Document Open Access Logo

An Evaluation of the Impact of Ignition Location Uncertainty on Forest Fire Ignition Prediction Using Bayesian Logistic Regression (Short Paper)

Authors David Röbl , Rizwan Bulbul , Johannes Scholz , Mortimer M. Müller , Harald Vacik



PDF
Thumbnail PDF

File

LIPIcs.GIScience.2023.62.pdf
  • Filesize: 1.49 MB
  • 7 pages

Document Identifiers

Author Details

David Röbl
  • Institute of Geodesy, Graz University of Technology, Graz, Austria
Rizwan Bulbul
  • Institute of Geodesy, Graz University of Technology, Graz, Austria
Johannes Scholz
  • Institute of Geodesy, Graz University of Technology, Graz, Austria
Mortimer M. Müller
  • Institute of Silviculture, University of Natural Resources and Life Sciences, Vienna, Austria
Harald Vacik
  • Institute of Silviculture, University of Natural Resources and Life Sciences, Vienna, Austria

Cite AsGet BibTex

David Röbl, Rizwan Bulbul, Johannes Scholz, Mortimer M. Müller, and Harald Vacik. An Evaluation of the Impact of Ignition Location Uncertainty on Forest Fire Ignition Prediction Using Bayesian Logistic Regression (Short Paper). In 12th International Conference on Geographic Information Science (GIScience 2023). Leibniz International Proceedings in Informatics (LIPIcs), Volume 277, pp. 62:1-62:7, Schloss Dagstuhl - Leibniz-Zentrum für Informatik (2023)
https://doi.org/10.4230/LIPIcs.GIScience.2023.62

Abstract

This study investigates the impact of location uncertainty on the predictive performance of Bayesian Logistic Regression (BLR) for forest fire ignition prediction in Austria. Historical forest fire ignitions are used to create a dataset for training models with the capability to assess the general forest fire ignition susceptibility. Each recorded fire ignition contains a timestamp, the estimated location of the ignition and a radius defining the area within which the unknown true location of the ignition point is located. As the values of the predictive features are calculated based on the assumed location, and not the unknown true location, the training data is biased due to input uncertainties. This study is set to assess the impact of input data uncertainty on the predictive performance of the model. For this we use a data binning approach that splits the input data into groups based on their location uncertainty and use them later for training multiple BLR models. The predictive performance of the models is then compared based on their accuracy, area under the receiver operating characteristic curve (AUC) scores and brier scores. The study revealed that higher location uncertainty leads to decreased accuracy and AUC score, accompanied by an increase in the brier score, while demonstrating that the BLR model trained on a smaller high-quality dataset outperforms the model trained on the full dataset, despite its smaller size. The study’s contribution is to provide insights into the practical implications of location uncertainty on the quality of forest fire susceptibility predictions, with potential implications for forest risk management and forest fire documentation.

Subject Classification

ACM Subject Classification
  • Theory of computation → Bayesian analysis
Keywords
  • Forest Fire Prediction
  • Ignition Location Uncertainty
  • Bayesian Logistic Regression
  • Bayesian Inference
  • Probabilistic Programming

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads

References

  1. Giuseppe Amatulli, Fernando Peréz-Cabello, and Juan de la Riva. Mapping lightning/human-caused wildfires occurrence under ignition point location uncertainty. Ecological modelling, 200(3-4):321-333, 2007. Google Scholar
  2. Natalie Arndt, Harald Vacik, Valerie Koch, Alexander Arpaci, and Hartnut Gossow. Modeling human-caused forest fire ignition for assessing forest fire danger in austria. iForest-Biogeosciences and Forestry, 6(6):315, 2013. Google Scholar
  3. Alexander Arpaci, Bodo Malowerschnig, Oliver Sass, and Harald Vacik. Using multi variate data mining techniques for estimating fire susceptibility of tyrolean forests. Applied Geography, 53:258-270, 2014. Google Scholar
  4. Umang Bhatt, Javier Antorán, Yunfeng Zhang, Q Vera Liao, Prasanna Sattigeri, Riccardo Fogliato, Gabrielle Melançon, Ranganath Krishnan, Jason Stanley, Omesh Tickoo, and others. Uncertainty as a form of transparency: Measuring, communicating, and using uncertainty. In Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society, pages 401-413, 2021. Google Scholar
  5. Ross A Bradstock, JS Cohn, A Malcolm Gill, Michael Bedward, and C Lucas. Prediction of the probability of large fires in the sydney region of south-eastern australia using fire weather. International Journal of Wildland Fire, 18(8):932-943, 2009. Google Scholar
  6. Glenn W Brier and others. Verification of forecasts expressed in terms of probability. Monthly weather review, 78(1):1-3, 1950. Google Scholar
  7. Filipe X Catry, Francisco C Rego, Fernando L Bação, and Francisco Moreira. Modeling and mapping wildfire ignition risk in Portugal. International Journal of Wildland Fire, 18(8):921-931, 2009. Google Scholar
  8. Georgios Charizanos and Haydar Demirhan. Bayesian prediction of wildfire event probability using normalized difference vegetation index data from an Australian forest. Ecological Informatics, 73:101899, 2023. Google Scholar
  9. Andrew Gelman, John B Carlin, Hal S Stern, David B Dunson, Aki Vehtari, and Donald B Rubin. Bayesian Data Analysis. Chapman and Hall/CRC, 3rd edition, 2013. URL: https://doi.org/10.1201/b16018.
  10. Piyush Jain, Sean C P Coogan, Sriram Ganapathi Subramanian, Mark Crowley, Steve Taylor, and Mike D Flannigan. A review of machine learning applications in wildfire science and management. Environmental Reviews, 28(4):478-505, 2020. Google Scholar
  11. Meelis Kull and Peter A Flach. Reliability maps: a tool to enhance probability estimates and improve classification accuracy. In Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2014, Nancy, France, September 15-19, 2014. Proceedings, Part II 14, pages 18-33. Springer, 2014. Google Scholar
  12. J. San-Miguel-Ayanz, T. Durrant, R. Boca, P. Maianti, G. Libertá, T. Artés-Vivancos, D. Oom, A. Branco, D. de Rigo, D. Ferrari, H. Pfeiffer, R. Grecchi, M. Onida, and P. Löffler. Forest Fires in Europe, Middle East and North Africa 2021. Technical report, Publications Office of the European Union, Luxembourg, 2022. URL: https://doi.org/10.2760/34094.
  13. Harald Vacik, Natalie Arndt, Alexander Arpaci, Valerie Koch, Mortimer Mueller, and Hartmut Gossow. Characterisation of forest fires in Austria. Austrian Journal of Forest Science, 128(1):1-31, 2011. Google Scholar
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail