Smart Structures and Systems

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

A study on the characteristics of applying oversampling algorithms to Fosberg Fire-Weather Index (FFWI) data

  • Sang Yeob Kim (Department of Fire and Disaster Prevention, Konkuk University) ;
  • Dongsoo Lee (School of Civil, Environmental and Architectural Engineering, Korea University) ;
  • Jung-Doung Yu (Department of Civil Engineering, Joongbu University) ;
  • Hyung-Koo Yoon (Department of Construction and Disaster Prevention Engineering, Daejeon University)
  • Received : 2024.05.07
  • Accepted : 2024.08.20
  • Published : 2024.07.25
⟨ Previous Next ⟩

Abstract

Oversampling algorithms are methods employed in the field of machine learning to address the constraints associated with data quantity. This study aimed to explore the variations in reliability as data volume is progressively increased through the use of oversampling algorithms. For this purpose, the synthetic minority oversampling technique (SMOTE) and the borderline synthetic minority oversampling technique (BSMOTE) are chosen. The data inputs, which included air temperature, humidity, and wind speed, are parameters used in the Fosberg Fire-Weather Index (FFWI). Starting with a base of 52 entries, new data sets are generated by incrementally increasing the data volume by 10% up to a total increase of 100%. This augmented data is then utilized to predict FFWI using a deep neural network. The coefficient of determination (R2) is calculated for predictions made with both the original and the augmented datasets. Suggesting that increasing data volume by more than 50% of the original dataset quantity yields more reliable outcomes. This study introduces a methodology to alleviate the challenge of establishing a standard for data augmentation when employing oversampling algorithms, as well as a means to assess reliability.

Keywords

Acknowledgement

This research was supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (NRF-2020R1A2C2012113).

References

  1. Abdi, Y. (2024), "Investigation of the strength behavior and failure modes of layered sedimentary rocks under Brazilian test conditions", Int. J. Geo-Eng., 15(1), 6. https://doi.org/10.1186/s40703-024-00208-2
  2. Al-Swaidani, A.M., Meziab, A., Khwies, W.T., Al-Bali, M. and Lala, T. (2024), "Building MLR, ANN and FL models to predict the strength of problematic clayey soil stabilized with a combination of nano lime and nano pozzolan of natural sources for pavement construction", Int. J. Geo-Eng., 15(1), 2. https://doi.org/10.1186/s40703-023-00201-1
  3. Bang, H., Yu, B. and Jeon, H. (2023), "Assembly performance evaluation method for prefabricated steel structures using deep learning and k-nearest neighbors", Smart Struct. Syst., Int. J., 32(2), 111-121. https://doi.org/10.12989/sss.2023.32.2.111
  4. Burke, M., Driscoll, A., Heft-Neal, S., Xue, J., Burney, J. and Wara, M. (2021), "The changing risk and burden of wildfire in the United States", Proceedings of the National Academy of Sciences, 118(2), e2011048118. https://doi.org/10.1073/pnas.2011048118
  5. Chawla, N.V., Bowyer, K.W., Hall, L.O. and Kegelmeyer, W.P. (2002), "SMOTE: synthetic minority over-sampling technique", J. Artif. Intell. Res., 16, 321-357. https://doi.org/10.1613/jair.953
  6. Deeming, J.E. (1972), National fire-danger rating system; Rocky Mountain Forest and Range Experiment Station, Forest Service, USA.
  7. Fosberg, M.A. (1981), Weather in wildland fire management: the fire weather index.
  8. Gill, A.M., Stephens, S.L. and Cary, G.J. (2013), "The worldwide "wildfire" problem", Ecolog. Applicat., 23(2), 438-454. https://doi.org/10.1890/10-2213.1
  9. GM, B. (1959), "Combustion of forest fuels", In: Forest fire: control and use, pp. 61-89.
  10. Han, H., Wang, W.-Y. and Mao, B.-H. (2005), "BorderlineSMOTE: a new over-sampling method in imbalanced data sets learning", In: International Conference on Intelligent Computing. https://doi.org/10.1007/11538059_91
  11. Kim, S. and Yoon, H.-K. (2023), "Application of classification coupled with PCA and SMOTE, for obtaining safety factor of landslide based on HRA", Bull. Eng. Geol. Environ., 82(10), 381. https://doi.org/10.1007/s10064-023-03403-0
  12. Lee, J.S., Park, J., Kim, J. and Yoon, H.K. (2022), "Study of oversampling algorithms for soil classifications by field velocity resistivity probe", Geomech. Eng., Int. J., 30(3), 247-258. https://doi.org/10.12989/gae.2022.30.3.247
  13. Li, W., Zhao, W., Yang, M., Hong, N. and Du, Y. (2023a), "Dynamic characteristics monitoring of wind turbine blades based on improved YOLOv5 deep learning model", Smart Struct. Syst., Int. J., 31(5), 469-483. https://doi.org/10.12989/sss.2023.31.5.469
  14. Li, Y.-F., He, W.-Y., Ren, W.-X., Liu, G. and Sun, H.-P. (2023b), "Dynamic deflection monitoring method for long-span cable-stayed bridge based on bi-directional long short-term memory neural network", Smart Struct. Syst., Int. J., 32(5), 297-308. https://doi.org/10.12989/sss.2023.32.5.297
  15. Min, D.-H., Kim, Y., Kim, S. and Yoon, H.-K. (2023), "Strategy of oversampling geotechnical parameters through geostatistical, SMOTE, and CTGAN methods for assessing susceptibility of landslide", Landslides, 1-17. https://doi.org/10.1007/s10346-023-02166-9
  16. Park, J., Lee, J.S. and Yoon, H.K. (2023), "Geoacoustic and geophysical data-driven seafloor sediment classification through machine learning algorithms with property-centered oversampling techniques", Comput.-Aided Civil Infrastruct. Eng., 39(14), 2105-2121. https://doi.org/10.1111/mice.13126
  17. Peng, X., Zhou, K., Duan, B., Zhong, X., Zhao, C. and Zhang, T. (2023), "A fast and simplified crack width quantification method via deep Q learning", Smart Struct. Syst., Int. J., 32(4), 219-233. https://doi.org/10.12989/sss.2023.32.4.219
  18. Rothermel, R.C. (1972), A mathematical model for predicting fire spread in wildland fuels; Intermountain Forest & Range Experiment Station, Forest Service, USA.
  19. Samadi, H., Hassanpour, J. and Rostami, J. (2023), "Prediction of earth pressure balance for EPB-TBM using machine learning algorithms", Int. J. Geo-Eng., 14(1), 21. https://doi.org/10.1186/s40703-023-00198-7
  20. Simard, A.J. (1968), The moisture content of forest fuels; University of California Oakland, CA, USA.
  21. Suh, H.S. (2024), "Evolution of anisotropic capillarity in unsaturated granular media within the pendular regime", Int. J. Geo-Eng., 15(1), 10. https://doi.org/10.1186/s40703-024-00211-7
  22. Tymstra, C., Stocks, B.J., Cai, X. and Flannigan, M.D. (2020), "Wildfire management in Canada: Review, challenges and opportunities", Progress Disaster Sci., 5, 100045. https://doi.org/10.1016/j.pdisas.2019.100045
  23. Zhu, H., Li, Z., Huang, M., Ji, P., Huang, H. and Zhang, Q. (2023), "Automatic assessment of post-earthquake buildings based on multi-task deep learning with auxiliary tasks", Smart Struct. Syst., Int. J., 31(4), 383-392. https://doi.org/10.12989/sss.2023.31.4.383