Abstract
Graph Neural Networks (GNN) have gained recognition as a promising method for addressing graph-based problems and modeling complex relationships in data. A notable application of GNN is graph classification, where the goal is to assign a label to an entire graph by considering its structure and features. This paper introduces a novel method for GNN graph classification to detect abnormal climate change patterns. By constructing graphs from temperature time series data and labeling them based on average cosine similarities between consecutive years, we demonstrate the effectiveness of GNN graph classification in identifying abnormal climate patterns. Outliers in the classification results, such as stable patterns in some Mediterranean cities and unstable patterns in some cities in China and Mexico, underscore the importance of regional factors and highlight the capability of GNN graph classification models in detecting and understanding such variations. Studying these outliers enhances our understanding of climate characteristics, global patterns, and contributes valuable insights to global warming research.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (2012). https://proceedings.neurips.cc/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015). https://doi.org/10.1038/nature14539
Noy, N., Gao, Y., Jain, A., Narayanan, A., Patterson, A., Taylor, J.: Industry-scale knowledge graphs: lessons and challenges (2019). https://queue.acm.org/detail.cfm?id=3332266
Bronstein, M.M., Bruna, J., Cohen, T., Veličković, P.: Geometric deep learning: grids, groups, graphs, geodesics, and gauges (2021). https://arxiv.org/pdf/2104.13478.pdf
Temperature History of 1000 cities 1980 to 2020 (2020). https://www.kaggle.com/datasets/hansukyang/temperature-history-of-1000-cities-1980-to-2020
Bradley, A.: SEMANTICS 2017, Amsterdam (2017). https://2017.semantics.cc/aaron-bradley-eamonn-glass
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., Philip, S.Y.: A comprehensive survey on graph neural networks (2019). https://arxiv.org/pdf/1901.00596.pdf
Wang, M., Qiu, L., Wang, X.: A survey on knowledge graph embeddings for link prediction. In: Symmetry (2021). https://doi.org/10.3390/sym13030485
Adamczyk, J.: Application of graph neural networks and graph descriptors for graph classification (2022). https://arxiv.org/pdf/2211.03666.pdf
Hu, W., et al.: Strategies for pre-training graph neural networks. In: ICLR 2020 (2020). https://doi.org/10.48550/arXiv.1905.12265
He, H., Queen, O., Koker, T., Cuevas, C., Tsiligkaridis, T., Zitnik, M.: Domain adaptation for time series under feature and label shifts (2023). https://arxiv.org/pdf/2302.03133.pdf
GNN Graph Classification for Climate Change Patterns (2023). https://sparklingdataocean.com/2023/02/11/cityTempGNNgraphs/
Pytorch Geometric Library Graph Classification with Graph Neural Networks (2023). https://pytorchgeometric.io/
Romanova, A.: Symmetry metrics for pairwise entity similarities. In: Pardede, E., Delir Haghighi, P., Khalil, I., Kotsis, G. (eds.) Information Integration and Web Intelligence. iiWAS 2022. LNCS, vol. 13635, pp. 476–488. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-21047-1_44
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Romanova, A. (2023). GNN Graph Classification Method to Discover Climate Change Patterns. In: Iliadis, L., Papaleonidas, A., Angelov, P., Jayne, C. (eds) Artificial Neural Networks and Machine Learning – ICANN 2023. ICANN 2023. Lecture Notes in Computer Science, vol 14257. Springer, Cham. https://doi.org/10.1007/978-3-031-44216-2_32
Download citation
DOI: https://doi.org/10.1007/978-3-031-44216-2_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44215-5
Online ISBN: 978-3-031-44216-2
eBook Packages: Computer ScienceComputer Science (R0)