Abstract
The frequency of wildfires increases yearly and poses a constant threat to the environment and human beings. Different factors, for example surrounding infrastructure to an area (e.g., campfire sites or power lines) contribute to the occurrence of wildfires. In this paper, we propose using a Spatio-Temporal Knowledge Graph (STKG) based on OpenStreetMap (OSM) data for modeling such infrastructure. Based on that knowledge graph, we use the RDF2vec approach to create embeddings for predicting wildfires, and we align different vector spaces generated at each temporal step by partial rotation. In an experimental study, we determine the effect of the surrounding infrastructure by comparing different data composition strategies, which involve a prediction based on tabular data, a combination of tabular data and embeddings, and solely embeddings. We show that the incorporation of the STKG increases the prediction quality of wildfires.
About the authors
Martin Böckling studied Business Informatic at the University of Mannheim. He is currently a PhD student at the chair of Prof. Dr. Heiko Paulheim, where he focuses his research on Spatio-Temporal Knowledge Graphs and its usage in prediction tasks. During his master studies, he was involved in several research projects exploring the usage of knowledge graphs in different research domains. For his Bachelor and Master studies, he was participated in a study program within SAP.
Prof. Dr. Heiko Paulheim is a full professor for data science at the University of Mannheim. He holds a PhD from the Technical University of Darmstadt and has conducted research at the University of Applied Sciences of Darmstadt, SAP Research, and the Technical University of Darmstadt prior to this position. His group conducts various projects around knowledge graphs, yielding, among others, the public knowledge graphs WebIsALOD, CaLiGraph, and DBkWik. Moreover, his group is concerned with using knowledge graphs in machine learning, which has lead to the development of the widespread RDF2vec method for knowledge graph embeddings. In the recent past, Heiko Paulheim also leads projects which are concerned with ethical, societal, and legal aspects of AI, such as price-setting AIs on antitrust legislation, ethical news recommenders, and the analysis of hate speech in social media.
Dr. Sarah Detzler is the Competence Lead for Data Science and Machine Learning at SAP. She holds a PhD from KIT and was part of the research group for efficient algorithms focusing on evolutionary algorithms. In her PhD research she focused on the algorithmic optimization of charging networks for electric cars using factos as the price together with fixed boundary conditions. Besides her PhD degree, she holds a Bachelor and Master degree in both mathematics and physics.
Acknowledgments
Map data copyrighted OpenStreetMap contributors and available from https://www.openstreetmap.org.
-
Research ethics: Not applicable.
-
Informed consent: Not applicable.
-
Author contributions: The authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Competing interests: The authors state no conflict of interest.
-
Research funding: None declared.
-
Data availability: The raw data can be obtained on request from the corresponding author.
References
[1] K. Hoover and L. A. Hanson, “Wildfire statistics,” Congr. Res. Serv., vol. 2, pp. 1–3, 2021.Search in Google Scholar
[2] E. Pastor, L. Zárate, E. Planas, and J. Arnaldos, “Mathematical models and calculation systems for the study of wildland fire behaviour,” Prog. Energy Combust. Sci., vol. 29, no. 2, pp. 139–153, 2003. https://doi.org/10.1016/s0360-1285(03)00017-0.Search in Google Scholar
[3] W. R. Tobler, “A computer movie simulating urban growth in the detroit region,” Econ. Geogr., vol. 46, pp. 234–240, 1970. https://doi.org/10.2307/143141.Search in Google Scholar
[4] M. H. Nami, A. Jaafari, M. Fallah, and S. Nabiuni, “Spatial prediction of wildfire probability in the hyrcanian ecoregion using evidential belief function model and gis,” Int. J. Environ. Sci. Technol., vol. 15, no. 2, pp. 373–384, 2018. https://doi.org/10.1007/s13762-017-1371-6.Search in Google Scholar
