Search Results (33)

Forest fires pose a significant threat to human life and property. The early detection of smoke and flames can significantly reduce the damage caused by forest fires to human society. This article presents an SFGI-YOLO model based on YOLO11n, which demonstrates outstanding advantages in detecting forest fires and smoke, particularly in the context of early fire monitoring. The main principles of the algorithm include the following: first, a small-object detection head P2 is added to better extract shallow feature information; a Feature Enhancement Module (FEM) is utilized to increase feature richness, expand the receptive field, and enhance detection capabilities for small objects across multiple scales; the lightweight GhostConv is employed to significantly reduce computational costs and decrease the number of parameters; and Inception DWConv is combined with a C3k2 module to utilize multiple parallel branches, thereby enlarging the receptive field. The improved algorithm achieved a mean Average Precision (mAP50) of 95.4% on a custom forest fire dataset, surpassing the YOLO11n model by 1.8%. This model offers more accurate detection of forest fires, reducing both missed detections and false positives and thereby meeting the high precision and real-time detection requirements in forest fire monitoring. Full article

Prolonged inundations are altering coastal forest ecosystems of the southeastern US, causing extensive tree die-offs and the development of ghost forests. This hydrological stressor also alters carbon fluxes, threatening the stability of coastal carbon sinks. This study was conducted to investigate the interactions between hydrological drivers and ecosystem responses by analyzing daily eddy covariance flux data from a wetland forest in North Carolina, USA, spanning 2009–2019. We analyzed temporal patterns of net ecosystem exchange (NEE), gross primary productivity (GPP), and ecosystem respiration (RE) under both flooded and non-flooded conditions and evaluated their relationships with observed tree mortality. Generalized Additive Modeling (GAM) revealed that groundwater table depth (GWT), leaf area index (LAI), NEE, and net radiation (Rn) were key predictors of mortality transitions (R² = 0.98). Elevated GWT induces root anoxia; declining LAI reduces productivity; elevated NEE signals physiological breakdown; and higher Rn may amplify evapotranspiration stress. Receiver Operating Characteristic (ROC) analysis revealed critical early warning thresholds for tree mortality: GWT = 2.23 cm, LAI = 2.99, NEE = 1.27 g C m⁻² d⁻¹, and Rn = 167.54 W m⁻². These values offer a basis for forecasting forest mortality risk and guiding early warning systems. Our findings highlight the dominant role of hydrological variability in ecosystem degradation and offer a threshold-based framework for early detection of mortality risks. This approach provides insights into managing coastal forest resilience amid accelerating sea level rise. Full article

Bottomland hardwood wetland forests along the Atlantic Coast of the United States have been changing over time; this change has been exceptionally apparent in the last two decades. Tree mortality is one of the most visually striking changes occurring in these coastal forests today. Using 2009–2019 tree mortality data from a bottomland hardwood forest monitored for long-term flux studies in North Carolina, we evaluated species composition and tree mortality trends and partitioned variance among hydrologic (e.g., sea level rise (SLR), groundwater table depth), biological (leaf area index (LAI)), and climatic (solar radiation and air temperature) variables affecting tree mortality. Results showed that the tree mortality rate rose from 1.64% in 2009 to 45.82% over 10 years. Tree mortality was primarily explained by a structural equation model (SEM) with R² estimates indicating the importance of hydrologic (R² = 0.65), biological (R² = 0.37), and climatic (R² = 0.10) variables. Prolonged inundation, SLR, and other stressors drove the early stages of ‘ghost forest’ formation in a formerly healthy forested wetland relatively far inland from the nearest coastline. This study contributes to a growing understanding of widespread coastal ecosystem transition as the continental margin adjusts to rising sea levels, which needs to be accounted for in ecosystem modeling frameworks. Full article

Atlantic White Cedar (Chamaecyparis thyoides) (AWC) anchors a globally threatened ecosystem that is being impacted by climate change, as these trees are vulnerable to hurricane events, sea-level rises, and increasing salinity at the forest–marsh ecotone. In this study, we determined the current amount and distribution of AWC in an area that is experiencing sea-level rises that are higher than the global average rate. We used a combination of a field investigation and aerial photo interpretation to identify known locations of AWC, then integrated Sentinel-1 and 2A satellite data with abiotic variables into a species distribution model. We developed a spectral signature of AWC to aid in our understanding of phenology differences from nearby species groups. The selected model had an out-of-bag error of 7.2%, and 8 of the 11 variables retained in the final model were derived from remotely sensed data, highlighting the importance of including temporal data to exploit divergent phenology. Model predictions were strong in live AWC stands and, accurately, did not predict live AWC in stands that experienced high levels of mortality after Hurricane Sandy. The model presented in this study provides high utility for AWC management and tracking mortality dynamics within stands after disturbances such as hurricanes. Full article

