Search Results (498)

Forest fires pose a serious threat to forest ecosystems, biodiversity, carbon sequestration, and sustainable socioeconomic development. Timely and accurate detection is essential for effective early warning and emergency response. However, existing deep learning-based methods often face challenges in balancing detection accuracy and computational efficiency under UAV-assisted forestry monitoring scenarios. This study proposes YOLO-MR, a compact and efficient forest fire detection framework based on YOLOv8n for UAV-assisted intelligent forestry monitoring. The proposed method incorporates a multi-scale deep dilated spatial pyramid fast pooling module, GhostConv, an improved ReC2f module, and an additional P2 detection layer, as well as PIoUv2 loss, enabling more effective multi-scale feature representation and improved target localization. Evaluation using the public M4SFWD dataset together with the self-constructed UFFD dataset verifies the effectiveness and generalization capability of YOLO-MR. Compared against YOLOv8n, the proposed YOLO-MR delivers increases of 1.3%, 2.1%, 1.3%, and 2.1% for Precision, Recall, mAP50, and mAP50-90, respectively, on the M4SFWD dataset, with corresponding gains of 0.9%, 1.8%, 1.8%, and 2.5% on the UFFD dataset. Meanwhile, the proposed model requires only 2.85 M parameters, which is 5.3% fewer than the baseline, demonstrating improved parameter efficiency. The experimental results demonstrate that YOLO-MR provides an effective trade-off between detection performance and computational efficiency, offering a promising solution for Unmanned Aerial Vehicle (UAV)-assisted forest fire monitoring and early warning. By enabling timely wildfire detection with a compact and efficient architecture, the proposed framework supports sustainable intelligent forestry monitoring, contributes to ecosystem protection and disaster prevention, and promotes sustainable forest management. Full article

Accurate detection in the early stages of a fire is a crucial prerequisite for the efficient implementation of fire suppression and emergency rescue operations. Its accuracy and timeliness directly affect the control of disaster loss severity. Traditional fire detection methods mainly include three categories, which are manual inspection, sensor detection, and visual recognition. However, manual inspection is restricted by labor costs and time efficiency, making it difficult to achieve large-scale, high-frequency and real-time fire monitoring. Sensor detection is easily interfered by environmental factors such as temperature, humidity, and dust, leading to frequent false alarms and missed alarms. Visual recognition technology has shortcomings in aspects such as detailed feature perception, dynamic scene modeling, and reasoning robustness in complex environments, making it difficult to meet the requirements of high-precision detection. To address these issues, this study innovatively proposes a lightweight fire and smoke detection model based on semantic enhancement and frequency domain perception modeling, which is named the SemaFire you only look once (SemaFire-YOLO) model. The model constructs a large language and vision assistant (LLaVA) semantic guidance module, which uses a large language model to understand and guide the semantic features of images, thereby enhancing the saliency representation intensity of small and weak target regions. Then, a Haar wavelet-based downsampling module is adopted, which compresses spatial information while preserving high-frequency features such as flame edges and smoke textures, improving the accuracy of target recognition. Next, the convolution modulation mechanism is introduced to replace the traditional attention mechanism, enhancing the overall modeling efficiency and reducing computational overhead. Finally, a Dynamic Tanh normalization module is adopted to replace the batch normalization module in the traditional YOLO algorithm, strengthening the model’s representation stability and reasoning robustness under unstable input distributions. Experimental results show that the SemaFire-YOLO model achieves a mean average precision (mAP@0.5) of 64.30% on the fire image dataset, which is 0.8, 2.0, 0.6, and 3.8 percentage points higher than that of mainstream models such as YOLOv5n, YOLOv8n, YOLOv11n, and YOLOv12n, respectively. It exhibits better boundary detection capability and practical deployment potential. Through visual analysis, the results indicate that the improved SemaFire-YOLO model achieves more accurate detection and higher confidence in actual complex scenarios, further verifying the model’s robustness and accuracy in complex scenarios such as low contrast and dynamic fire conditions. Full article

Compound spring floods in cold-continental and semi-arid interiors arise from interacting snowmelt, rain-on-snow events, intense precipitation, and frozen or saturated soils, yet these mechanisms remain poorly synthesized for Central Asia. This review develops a process-oriented framework linking preconditioning, triggers, propagation/amplification, impacts, and recovery outcomes. The synthesis shows that the most destructive spring floods occur when substantial antecedent snow storage and restricted infiltration coincide with rapid warming and rainfall, producing efficient runoff generation and widespread impacts. Evidence from Kazakhstan and comparable continental regions indicates that mechanistic understanding is relatively robust, but standardized event-level reporting of snow-water equivalent, soil wetness, precipitation phase, routing constraints, and recovery indicators remains uneven. To support post-disaster comparison, we introduce and demonstrate a Recovery Effectiveness Index (REI) combining housing resettlement, compensation, infrastructure restoration, and equity of assistance. A proof-of-concept application to the 2024 Kazakhstan floods produced a 21 June 2024 snapshot REI of 0.607–0.757 and an end-year REI of 0.850–1.000, depending on the treatment of the equity component. The framework supports compound-driver monitoring, early warning, recovery benchmarking, and more harmonized flood-risk assessment in data-sparse continental regions. Full article

