MWMingyang Wang

Mingyang Wang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Mingyang Wang has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    GAT-Informer: A Spatiotemporal Graph Neural Network Model for Urban Passenger Flow Forecasting

    by Yongjian Ma, Mingyang Wang, Wei Zhou, Huifu Jiang, Xiao Qin, Linsen Du, Jinyang Cao

    Accurate bus passenger flow prediction is a critical prerequisite for optimizing resource allocation in intelligent bus systems and improving public transport service quality. However, due to dynamic fluctuations in passenger travel demand and the complex topological structure of bus networks, effectively capturing the inherent spatiotemporal dependencies of passenger flow remains a significant challenge. To address this issue, this paper proposes GAT-Informer, a hybrid deep learning model for short-term bus passenger flow prediction. Unlike conventional methods that mainly rely on fixed physical adjacency or single-view spatial correlations, the proposed model incorporates domain knowledge into graph construction through a four-dimensional associated-node mechanism. Specifically, four types of features, namely line connectivity, spatial proximity, OD correlation, and station functional similarity, are used to identify relevant associated nodes and construct a passenger flow interaction spatiotemporal graph that better reflects inter-station dependencies. Based on this graph, a Graph Attention Network (GAT) is introduced to adaptively learn spatial interaction features and differentiated influence weights among associated stations. The spatially enhanced features extracted by GAT are then fed into the Informer network, where probabilistic sparse self-attention and hierarchical timestamp encoding are employed to efficiently capture long-term temporal dependencies and periodic fluctuation patterns of passenger flow. Experimental results based on bus passenger flow data from Foshan City show that the proposed GAT-Informer model significantly outperforms benchmark models, including LSTM-Transformer, CNN-GRU, and STGCN, across different prediction horizons, validating its effectiveness and improved predictive performance in bus passenger flow prediction.


  • Open Access

    Sedimentary Facies Types and Their Control of Reservoirs in the Lower Jurassic Lacustrine Facies Shale of the Lianggaoshan Formation, Northeastern Sichuan Basin, China

    by Chao Ni, Xueju Lv, Xinjian Zhu, Jianyong Zhang, Jiahao Wang, Mingyang Wang, Ruibin Xu

    In recent years, new breakthroughs have been made in the field of shale oil and gas exploration in the Lower Jurassic Lianggaoshan Formation in Sichuan Basin. At present, there is a lack of systematic studies on reservoir properties and sedimentary facies of the Lianggaoshan Formation shale. Therefore, in this study, taking the Lianggaoshan Formation in Sichuan Basin as an example, the sedimentary facies types of shale reservoirs and their control over shale oil and gas are systematically studied, based on a large number of outcrops, experimental testing, logging, and seismic interpretation methods. The results show that five sedimentary microfacies are developed in the Lianggaoshan Formation in the study area, namely, semi-deep lake mud, shallow lake mud, wave-influenced shallow lake mud, delta-influenced shallow lake mud, and underwater interbranch bay microfacies. The stratum thickness of the Lianggaoshan Formation is in the range of 26–315 m, and mainly distributed in the eastern region, but rapidly thinned in the northwestern region. The sedimentary sequence framework of the Lianggaoshan Formation has been constructed. Moreover, the lithology of the Lianggaoshan Formation shale has been divided into three types, including shale, massive mudstone and silty mudstone. The brittleness index and total organic carbon (TOC) value of three types of shale show a negative correlation. Silty mudstone has the highest brittleness, while that of black shale is the lowest. For porosity and permeability, massive mudstone is better than silty mudstone, and silty mudstone is better than black shale. There are many kinds of matrix pores in the Lianggaoshan Formation shale, and the development degree of inorganic pores is higher than that of organic pores. Finally, based on the analysis of oil-bearing, pore types, physical properties and productivity, it is considered that black shale facies is the most favorable lithofacies type. The deep–semi-deep lacustrine facies belt obviously controls the shale oil enrichment of the Lianggaoshan Formation.