TOWARDS TRUSTWORTHY WILDFIRE DETECTION: INTEGRATING EXPLAINABILITY AND UNCERTAINTY IN DEEP LEARNING MODELS
Keywords:
trustworthy artificial intelligence; wildfire detection; Grad-CAM; uncertainty calibration; deep learning.Abstract
Wildfires are now a climate-driven, year-round hazard, raising the value of deep learning for early visual detection. This study presents BlazeVeritas AI, a wildfire detection framework integrating CNN, ResNet-18 [8], and DenseNet-121 [5] with Grad-CAM [7] explainability and uncertainty calibration via Monte Carlo Dropout [9] and Temperature Scaling, deployed through FastAPI and Streamlit. Results show that pairing explanation with calibrated uncertainty improves the reliability of wildfire decision-support systems.
References
Jain, P., Coogan, S. C. P., Subramanian, S. G., Crowley, M., Taylor, S., & Flannigan, M. D. (2020). A review of machine learning applications in wildfire science and management. Environmental Reviews, 28(4), 478–505.
Khan, S., Khan, A., Maqsood, M., Aadil, F., & Ghazanfar, M. A. (2022). Convolutional neural networks for fire and smoke detection: A comprehensive survey. Multimedia Tools and Applications, 81(24), 35143–35180.
Guo, C., Pleiss, G., Sun, Y., & Weinberger, K. Q. (2017). On calibration of modern neural networks. In Proceedings of the 34th International Conference on Machine Learning (ICML) (pp. 1321–1330).
Frizzi, S., Kaabi, R., Bouchouicha, M., Ginoux, J.-M., Moreau, E., & Fnaiech, F. (2016). Convolutional neural network for video fire and smoke detection. In Proceedings of the 42nd Annual Conference of the IEEE Industrial Electronics Society (IECON) (pp. 877–882).
Park, M., Tran, D. Q., Jung, D., & Park, S. (2020). Wildfire-detection method using DenseNet and CycleGAN data augmentation-based remote camera imagery. Remote Sensing, 12(22), Article 3715.
Gal, Y., & Ghahramani, Z. (2016). Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. In Proceedings of the 33rd International Conference on Machine Learning (ICML) (pp. 1050–1059).
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-CAM: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE International Conference on Computer Vision (ICCV) (pp. 618–626).
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 770–778).
Naeini, M. P., Cooper, G. F., & Hauskrecht, M. (2015). Obtaining well calibrated probabilities using Bayesian binning. In Proceedings of the 29th AAAI Conference on Artificial Intelligence (pp. 2901–2907).