Wildfire detection through deep learning based on Himawari-8 satellites platform

Ding, Changcheng; Zhang, Xiaoyu; Chen, Jianyu; Ma, Shuchang; Lu, Yujun; Han, Weili

doi:10.1080/01431161.2022.2119110

Cited by 13 publications

(8 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From this, they achieved an accuracy of greater than 80%, which exceeds more established algorithms like support vector machines and k-means clustering. 17 Al-Dabbagh and Ilyas (2023) tested multiple deep learning models for semantic segmentation on a manuallycreated dataset from Sentinel-2 imagery, and found that the U-Net with a ResNet50 encoder performed the best, with an precision of 98.91%. 18 Recently, a new architecture was proposed by Tang et al (2020) for semantic segmentation called ResWnet.…”

Section: Semantic Segmentation Architecturesmentioning

confidence: 99%

Using ResWnet for semantic segmentation of active wildfires from Landsat-8 imagery

Afsar,

Sultana,

Abouzahra

et al. 2024

Pattern Recognition and Tracking XXXV

View full text Add to dashboard Cite

Wildfires are a key aspect of many ecosystems, but climate change has created conditions more conducive for devastating wildfires. Thus, it is imperative that relevant agencies know where small fires occur expeditiously. Remote sensing is a key tool for active fire detection (AFD), and satellite imagery in particular is useful due to covering wide areas. Semantic segmentation architectures like U-Net have been used for AFD and have proven very effective. In this paper, we apply a unique variant of U-Net called ResWnet towards AFD, using a large global dataset. ResWnet achieved a precision of 95% and an F-Score of 94.2%, which is better than a U-Net trained on the same dataset.

show abstract

Section: Semantic Segmentation Architecturesmentioning

confidence: 99%

Using ResWnet for semantic segmentation of active wildfires from Landsat-8 imagery

Afsar,

Sultana,

Abouzahra

et al. 2024

Pattern Recognition and Tracking XXXV

View full text Add to dashboard Cite

show abstract

“…Zou et al proposed an attentionbased convolutional neural network that can learn the complex behaviors of wildfires across different fire-prone regions [43]. Ding et al proposed a fully connected convolutional neural network for identifying the location and intensity of wildfires, which greatly exceeds that of other machine learning algorithms, such as support vector machine and k-means clustering [44]. Although these methods have effectively improved the prediction accuracy of forest fire spread, they mainly utilize 2DCNN to process the spatial features of forest fire spread, neglecting temporal dynamics.…”

Section: Introductionmentioning

confidence: 99%

AutoST-Net: A Spatiotemporal Feature-Driven Approach for Accurate Forest Fire Spread Prediction from Remote Sensing Data

Chen,

Tian,

Zheng

et al. 2024

Forests

View full text Add to dashboard Cite

Forest fires, as severe natural disasters, pose significant threats to ecosystems and human societies, and their spread is characterized by constant evolution over time and space. This complexity presents an immense challenge in predicting the course of forest fire spread. Traditional methods of forest fire spread prediction are constrained by their ability to process multidimensional fire-related data, particularly in the integration of spatiotemporal information. To address these limitations and enhance the accuracy of forest fire spread prediction, we proposed the AutoST-Net model. This innovative encoder–decoder architecture combines a three-dimensional Convolutional Neural Network (3DCNN) with a transformer to effectively capture the dynamic local and global spatiotemporal features of forest fire spread. The model also features a specially designed attention mechanism that works to increase predictive precision. Additionally, to effectively guide the firefighting work in the southwestern forest regions of China, we constructed a forest fire spread dataset, including forest fire status, weather conditions, terrain features, and vegetation status based on Google Earth Engine (GEE) and Himawari-8 satellite. On this dataset, compared to the CNN-LSTM combined model, AutoST-Net exhibits performance improvements of 5.06% in MIou and 6.29% in F1-score. These results demonstrate the superior performance of AutoST-Net in the task of forest fire spread prediction from remote sensing images.

show abstract

“…To the best of our knowledge, there exist only two related studies in the related literature. Ding et al [47] proposed a fully connected CNN model based on the Himawari-8 satellite platform, with its wildfire detection accuracy of > 80% that was significantly higher than that of the other traditional machine learning algorithms, such as support vector machine, random forest and clustering of k-means. However, the testing data in their study mostly included images of large-area fires, although most small fires occupy only a few pixels; thus, their model performance remains to be validated against small fire events.…”

Section: Introductionmentioning

confidence: 99%

Near Real-Time Monitoring of Fire Spots Using a Novel SBT-FireNet Based on Himawari-8 Satellite Images

Hong,

Tang,

Pan

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Detailed and timely monitoring of the location and intensity of the fire is critical to reducing the destructive impacts of a fire. Satellite imagery platforms, in particular geostationary satellites with high temporal resolution, allow for real-time fire monitoring. However, because of the coarse resolution of geostationary satellite images, even when deep learning models are applied, precision still remains limited. Thus, the prediction models easily fall into a local optimal solution because of the insufficient semantic information from low spatial resolution. Therefore, in this study, we proposed a novel deep learning model, SBT-FireNet, to monitor fire spots from Himawari-8 satellite images. Specifically, the extraction modules of spatial, band, and time-series features were designed and integrated into the model. The spatial feature extraction module served to collate information about fires and their surrounding environment, while the band and time-series features were designed to obtain fire-sensitive band and time information, respectively. The newly structured SBT-FireNet model was tested in four fire-prone areas with high forest cover. The precision of SBT-FireNet in four test areas is 35.2 % higher than other methods. The model yielded significant improvements through the combination of the modules of spatial, band, and time-series features and their fire-tailored design. The advantages of the high temporal resolution of geostationary satellite images were fully integrated into the model to ensure that the model monitors the possibility of fire in an automated way in a near-real-time manner.

show abstract

Wildfire detection through deep learning based on Himawari-8 satellites platform

Cited by 13 publications

References 24 publications

Using ResWnet for semantic segmentation of active wildfires from Landsat-8 imagery

Using ResWnet for semantic segmentation of active wildfires from Landsat-8 imagery

AutoST-Net: A Spatiotemporal Feature-Driven Approach for Accurate Forest Fire Spread Prediction from Remote Sensing Data

Near Real-Time Monitoring of Fire Spots Using a Novel SBT-FireNet Based on Himawari-8 Satellite Images

Contact Info

Product

Resources

About