FireDetXplainer: Decoding Wildfire Detection With Transparency and Explainable AI Insights
Recent analyses by leading national wildfire and emergency monitoring agencies have highlighted an alarming trend: the impact of wildfire devastation has escalated to nearly three times that of a decade ago. To address this challenge, we propose FireDetXplainer (FDX), a robust deep-learning model th...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10486908/ |
| _version_ | 1827281455098626048 |
|---|---|
| author | Syeda Fiza Rubab Arslan Abdul Ghaffar Gyu Sang Choi |
| author_facet | Syeda Fiza Rubab Arslan Abdul Ghaffar Gyu Sang Choi |
| author_sort | Syeda Fiza Rubab |
| collection | DOAJ |
| description | Recent analyses by leading national wildfire and emergency monitoring agencies have highlighted an alarming trend: the impact of wildfire devastation has escalated to nearly three times that of a decade ago. To address this challenge, we propose FireDetXplainer (FDX), a robust deep-learning model that enhances the interpretability often lacking in current solutions. FDX employs an innovative approach, combining transfer learning and fine-tuning methodologies with the Learning without Forgetting (LwF) framework. A key aspect of our methodology is the utilization of the pre-trained MobileNetV3 model, renowned for its efficiency in image classification tasks. Through strategic adaptation and augmentation, we have achieved an exceptional classification accuracy of 99.91%. The model is further refined with convolutional blocks and advanced image pre-processing techniques, contributing to this high level of precision. Leveraging diverse datasets from Kaggle and Mendeley, FireDetXplainer incorporates Explainable AI (XAI) tools such as Gradient Weighted Class Activation Map (Grad-CAM) and Local Interpretable Model-Agnostic Explanations (LIME) for comprehensive result interpretation. Our extensive experimental results demonstrate that FireDetXplainer not only outperforms existing state-of-the-art models but does so with remarkable accuracy, making it a highly effective solution for interpretable image classification in wildfire management. |
| first_indexed | 2024-04-24T09:01:35Z |
| format | Article |
| id | doaj.art-2a972c28b15a47019d55a73aa87f15df |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-24T09:01:35Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-2a972c28b15a47019d55a73aa87f15df2024-04-15T23:00:31ZengIEEEIEEE Access2169-35362024-01-0112523785238910.1109/ACCESS.2024.338365310486908FireDetXplainer: Decoding Wildfire Detection With Transparency and Explainable AI InsightsSyeda Fiza Rubab0https://orcid.org/0009-0001-3632-7932Arslan Abdul Ghaffar1https://orcid.org/0009-0004-4744-8221Gyu Sang Choi2https://orcid.org/0000-0002-0854-768XDepartment of Information and Communication Engineering, Yeungnam University, Gyeongsan, Republic of KoreaDepartment of Information and Communication Engineering, Yeungnam University, Gyeongsan, Republic of KoreaDepartment of Information and Communication Engineering, Yeungnam University, Gyeongsan, Republic of KoreaRecent analyses by leading national wildfire and emergency monitoring agencies have highlighted an alarming trend: the impact of wildfire devastation has escalated to nearly three times that of a decade ago. To address this challenge, we propose FireDetXplainer (FDX), a robust deep-learning model that enhances the interpretability often lacking in current solutions. FDX employs an innovative approach, combining transfer learning and fine-tuning methodologies with the Learning without Forgetting (LwF) framework. A key aspect of our methodology is the utilization of the pre-trained MobileNetV3 model, renowned for its efficiency in image classification tasks. Through strategic adaptation and augmentation, we have achieved an exceptional classification accuracy of 99.91%. The model is further refined with convolutional blocks and advanced image pre-processing techniques, contributing to this high level of precision. Leveraging diverse datasets from Kaggle and Mendeley, FireDetXplainer incorporates Explainable AI (XAI) tools such as Gradient Weighted Class Activation Map (Grad-CAM) and Local Interpretable Model-Agnostic Explanations (LIME) for comprehensive result interpretation. Our extensive experimental results demonstrate that FireDetXplainer not only outperforms existing state-of-the-art models but does so with remarkable accuracy, making it a highly effective solution for interpretable image classification in wildfire management.https://ieeexplore.ieee.org/document/10486908/Deep learningexplainable AI (XAI)transfer learningwildfire detection |
| spellingShingle | Syeda Fiza Rubab Arslan Abdul Ghaffar Gyu Sang Choi FireDetXplainer: Decoding Wildfire Detection With Transparency and Explainable AI Insights IEEE Access Deep learning explainable AI (XAI) transfer learning wildfire detection |
| title | FireDetXplainer: Decoding Wildfire Detection With Transparency and Explainable AI Insights |
| title_full | FireDetXplainer: Decoding Wildfire Detection With Transparency and Explainable AI Insights |
| title_fullStr | FireDetXplainer: Decoding Wildfire Detection With Transparency and Explainable AI Insights |
| title_full_unstemmed | FireDetXplainer: Decoding Wildfire Detection With Transparency and Explainable AI Insights |
| title_short | FireDetXplainer: Decoding Wildfire Detection With Transparency and Explainable AI Insights |
| title_sort | firedetxplainer decoding wildfire detection with transparency and explainable ai insights |
| topic | Deep learning explainable AI (XAI) transfer learning wildfire detection |
| url | https://ieeexplore.ieee.org/document/10486908/ |
| work_keys_str_mv | AT syedafizarubab firedetxplainerdecodingwildfiredetectionwithtransparencyandexplainableaiinsights AT arslanabdulghaffar firedetxplainerdecodingwildfiredetectionwithtransparencyandexplainableaiinsights AT gyusangchoi firedetxplainerdecodingwildfiredetectionwithtransparencyandexplainableaiinsights |