[5] S. J. Kim, C.-H. Lim, G. S. Kim, et al.., “Multi-temporal analysis of forest fire probability using socio-economic and environmental variables,” Rem. Sens., vol. 11, no. 1, pp. 86–105, 2019. https://doi.org/10.3390/rs11010086.Search in Google Scholar
[6] K. Janowicz, P. Hitzler, W. Li, et al.., “Know, know where, knowwheregraph: a densely connected, cross-domain knowledge graph and geo-enrichment service stack for applications in environmental intelligence,” AI Mag., vol. 43, no. 1, pp. 30–39, 2022. https://doi.org/10.1002/aaai.12043.Search in Google Scholar
[7] J. Michael Johnson, T. Narock, J. Singh-Mohudpur, et al.., “Knowledge graphs to support real–time flood impact evaluation,” AI Mag., vol. 43, no. 1, pp. 40–45, 2022. https://doi.org/10.1002/aaai.12035.Search in Google Scholar
[8] J. Wu, F. Orlandi, D. O’Sullivan, and S. Dev, “Linkclimate: an interoperable knowledge graph platform for climate data,” Comput. Geosci., vol. 169, p. 2022, 2022. https://doi.org/10.1016/j.cageo.2022.105215.Search in Google Scholar
[9] B. Shbita, C. A. Knoblock, W. Duan, Y.-Y. Chiang, J. H. Uhl, and S. Leyk, “Building spatio-temporal knowledge graphs from vectorized topographic historical maps,” Semantic Web, vol. 14, no. 3, pp. 527–549, 2023. https://doi.org/10.3233/sw-222918.Search in Google Scholar
[10] A. Anjomshoaa, H. Schuster, J. Wachs, and A. Polleres, “From data to insights: constructing spatiotemporal knowledge graphs for city resilience use cases,” in Second International Workshop On Linked Data-driven Resilience Research 2023, 2023.Search in Google Scholar
[11] J. Gastinger, N. Steinert, S. Gründer-Fahrer, and M. Martin, “Dynamic representations of global crises: creation and analysis of a temporal knowledge graph for conflicts, trade and value networks,” in Second International Workshop On Linked Data-driven Resilience Research 2023, 2023.Search in Google Scholar
[12] L. Giglio, C. Justice, L. Boschetti, and D. Roy, “Mcd64a1 modis/terra+aqua burned area monthly l3 global 500m sin grid v006,” 2015. https://doi.org/10.5067/MODIS/MCD64A1.006.Search in Google Scholar
[13] M. J. Menne, I. Durre, R. S. Vose, B. E. Gleason, and T. G. Houston, “An overview of the global historical climatology network-daily database,” J. Atmos. Ocean. Technol., vol. 29, no. 7, pp. 897–910, 2012. https://doi.org/10.1175/jtech-d-11-00103.1.Search in Google Scholar
[14] L. Yang, S. Jin, P. Danielson, et al.., “A new generation of the United States national land cover database: requirements, research priorities, design, and implementation strategies,” ISPRS J. Photogrammetry Remote Sens., vol. 146, pp. 108–123, 2018. https://doi.org/10.1016/j.isprsjprs.2018.09.006.Search in Google Scholar
[15] OpenStreetMap Contributors, Planet Dump, 2017.Search in Google Scholar
[16] M. Padgham, R. Lovelace, M. Salmon, and R. Bob, “osmdata,” J. Open Source Softw., vol. 2, p. 305, 2017, https://doi.org/10.21105/joss.00305.Search in Google Scholar
[17] K. Short, Spatial Wildfire Occurrence Data for the United States, 1992–2015 [FPA FOD 20170508], Fort Collins, Forest Service Research Data Archive, 2017.Search in Google Scholar
[18] P. Rigaux, M. Scholl, and A. Voisard, Spatial Databases, 1st ed. Boston, MA, Morgan Kaufmann and Safari, 2001.10.1016/B978-155860588-6/50003-8Search in Google Scholar
[19] Lu Wang and T. Ai, “The comparison of drainage network extraction between square and hexagonal grid-based dem,” Int. Arch. Photogram. Rem. Sens. Spatial Inf. Sci., vol. XLII-4, pp. 687–692, 2018. https://doi.org/10.5194/isprs-archives-xlii-4-687-2018.Search in Google Scholar
[20] P. D. Colin, S. P. O. Birch, and J. A. Beecham, “Rectangular and hexagonal grids used for observation, experiment and simulation in ecology,” Ecol. Model., vol. 206, nos. 3–4, pp. 347–359, 2007. https://doi.org/10.1016/j.ecolmodel.2007.03.041.Search in Google Scholar
[21] T. Pede and G. Mountrakis, “An empirical comparison of interpolation methods for modis 8-day land surface temperature composites across the conterminous unites states,” ISPRS J. Photogrammetry Remote Sens., vol. 142, pp. 137–150, 2018. https://doi.org/10.1016/j.isprsjprs.2018.06.003.Search in Google Scholar
