In this mini-review, we focus on the research activities on solid superbase catalysts that have been conducted in the past two decades. We summarize the type and preparation of superbases, the mechanism for the generation of basic sites, and the applications of superbases in catalysis. It is pointed out that several kinds of superbases are reported so far with the majority of solid superbases generated using a single metal oxide as support. However, the superbases are extremely sensitive to water and CO 2 , and rigorous conditions are required for their preparation and utilization. As a consequence, the development and application of solid superbases is limited. Despite the understanding of formation mechanism of superbasic sites being essential for the design of solid superbases, reports on this aspect are scant. It is envisaged that composite metal oxides and porous materials should be developed as support materials to generate novel solid superbases, and our recent research results open up a new route for the design and synthesis of composite oxide superbase materials. Efforts should be devoted to study the generation of superbase sites by adopting advanced techniques for characterization and new methods for theoretical investigation. Moreover, it is predicted that solid superbases will find new applications in catalysis, especially in reactions that require high temperatures for desorption of acidic substances from surfaces of superbases.

No abstract

No abstract

Traffic flow prediction is a critical component of intelligent transportation systems, especially in the prevention of traffic congestion in urban areas. While significant efforts have been devoted to enhancing the accuracy of traffic prediction, the interpretability of traffic prediction also needs to be considered to enhance persuasiveness, particularly in the era of deep-learning-based traffic cognition. Although some studies have explored interpretable neural networks from the feature and result levels, model-level explanation, which explains the reasoning process of traffic prediction through transparent models, remains underexplored and requires more attention. In this paper, we propose a novel self-constructed deep fuzzy neural network, SCDFNN, for traffic flow prediction with model interpretability. By leveraging recent advances in neuro-symbolic computation for automatic rule learning, SCDFNN learns interpretable human traffic cognitive rules based on deep learning, incorporating two innovations: (1) a new fuzzy neural network hierarchical architecture constructed for spatial-temporal dependences in the traffic feature domain; (2) a modified Wang–Mendel method used to fuse regional differences in traffic data, resulting in adaptive fuzzy-rule weights without sacrificing interpretability. Comprehensive experiments on well-known traffic datasets demonstrate that the proposed approach is comparable to state-of-the-art deep models, and the SCDFNN’s unique hierarchical architecture allows for transparency.

No abstract