Research on Intelligent Prediction Method for Dynamic Changes of Manufacturing Industrial Land Based on Graph Attention and Spatial Decoding
DOI:
https://doi.org/10.4108/eetsis.14321Keywords:
Manufacturing industrial land change, Spatiotemporal prediction, Graph attention network, Transformer, Spatial decodingAbstract
Recent advances in artificial intelligence have enabled effective modeling of complex industrial spatial systems. Predicting dynamic changes in manufacturing industrial land remains challenging due to spatial heterogeneity and temporal evolution across multiple influencing factors. This study develops a computational framework that integrates graph attention networks and Transformer-based temporal modeling with a spatial decoding module to forecast manufacturing industrial land change. Historical multi-source data spanning 2014 to 2023 are structured as a spatiotemporal graph, with nodes representing spatial units and edges encoding spatial proximity, transportation connections, and functional similarity. Graph attention networks learn the influence of neighboring units, while the Transformer captures temporal dependencies across consecutive periods. The spatial decoding module converts node-level predictions into geographic maps, generating interpretable probability and classification outputs. Experiments demonstrate that the proposed method outperforms baseline models in node-level classification with an accuracy of 0.768 and a Macro-F1 score of 0.712, achieves high spatial consistency with a Kappa of 0.668 and a mean intersection over union of 0.498, and accurately predicts manufacturing industrial land change intensity with a mean absolute error of 0.077 and an R² of 0.765. A component-wise ablation experiment further evaluates the contributions of the main model components. The results show that combining spatial graph modeling with temporal deep learning provides a robust computational approach for manufacturing industrial land change prediction and supports data-driven industrial land planning decisions.
References
[1] Lee J, Davari H, Singh J, et al. Industrial Artificial Intelligence for industry 4.0-based manufacturing systems[J]. Manufacturing Letters, 2018, 18: 20-23.
[2] Leng J, Zhu X, Huang Z, et al. Unlocking the power of industrial artificial intelligence towards Industry 5.0: Insights, pathways, and challenges[J]. Journal of Manufacturing Systems, 2024, 73: 349-363.
[3] Mansour S, Al-Belushi M, Al-Awadhi T. Monitoring land use and land cover changes in the mountainous cities of Oman using GIS and CA-Markov modelling techniques[J]. Land use policy, 2020, 91: 104414.
[4] Verburg P H, Soepboer W, Veldkamp A, et al. Modeling the spatial dynamics of regional land use: the CLUE-S model[J]. Environmental management, 2002, 30(3): 391-405.
[5] Xu L, Liu X, Tong D, et al. Forecasting urban land use change based on cellular automata and the PLUS model[J]. Land, 2022, 11(5): 652.
[6] Kuang W, Liu J, Dong J, et al. The rapid and massive urban and industrial land expansions in China between 1990 and 2010: A CLUD-based analysis of their trajectories, patterns, and drivers[J]. Landscape and Urban Planning, 2016, 145: 21-33.
[7] Zhang S, Li C, Ma Z, et al. Influences of different transport routes and road nodes on industrial land conversion: A case study of Changchun City of Jilin Province, China[J]. Chinese Geographical Science, 2020, 30(3): 544-556.
[8] Wang J, Hadjikakou M, Hewitt R J, et al. Simulating large-scale urban land-use patterns and dynamics using the U-Net deep learning architecture[J]. Computers, Environment and Urban Systems, 2022, 97: 101855.
[9] Niu H, Silva E A. Delineating urban functional use from points of interest data with neural network embedding: A case study in Greater London[J]. Computers, Environment and Urban Systems, 2021, 88: 101651.
[10] Ren Y, Xie Z, Zhai S. Urban land use classification model fusing multimodal deep features[J]. ISPRS International Journal of Geo-Information, 2024, 13(11): 378.
[11] Corso G, Stark H, Jegelka S, et al. Graph neural networks[J]. Nature Reviews Methods Primers, 2024, 4: 17.
[12] Scarselli F, Gori M, Tsoi A C, et al. The graph neural network model[J]. IEEE Transactions on Neural Networks, 2009, 20(1): 61-80.
[13] Kipf T N, Welling M. Semi-Supervised Classification with Graph Convolutional Networks[C]//International Conference on Learning Representations. 2017.
[14] Xu Y, Zhou B, Jin S, et al. A framework for urban land use classification by integrating the spatial context of points of interest and graph convolutional neural network method[J]. Computers, Environment and Urban Systems, 2022, 95: 101807.
[15] Xu R, Chen Z, Li F, et al. Identification of urban functional zones based on POI density and marginalized graph autoencoder[J]. ISPRS International Journal of Geo-Information, 2023, 12(8): 343.
[16] Veličković P, Cucurull G, Casanova A, et al. Graph Attention Networks[C]//International Conference on Learning Representations. 2018.
[17] He L, Bai L, Yang X, et al. High-order graph attention network[J]. Information Sciences, 2023, 630: 222-234.
[18] Vaswani A, Shazeer N, Parmar N, et al. Attention Is All You Need[C]//Advances in Neural Information Processing Systems. 2017, 30: 5998-6008.
[19] Huang C, Zhou Y, Wu T, et al. A cellular automata model coupled with partitioning CNN-LSTM and PLUS models for urban land change simulation[J]. Journal of Environmental Management, 2024, 351: 119828.
[20] Zhao X, Wang P, Gao S, et al. Combining LSTM and PLUS models to predict future urban land use and land cover change: A case in Dongying City, China[J]. Remote Sensing, 2023, 15(9): 2370.
[21] Yu B, Yin H, Zhu Z. Spatio-Temporal Graph Convolutional Networks: A deep learning framework for traffic forecasting[C]//Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. 2018: 3634-3640.
[22] Guo S, Lin Y, Feng N, et al. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2019, 33(1): 922-929.
[23] Tan X, Chen W, Cao H, et al. Identifying spatiotemporal characteristics and driving factors of industrial land use morphology in China[J]. Expert Systems with Applications, 2024, 235: 121231.
[24] Lu W, Tao C, Ji Q, et al. Social information fused urban functional zones classification network[C]//ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2020, V-3-2020: 263-268.
[25] Tao Y, Liu W, Chen J, et al. A graph-based multimodal data fusion framework for identifying urban functional zone[J]. International Journal of Applied Earth Observation and Geoinformation, 2025, 136: 104353.
[26] Li C, Gao X, He B J, et al. Coupling coordination relationships between urban-industrial land use efficiency and accessibility of highway networks: Evidence from Beijing-Tianjin-Hebei urban agglomeration, China[J]. Sustainability, 2019, 11(5): 1446.
[27] Xie Y, Zhang Y, Gong M, et al. Mgat: Multi-view graph attention networks[J]. Neural Networks, 2020, 132: 180-189.
[28] Zhao A, Huang J, Gao F, et al. Regional allocation of industrial land in industrializing China: Does spatial mismatch exist?[J]. Landscape Research, 2023, 48(3): 396-411.
[29] Zhao X, Zhang L, Huang X, et al. Evolution of the spatiotemporal pattern of urban industrial land use efficiency in China[J]. Sustainability, 2018, 10(7): 2174.
[30] Oono K, Suzuki T. Graph Neural Networks Exponentially Lose Expressive Power for Node Classification[C]//International Conference on Learning Representations. 2020.
[31] He Q, Tang X. Identification and analysis of industrial land in China based on the point of interest data and random forest model[J]. Frontiers in Environmental Science, 2022, 10: 907383.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Yuxuan Hu, Yinan Lin
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