[22] G. Matheron, “Principles of geostatistics,” Econ. Geol., vol. 58, no. 8, pp. 1246–1266, 1963. https://doi.org/10.2113/gsecongeo.58.8.1246.Search in Google Scholar
[23] E. Clementini, P. Di Felice, and P. van Oosterom, “A small set of formal topological relationships suitable for end-user interaction,” in Advances in Spatial Databases, Volume 692 of Lecture Notes in Computer Science, G. Goos, J. Hartmanis, D. Abel, and B. C. Ooi, Eds., Berlin, Heidelberg, Springer, 1993, pp. 277–295.10.1007/3-540-56869-7_16Search in Google Scholar
[24] P. Ristoski and H. Paulheim, “Rdf2vec: rdf graph embeddings for data mining,” in The Semantic Web – ISWC 2016, Volume 9981 of Lecture Notes in Computer Science, P. Groth, E. Simperl, A. Gray, et al.., Eds., Cham, Springer International Publishing, 2016, pp. 498–514.10.1007/978-3-319-46523-4_30Search in Google Scholar
[25] W. L. Hamilton, J. Leskovec, and D. Jurafsky, “Diachronic word embeddings reveal statistical laws of semantic change,” in Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), K. Erk and N. A. Smith, Eds., Stroudsburg, PA, USA, Association for Computational Linguistics, 2016, pp. 1489–1501.10.18653/v1/P16-1141Search in Google Scholar
[26] T. Chen and C. Guestrin, “Xgboost: a scalable tree boosting system,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, B. Krishnapuram, M. Shah, A. Smola, C. Aggarwal, D. Shen, and R. Rastogi, Eds., New York, NY, USA, ACM, 2016, pp. 785–794.10.1145/2939672.2939785Search in Google Scholar
[27] F. Nogueira. “Bayesian optimization: open source constrained global optimization tool for python,” 2014. https://github.com/fmfn/BayesianOptimization.Search in Google Scholar
[28] J. Snoek, H. Larochelle, and R. P. Adams, “Practical Bayesian optimization of machine learning algorithms,” in Advances in Neural Information Processing Systems 25, Volume 25 of Advances in Neural Information Processing Systems, P. Bartlett, F. C. N. Pereira, C. J. C. Burges, L. Bottou, and K. Q. Weinberger, Eds., Red Hook, NY, Curran Associates, Inc, 2012, pp. 1–9.Search in Google Scholar
[29] O. Z. Maimon and L. Rokach, Data Mining and Knowledge Discovery Handbook, 2nd ed. New York, London, Springer, 2010.10.1007/978-0-387-09823-4Search in Google Scholar
[30] J. S. Littell, “Drought and fire in the western USA: is climate attribution enough?” Curr. Clim. Change Rep., vol. 4, no. 4, pp. 396–406, 2018. https://doi.org/10.1007/s40641-018-0109-y.Search in Google Scholar
[31] State Climate Extremes Committee, Records, 2022.Search in Google Scholar
[32] A. Dsouza, N. Tempelmeier, R. Yu, S. Gottschalk, and D. Elena, “Worldkg: a world-scale geographic knowledge graph,” in Proceedings of the 30th ACM International Conference on Information & Knowledge Management, G. Demartini, G. Zuccon, J. Shane Culpepper, Z. Huang, and H. Tong, Eds., New York, NY, USA, ACM, 2021, pp. 4475–4484.10.1145/3459637.3482023Search in Google Scholar
[33] A. Basiri, M. Jackson, P. Amirian, et al.., “Quality assessment of OpenStreetMap data using trajectory mining,” Geo Spat. Inf. Sci., vol. 19, no. 1, pp. 56–68, 2016, https://doi.org/10.1080/10095020.2016.1151213.Search in Google Scholar
[34] Q. Wang, Z. Mao, B. Wang, and Li Guo, “Knowledge graph embedding: a survey of approaches and applications,” IEEE Trans. Knowl. Data Eng., vol. 29, no. 12, pp. 2724–2743, 2017. https://doi.org/10.1109/tkde.2017.2754499.Search in Google Scholar
[35] F. Krause, “Dynamic knowledge graph embeddings via local embedding reconstructions,” in The Semantic Web: ESWC 2022 Satellite Events, Volume 13384 of Lecture Notes in Computer Science, P. Groth, A. Rula, J. Schneider, et al.., Eds., Cham, Springer International Publishing, 2022, pp. 215–223.10.1007/978-3-031-11609-4_36Search in Google Scholar
[36] M. Nayyeri, S. Vahdati, M. T. Khan, et al.., “Dihedron algebraic embeddings for spatio-temporal knowledge graph completion,” in The Semantic Web: 19th International Conference, ESWC 2022, Hersonissos, Crete, Greece, May 29–June 2, 2022, Proceedings, Springer, 2022, pp. 253–269.10.1007/978-3-031-06981-9_15Search in Google Scholar
© 2023 Walter de Gruyter GmbH, Berlin/Boston
