Cited by Enhancing active fire detection in Sentinel 2 imagery using GLCM texture features in random forest models

An advanced multi-source data fusion method utilizing deep learning techniques for fire detection DOI

Shikuan Wang, Mengquan Wu, Xinghua Wei

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2024, Volume and Issue: 142, P. 109902 - 109902

Published: Dec. 22, 2024

Language: Английский

Citations

Deep Learning-Based Multistage Fire Detection System and Emerging Direction DOI

Tofayet Sultan, Mohammad Sayem Chowdhury, Mejdl Safran

et al.

Fire, Journal Year: 2024, Volume and Issue: 7(12), P. 451 - 451

Published: Nov. 30, 2024

Fires constitute a significant risk to public safety and property, making early accurate detection essential for an effective response damage mitigation. Traditional fire methods have limitations in terms of accuracy adaptability, particularly complex environments which various stages (such as smoke active flames) need be distinguished. This study addresses the critical comprehensive system capable multistage classification, differentiating between non-fire, smoke, apartment fires, forest fires. We propose deep learning-based model using customized DenseNet201 architecture that integrates preprocessing steps explainable AI techniques, such Grad-CAM++ SmoothGrad, enhance transparency interpretability. Our was trained tested on diverse, multisource dataset, achieving 97%, along with high precision recall. The comparative results demonstrate superiority proposed over other baseline models handling detection. research provides advancement toward more reliable, interpretable, systems adapting different types, opening new possibilities environmentally friendly type detection, ultimately enhancing enabling faster, targeted emergency responses.

Language: Английский

Citations

Evaluation of Three Algorithms and Forest Fire Risk Prediction in Zhejiang Province of China DOI

Richard Bian,

Keji Chen,

Guoqiang Li

et al.

Forests, Journal Year: 2024, Volume and Issue: 15(12), P. 2146 - 2146

Published: Dec. 5, 2024

Forest fires represent a paramount natural disaster of global concern. Zhejiang Province has the highest forest coverage rate in China, and are one main disasters impacting management region. In this study, we comprehensively analyzed spatiotemporal distribution based on MODIS data from 2013 to 2023. The results showed that annual incidence shown an overall downward trend 2023, with occurring more frequently winter spring. By utilizing eight contributing factors fire occurrence as variables, three models were constructed: Logistic Regression (LR), Random (RF), eXtreme Gradient Boosting (XGBoost). RF XGBoost demonstrated high predictive ability, achieving accuracy rates 0.85 0.92, f1-score 0.84 AUC values 0.892 0.919, respectively. Further analysis using revealed elevation precipitation had most significant effects fires. Additionally, predictions risk generated by indicated is southern part Province, particularly Wenzhou Lishui areas, well southwest Hangzhou area north Quzhou area. future, can be predicted site models, providing scientific reference for aiding prevention mitigation impacts

Language: Английский

Citations

A Review of Methods and Sensors for Detecting Forest Fire DOI

S.P. Gupta, Vikash Kumar Mishra,

Vipin Rai

et al.

Published: Nov. 23, 2024

Language: Английский

Citations

Enhancing active fire detection in Sentinel 2 imagery using GLCM texture features in random forest models DOI

Bao Zhou,

Sha Gao, Ying Yin

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Dec. 28, 2024

Language: Английский

Citations