Forest fires pose a significant threat to ecosystems and communities. This study introduces innovative enhancements to the YOLOv8n object detection algorithm, significantly improving its efficiency and accuracy for real-time forest fire monitoring. By employing Depthwise Separable Convolution and Ghost Convolution, the model’s computational complexity is significantly reduced, making it suitable for deployment on resource-constrained edge devices. Additionally, Dynamic UpSampling and Coordinate Attention mechanisms enhance the model’s ability to capture multi-scale features and focus on relevant regions, improving detection accuracy for small-scale fires. The Distance-Intersection over Union loss function further optimizes the model’s training process, leading to more accurate bounding box predictions. Experimental results on a comprehensive dataset demonstrate that our proposed model achieves a 41% reduction in parameters and a 54% reduction in GFLOPs, while maintaining a high mean Average Precision (mAP) of 99.0% at an Intersection over Union (IoU) threshold of 0.5. The proposed model offers a promising solution for real-time forest fire monitoring, enabling a timely detection of, and response to, wildfires. Full article

The threat of forest fires to human life and property causes significant damage to human society. Early signs, such as small fires and smoke, are often difficult to detect. As a consequence, early detection of smoke and fires is crucial. Traditional forest fire detection models have shortcomings, including low detection accuracy and efficiency. The YOLOv8 model exhibits robust capabilities in detecting forest fires and smoke. However, it struggles to balance accuracy, model complexity, and detection speed. This paper proposes LD-YOLO, a lightweight dynamic model based on the YOLOv8, to detect forest fires and smoke. Firstly, GhostConv is introduced to generate more smoke feature maps in forest fires through low-cost linear transformations, while maintaining high accuracy and reducing model parameters. Secondly, we propose C2f-Ghost-DynamicConv as an effective tool for increasing feature extraction and representing smoke from forest fires. This method aims to optimize the use of computing resources. Thirdly, we introduce DySample to address the loss of fine-grained detail in initial forest fire images. A point-based sampling method is utilized to enhance the resolution of small-target fire images without imposing an additional computational burden. Fourthly, the Spatial Context Awareness Module (SCAM) is introduced to address insufficient feature representation and background interference. Also, a lightweight self-attention detection head (SADH) is designed to capture global forest fire and smoke features. Lastly, Shape-IoU, which emphasizes the importance of boundaries’ shape and scale, is used to improve smoke detection in forest fires. The experimental results show that LD-YOLO realizes an mAP_0.5 of 86.3% on a custom forest fire dataset, which is 4.2% better than the original model, with 36.79% fewer parameters, 48.24% lower FLOPs, and 15.99% higher FPS. Therefore, LD-YOLO indicates forest fires and smoke with high accuracy, fast detection speed, and a low model complexity. This is crucial to the timely detection of forest fires. Full article

Upper estuarine forested wetlands (UEFWs) play an important role in the sequestration of atmospheric carbon (C), which is facilitated by their position at the boundary of terrestrial and maritime environments but threatened by sea level rise. This study assessed the change in aboveground C stocks along the estuarine–riverine hydrogeomorphic gradient spanning salt-impacted freshwater tidal forested wetlands to freshwater forested wetlands in seasonally tidal and nontidal landscape positions. Standing stocks of C in forested wetlands were measured along two major coastal river systems, the Winyah Bay in South Carolina and the Savannah River in Georgia (USA), replicating and expanding a previous study to allow the assessment of change over time. Aboveground C stocks on these systems averaged 172.9 Mg C ha⁻¹, comparable to those found in UEFWs across the globe and distinct from the terrestrial forested ecosystems they are often considered to be a part of during large-scale C inventory efforts. Groundwater salinity conditions as low as 1.3 ppt were observed in conjunction with losses of aboveground C. When viewed in context alongside expected sea level rise and corresponding saltwater intrusion estimates, these data suggest a marked decrease in aboveground C stocks in forested wetlands situated in and around tidal estuaries. Full article

Due to extreme weather conditions and complex geographical features, the environments around power lines in forest areas have a high risk of wildfires. Once a wildfire occurs, it causes severe damage to the forest ecosystem. Monitoring wildfires around power lines in forested regions through deep learning can reduce the harm of wildfires to natural environments. To address the challenges of wildfire detection around power lines in forested areas, such as interference from complex environments, difficulty detecting small target objects, and high model complexity, a lightweight wildfire detection model based on the improved YOLOv8 is proposed. Firstly, we enhanced the image-feature-extraction capability using a novel feature-extraction network, GS-HGNetV2, and replaced the conventional convolutions with a Ghost Convolution (GhostConv) to reduce the model parameters. Secondly, the use of the RepViTBlock to replace the original Bottleneck in C2f enhanced the model’s feature-fusion capability, thereby improving the recognition accuracy for small target objects. Lastly, we designed a Resource-friendly Convolutional Detection Head (RCD), which reduces the model complexity while maintaining accuracy by sharing the parameters. The model’s performance was validated using a dataset of 11,280 images created by merging a custom dataset with the D-Fire data for monitoring wildfires near power lines. In comparison to YOLOv8, our model saw an improvement of 3.1% in the recall rate and 1.1% in the average precision. Simultaneously, the number of parameters and computational complexity decreased by 54.86% and 39.16%, respectively. The model is more appropriate for deployment on edge devices with limited computational power. Full article

