Assessment of Small-Extent Forest Fires in Semi-Arid Environment in Jordan Using Sentinel-2 and Landsat Sensors Data

Qarallah, Bassam; Othman, Yahia A.; Al-Ajlouni, Malik G.; Alheyari, Hadeel A.; Qoqazeh, Bara’ah A.

doi:10.3390/f14010041

Cited by 7 publications

(7 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While Unmanned Aerial Vehicle (UAV) patrols have become the primary method for forest-fire prevention, existing detection technologies often struggle to cope with the complexity of forest-fire images captured from high altitudes [3][4][5]. For example, Rahman et al [42] utilized the SSD model, leveraging texture and color information, to equip UAVs with high-speed and high-accuracy capabilities.…”

Section: Discussionmentioning

confidence: 99%

“…UAVs equipped with cameras fly over forests, taking real-time fire-monitoring photos and transmitting them to servers for analysis. There are also examples of hyperspectral and multispectral sensors being mounted on UAVs and applied to forest-fire prevention [3][4][5], which have the following problems compared to using RGB cameras: (1) hyperspectral and multispectral sensors cost much more than RGB cameras, making it easier for individuals and organizations to acquire and use RGB cameras without significant financial support; (2) RGB camera technology is very mature, is easier to integrate with the system, and can provide more comprehensive information; and (3) RGB cameras can provide real-time video streams and can quickly respond to emergency situations such as forest fires. Although hyperspectral and multispectral sensors can also provide real-time data, processing hyperspectral and multispectral data requires more complex processing and analysis, which requires more hardware equipment.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

FSNet: Enhancing Forest-Fire and Smoke Detection with an Advanced UAV-Based Network

Wu,

Qian,

et al. 2024

Forests

View full text Add to dashboard Cite

Forest fires represent a significant menace to both the ecological equilibrium of forests and the safety of human life and property. Upon ignition, fires frequently generate billowing smoke. The prompt identification and management of fire sources and smoke can efficiently avert the occurrence of extensive forest fires, thereby safeguarding both forest resources and human well-being. Although drone patrols have emerged as a primary method for forest-fire prevention, the unique characteristics of forest-fire images captured from high altitudes present challenges. These include remote distances, small fire points, smoke targets with light hues, and complex, ever-changing background environments. Consequently, traditional target-detection networks frequently exhibit diminished accuracy when handling such images. In this study, we introduce a cutting-edge drone-based network designed for the detection of forest fires and smoke, named FSNet. To begin, FSNet employs the YOCO data-augmentation method to enhance image processing, thereby augmenting both local and overall diversity within forest-fire images. Next, building upon the transformer framework, we introduce the EBblock attention module. Within this module, we introduce the notion of “groups”, maximizing the utilization of the interplay between patch tokens and groups to compute the attention map. This approach facilitates the extraction of correlations among patch tokens, between patch tokens and groups, and among groups. This approach enables the comprehensive feature extraction of fire points and smoke within the image, minimizing background interference. Across the four stages of the EBblock, we leverage a feature pyramid to integrate the outputs from each stage, thereby mitigating the loss of small target features. Simultaneously, we introduce a tailored loss function, denoted as Lforest, specifically designed for FSNet. This ensures the model’s ability to learn effectively and produce high-quality prediction boxes. We assess the performance of the FSNet model across three publicly available forest-fire datasets, utilizing mAP, Recall, and FPS as evaluation metrics. The outcomes reveal that FSNet achieves remarkable results: on the Flame, Corsican, and D-Fire datasets, it attains mAP scores of 97.2%, 87.5%, and 94.3%, respectively, with Recall rates of 93.9%, 87.3%, and 90.8%, respectively, and FPS values of 91.2, 90.7, and 92.6, respectively. Furthermore, extensive comparative and ablation experiments validate the superior performance of the FSNet model.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

FSNet: Enhancing Forest-Fire and Smoke Detection with an Advanced UAV-Based Network

Wu,

Qian,

et al. 2024

Forests

View full text Add to dashboard Cite

show abstract

“…To ensure the quality of AI-Hub data, the National Geographic Information Institute (NGII) of South Korea supervised the management and monitoring of image data quality, including radiometric calibration and geometric correction, while KOFPI managed the quality of label image data [28]. The dataset consists of 17,043 images, divided into a 7:3 ratio of training (11,929) and validation (5,114) images. Additionally, we constructed datasets with a resolution of 0.5 meters and a size of 256x256 pixels (Table 1).…”

Section: Study Area and Dataset Descriptionmentioning

confidence: 99%

“…Traditional methods for forest monitoring, such as ground surveys using the Global Navigation Satellite System (GNSS) and remote sensing techniques, have been widely used. Remote sensing, in particular, enables the detection of various land disturbances over time [5][6][7][8][9][10][11][12]. However, remote sensing methods may be limited in early-stage detection when ground access is restricted [13].…”

