in tracking and targeting poverty in developing countries.
Landform recognition is one of the most significant aspects of geomorphology research, which is the essential tool for landform classification and understanding geomorphological processes. Watershed object-based landform recognition is a new spot in the field of landform recognition. However, in the relevant studies, the quantitative description of the watershed generally focused on the overall terrain features of the watershed, which ignored the spatial structure and topological relationship, and internal mechanism of the watershed. For the first time, we proposed an effective landform recognition method from the perspective of the watershed spatial structure, which is separated from the previous studies that invariably used terrain indices or texture derivatives. The slope spectrum method was used herein to solve the uncertainty issue of the determination on the watershed area. Complex network and P–N terrain, which are two effective methodologies to describe the spatial structure and topological relationship of the watershed, were adopted to simulate the spatial structure of the watershed. Then, 13 quantitative indices were, respectively, derived from two kinds of watershed spatial structures. With an advanced machine learning algorithm (LightGBM), experiment results showed that the proposed method showed good comprehensive performances. The overall accuracy achieved 91.67% and the Kappa coefficient achieved 0.90. By comparing with the landform recognition using terrain indices or texture derivatives, it showed better performance and robustness. It was noted that, in terms of loess ridge and loess hill, the proposed method can achieve higher accuracy, which may indicate that the proposed method is more effective than the previous methods in alleviating the confusion of the landforms whose morphologies are complex and similar. In addition, the LightGBM is more suitable for the proposed method, since the comprehensive manifestation of their combination is better than other machine learning methods by contrast. Overall, the proposed method is out of the previous landform recognition method and provided new insights for the field of landform recognition; experiments show the new method is an effective and valuable landform recognition method with great potential as well as being more suitable for watershed object-based landform recognition.
Traffic flow forecasting is a critical input to intelligent transportation systems. Accurate traffic flow forecasting can provide an effective reference for implementing traffic management strategies, developing travel route planning, and public transportation risk assessment. Recent deep learning approaches of spatiotemporal neural networks to predict traffic flow show promise, but could be difficult to separately model the spatiotemporal aggregation in traffic data and intrinsic correlation or redundancy of spatiotemporal features extracted by the filter of the convolutional network. This can introduce biases in the predictions that interfere with subsequent planning decisions in transportation. To solve the mentioned problem, the filter attention-based spatiotemporal neural network (FASTNN) was proposed in this paper. First, the model used 3-dimensional convolutional neural networks to extract universal spatiotemporal dependencies from three types of historical traffic flow, the residual units were employed to prevent network degradation. Then, the filter spatial attention module was constructed to quantify the spatiotemporal aggregation of the features, thus enabling dynamic adjustment of the spatial weights. To model the intrinsic correlation and redundancy of features, this paper also constructed a lightweight module, named matrix factorization based resample module, which automatically learned the intrinsic correlation of the same features to enhance the concentration of the model on information-rich features, and used matrix factorization to reduce the redundant information between different features. The FASTNN has experimented on two large-scale real datasets (TaxiBJ and BikeNYC), and the experimental results show that the FASTNN has better prediction performance than various baselines and variant models.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.