A lightweight forest fire detection model based on YOLOv8 is proposed in this paper in response to the problems existing in traditional sensors for forest fire detection. The performance of traditional sensors is easily constrained by hardware computing power, and their adaptability in different environments needs improvement. To balance the accuracy and speed of fire detection, the GhostNetV2 lightweight network is adopted to replace the backbone network for feature extraction of YOLOv8. The Ghost module is utilized to replace traditional convolution operations, conducting feature extraction independently in different dimensional channels, significantly reducing the complexity of the model while maintaining excellent performance. Additionally, an improved CPDCA channel priority attention mechanism is proposed, which extracts spatial features through dilated convolution, thereby reducing computational overhead and enabling the model to focus more on fire targets, achieving more accurate detection. In response to the problem of small targets in fire detection, the Inner IoU loss function is introduced. By adjusting the size of the auxiliary bounding boxes, this function effectively enhances the convergence effect of small target detection, further reducing missed detections, and improving overall detection accuracy. Experimental results indicate that, compared with traditional methods, the algorithm proposed in this paper significantly improves the average precision and FPS of fire detection while maintaining a smaller model size. Through experimental analysis, compared with YOLOv3-tiny, the average precision increased by 5.9% and the frame rate reached 285.3 FPS when the model size was only 4.9 M; compared with Shufflenet, the average precision increased by 2.9%, and the inference speed tripled. Additionally, the algorithm effectively addresses false positives, such as cloud and reflective light, further enhancing the detection of small targets and reducing missed detections. Full article

Coastal Zone Soil Survey mapping provides interpretive information that can be used to increase coastal resiliency and quantify how coastal ecosystems are changing over time. North Carolina has approximately 400,500 ha of land within 500 m of the tidal coastline that is expected to undergo some degree of salinization in the next century. This study examined 33 tidal wetlands in the Albemarle–Pamlico Sound along a salinity gradient to provide a coastal zone mapping framework to quantify shoreline change rates. The primary ecosystems evaluated include intact tidal forested wetlands (average water salinity, 0.15–1.61 ppt), degraded “ghost forest” wetlands (3.51–8.28 ppt), and established mesohaline marshes (11.73–15.47 ppt). The average shoreline rate of change (m/yr) was significantly different among estuary ecosystems (p = 0.004), soil type (organic or mineral) (p < 0.001), and shore fetch category (open or protected) (p < 0.001). From 1984 to 2020, a total of 2833 ha of land has been submerged due to sea level rise in the Albemarle–Pamlico Sound with the majority (91.6%) of this loss coming from tidal marsh and ghost forest ecosystems. The results from this study highlight the importance of maintaining healthy coastal forests, which have higher net accretion rates compared to other estuarine ecosystems. Full article

The timely and precise detection of forest fires is critical for halting the spread of wildfires and minimizing ecological and economic damage. However, the large variation in target size and the complexity of the background in UAV remote sensing images increase the difficulty of real-time forest fire detection. To address this challenge, this study proposes a lightweight YOLO model for UAV remote sensing forest fire detection (LUFFD-YOLO) based on attention mechanism and multi-level feature fusion techniques: (1) GhostNetV2 was employed to enhance the conventional convolution in YOLOv8n for decreasing the number of parameters in the model; (2) a plug-and-play enhanced small-object forest fire detection C2f (ESDC2f) structure was proposed to enhance the detection capability for small forest fires; (3) an innovative hierarchical feature-integrated C2f (HFIC2f) structure was proposed to improve the model’s ability to extract information from complex backgrounds and the capability of feature fusion. The LUFFD-YOLO model surpasses the YOLOv8n, achieving a 5.1% enhancement in mAP and a 13% reduction in parameter count and obtaining desirable generalization on different datasets, indicating a good balance between high accuracy and model efficiency. This work would provide significant technical support for real-time forest fire detection using UAV remote-sensing images. Full article