Section: Introductionmentioning

confidence: 99%

ResNet152-U-Net: Transfer Learning for the Semantic Segmentation of Forest Restoration Site Using Aerial Images

Son,

Ha,

Seong

et al. 2024

Preprint

View full text Add to dashboard Cite

Accurate detection of forest restoration sites using deep learning is crucial for effective ecosystem management, optimizing reforestation efforts, and ensuring environmental sustainability. While various deep learning-based systems have been developed for this purpose, the influence of different neural network architectures on model performance during the identification of forest restoration sites remains underexplored. This study aimed to address this gap by exploring the optimal methodology for extracting and classifying candidate sites for forest restoration based on Convolutional Neural Networks (CNNs), specialized for image recognition. Four categories—arable land, road and barren, quarry, and forest—were defined as candidate sites for forest restoration. A dataset comprising 17,043 samples was divided into training (11,929) and validation (5,114) sets at a ratio of 7:3 for model learning. Model accuracy was evaluated using pixel accuracy (PA) and mean intersection over union (mean IoU). The Resnet152-U-Net model demonstrated a pixel accuracy of 95.2% and a mean IoU of 61.3%, indicating excellent performance in extracting candidate sites for forest restoration. This approach offers spatial and temporal advantages over conventional field surveys or aerial image-based assessments, potentially serving as valuable data for selecting future forest restoration sites.

show abstract

“…It is extremely important to determine the destruction situation depending on the severity of the fire and to classify and map it, instead of carrying out the same forestry activity in the entire fire area. Burn severity maps thus can be useful tools to determine where natural regeneration should be carried out and to identify areas requiring rapid response after a fire, show erosion potential, and protect against rockfall and avalanches, especially in areas with high-severity burns (Busico et al 2019;Parajuli et al 2020;Li et al 2022;Morante-Carballo et al 2022;Qarallah et al 2022) In this study, the forest fire of 2020 in the Western Black Sea of Turkiye was analyzed. In the study site, the pre-and post-fire situation was determined for Kastamonu-Taşköprü Forestry Management Directorate using Sentinel-2 images.…”

Section: Introductionmentioning

confidence: 99%

Burn severity evaluation in black pine forests with topographical factors using Sentinel-2 in Kastamonu, Turkiye

Genç,

Küçük,

Keleş

et al. 2023

CERNE

View full text Add to dashboard Cite

Background: Forest fires are one of the most important natural disasters all over the world in terms of the damage they cause to the ecosystem. Turkey is also exposed to wildfires damaging large areas of forests every year. Wildfires endanger the sustainability of forest resources and cause significant biological and ecological damage to the forests. It is crucial to estimate fire behaviour characteristics to take effective interventions in the fire events. Obtaining data based on terrestrial measurements is very expensive and very time-consuming to predict fire behaviour characteristics. The use of remote sensing technologies is therefore very useful since the satellite images will be faster, more sensitive, and economical to determine the burning severity and burning areas.Results: In this study, the forest fire that occurred in the Kastamonu-Taşköprü district was analyzed with remote sensing techniques. The fire occurred in 2020 (06.09.2020). The fire satellite image was thus taken from the pre-fire period (26.08.2020) and post-fire period (13.10.2020). First of all, prefire and post-fire Sentinel-2 images of fire areas were used to determine the burned area using NBR (Normalized Burn Ratio) and dNBR (Differenced Normalized Burn Ratio) indices. Also, burned area rate and burn severity were evaluated depending on the altitude, aspect, and slope factors. Conclusion:The total burned area was 1504.9 ha. The maps showed that the burned areas were covered by moderate-and high-severity classes. The forest fire was more severe in the altitude range from 1170 to 1370m, at 20-33% slope and northerly aspects in the burned area. The existence of extreme meteorological factors and the horizontal and vertical continuity of the forest fuels have been the main factors in the effect of the fire on large areas. Estimation of forest fire risk, taking into account extreme meteorological conditions and fuel properties, will have an important place in forest ecology and management.

show abstract

Assessment of Small-Extent Forest Fires in Semi-Arid Environment in Jordan Using Sentinel-2 and Landsat Sensors Data

Cited by 7 publications

References 37 publications

FSNet: Enhancing Forest-Fire and Smoke Detection with an Advanced UAV-Based Network

FSNet: Enhancing Forest-Fire and Smoke Detection with an Advanced UAV-Based Network

ResNet152-U-Net: Transfer Learning for the Semantic Segmentation of Forest Restoration Site Using Aerial Images

Burn severity evaluation in black pine forests with topographical factors using Sentinel-2 in Kastamonu, Turkiye

Contact Info

Product

Resources

About