The timely and effective detection of forest fires is crucial for environmental and socio-economic protection. Existing deep learning models struggle to balance accuracy and a lightweight design. We introduce SWVR, a new lightweight deep learning algorithm. Utilizing the Reparameterization Vision Transformer (RepViT) and Simple Parameter-Free Attention Module (SimAM), SWVR efficiently extracts fire-related features with reduced computational complexity. It features a bi-directional fusion network combining top-down and bottom-up approaches, incorporates lightweight Ghost Shuffle Convolution (GSConv), and uses the Wise Intersection over Union (WIoU) loss function. SWVR achieves 79.6% accuracy in detecting forest fires, which is a 5.9% improvement over the baseline, and operates at 42.7 frames per second. It also reduces the model parameters by 11.8% and the computational cost by 36.5%. Our results demonstrate SWVR’s effectiveness in achieving high accuracy with fewer computational resources, offering practical value for forest fire detection. Full article

To solve the problem of the poor performance of a flame detection algorithm in a complex forest background, such as poor detection performance, insensitivity to small targets, and excessive computational load, there is an urgent need for a lightweight, high-accuracy, real-time detection system. This paper introduces a lightweight object-detection algorithm called GS-YOLOv5s, which is based on the YOLOv5s baseline model and incorporates a multi-scale feature fusion knowledge distillation architecture. Firstly, the ghost shuffle convolution bottleneck is applied to obtain richer gradient information through branching. Secondly, the WIoU loss function is used to address the issues of GIoU related to model optimization, slow convergence, and inaccurate regression. Finally, a knowledge distillation algorithm based on feature fusion is employed to further improve its accuracy. Experimental results based on the dataset show that compared to the YOLOv5s baseline model, the proposed algorithm reduces the number of parameters and floating-point operations by approximately 26% and 36%, respectively. Moreover, it achieved a 3.1% improvement in mAP_0.5 compared to YOLOv5s. The experiments demonstrate that GS-YOLOv5s, based on multi-scale feature fusion, not only enhances detection accuracy but also meets the requirements of lightweight and real-time detection in forest fire detection, commendably improving the practicality of flame-detection algorithms. Full article

Generative Adversarial Networks (GANs) possess remarkable fitting capabilities and play a crucial role in the field of computer vision. Super-resolution restoration is the process of converting low-resolution images into high-resolution ones, providing more detail and information. This is of paramount importance for monitoring and managing forest resources, enabling the surveillance of vegetation, wildlife, and potential disruptive factors in forest ecosystems. In this study, we propose an image super-resolution model based on Generative Adversarial Networks. We incorporate Multi-Scale Residual Blocks (MSRB) as the core feature extraction component to obtain image features at different scales, enhancing feature extraction capabilities. We introduce a novel attention mechanism, GAM Attention, which is added to the VGG network to capture more accurate feature dependencies in both spatial and channel domains. We also employ the adaptive activation function Meta ACONC and Ghost convolution to optimize training efficiency and reduce network parameters. Our model is trained on the DIV2K and LOVEDA datasets, and experimental results indicate improvements in evaluation metrics compared to SRGAN, with a PSNR increase of 0.709/2.213 dB, SSIM increase of 0.032/0.142, and LPIPS reduction of 0.03/0.013. The model performs on par with Real-ESRGAN but offers significantly improved speed. Our model efficiently restores single-frame remote sensing images of forests while achieving results comparable to state-of-the-art methods. It overcomes issues related to image distortion and texture details, producing forest remote sensing images that closely resemble high-resolution real images and align more closely with human perception. This research has significant implications on a global scale for ecological conservation, resource management, climate change research, risk management, and decision-making processes. Full article

Fog interference is an unfavorable issue when using vision sensors to monitor forest environmental resources. The existence of fog causes intelligent forest vision sensor equipment to fail to obtain accurate information on environmental resources. Therefore, this study proposes a lightweight forest scene image dehazing network to remove fog interference from the vision system. To deal with the extraction of detailed forest image features, we propose utilizing joint image priors including white balance, contrast, and gamma correction feature maps as inputs of the network to strengthen the learning ability of the deep network. Focusing on reducing the computational cost of the network, four different kinds of Ghost Bottleneck blocks, which adopt an SE attention mechanism to better learn the abundant forest image features for our network, are adopted. Moreover, a lightweight upsampling module combining a bilinear interpolation method and a convolution operation is proposed, thus reducing the computing space used by the fog removal module in the intelligent equipment. In order to adapt to the unique color and texture features of forest scene images, the cost function consisting of $L_1$ loss and multi-scale structural similarity (MS-SSIM) loss is specially designed to train the proposed network. The experimental results show that our proposed method obtains more natural visual effects and better evaluation indices. The proposed network is trained both on indoor and outdoor synthetic datasets and tested on synthetic and real foggy images. The PSNR achieves an average value of 26.00 dB and SSIM achieves 0.96 on the indoor synthetic dataset, while PSNR achieves an average value of 25.58 dB and SSIM achieves 0.94 on the outdoor synthetic test images. The average processing time of our proposed dehazing network for a single foggy image with a size of 480 × 640 is 0.26 s. Full article