Post-disaster emergency communication networks often suffer from coverage degradation and limited network observability, which makes it difficult to maintain reliable connectivity for evacuees. Existing UAV-assisted communication methods usually rely on network-side visible metrics for deployment decisions. As a result, they may overlook evacuees whose communication demands are hidden in coverage blind zones or observation blind zones along predefined evacuation corridors. To address this problem, this paper proposes a sensing-assisted UAV-BS recovery method for invisible evacuee demand. The method constructs an invisible-demand map by combining sensed evacuee states, ground coverage conditions, network observation states, and evacuation urgency. It further introduces an evacuation-flow demand map to describe continuous communication demand along evacuation corridors. These two maps are combined to guide temporary UAV-BS access recovery. The simulation results show that the proposed method achieves the best overall balance among invisible-demand recovery, evacuation-path coverage, and edge evacuee rate. Compared with the blind-zone-only baseline, it improves DCR (demand coverage ratio) from 0.365 to 0.373, DW-EPC (demand-weighted evacuation-path coverage) from 0.286 to 0.316, and the fifth-percentile evacuee rate from 1.559 to 1.672 bps/Hz. The proposed method also shows more stable performance under sensing-output uncertainty and constrained UAV response radius. Full article

Social media has emerged as a crucial environment for examining public sentiment during disasters, providing immediate insights into collective emotions and urgent expectations. This research examines the emotional reactions expressed on Turkish posts shared on the X platform (formerly Twitter) following the 6 February 2023 earthquake by employing an integrated method that combines topic modeling and topic-based sentiment analysis. Data were collected between 10 February 2023 and 28 February 2023. A large dataset consisting of 305,000 tweets was compiled, and 296,836 tweets remained for analysis after preprocessing and filtering procedures. Latent Dirichlet Allocation (LDA), enhanced with term frequency-inverse document frequency weighting and bigram extraction techniques, was applied to identify prominent themes, including rescue operations, appeals for assistance, communication about missing persons, and disaster management. The sentiment polarity within each topic was determined using a hybrid deep learning model incorporating Bidirectional Encoder Representations from Transformers (BERT) embeddings Convolutional Neural Networks (CNN), Bidirectional Long Short-Term Memory (BiLSTM) layers, and FastText representations. This model reached a classification accuracy of 94%, with F1-scores of 0.91 and 0.95, recall values of 0.90 and 0.96, and precision values of 0.92 and 0.95, achieving higher performance than the evaluated baseline models. The findings indicate that supportive, solidarity-oriented, and resilience-related communication patterns were among the most frequently observed positive sentiment expressions, whereas negative sentiments appeared more frequently in discussions regarding delays in aid delivery and perceived shortcomings in institutional response. This study presents a scalable and flexible framework for analyzing sentiment in Turkish-language crisis communication, providing insights that may support disaster response monitoring and decision-making processes as well as the development of systems for tracking public reactions in real time. Full article

Background/Objectives: Labor pain is a multidimensional experience associated with physiological, cultural, psychological, and contextual factors. This study aimed to examine the association of personality-related characteristics, cultural beliefs, obstetric characteristics, and proxy indicators of post-disaster context with labor pain perception among women giving birth in Hatay after the 2023 Türkiye earthquakes. Methods: This prospective observational study was conducted with 314 women admitted to Hatay Training and Research Hospital between February and June 2025. Participants were between 38 and 42 gestational weeks, had a singleton healthy fetus, were admitted in active labor, and were expected to give birth vaginally. Data were collected using a researcher-developed questionnaire, the Ten-Item Personality Inventory, and the Visual Analog Scale. Labor pain was assessed at 6 cm, 8 cm, and full cervical dilatation (10 cm). Results: VAS scores increased significantly across cervical dilatation points, from 5.04 ± 0.81 at 6 cm to 7.01 ± 0.82 at 8 cm and 8.06 ± 0.93 at full cervical dilatation (10 cm). Repeated-measures ANOVA showed a significant within-person increase in pain intensity across the three assessment points, F(2, 626) = 996.444, p < 0.001, partial η² = 0.761. Age was not significantly correlated with VAS pain score at full cervical dilatation. In exploratory unadjusted comparisons, VAS scores at full cervical dilatation differed according to education level, official marriage status, previous birth history and mode, attendance at antenatal education, and praying to relieve labor pain. In the multivariable regression model, higher Extraversion and higher education level were associated with lower VAS scores, whereas attendance at antenatal education, greater importance given to traditional rules, previous assisted vaginal/cesarean birth, and current place of residence were independently associated with VAS scores. Conscientiousness was not significantly associated with VAS scores in the adjusted model. Earthquake experience was not significantly associated with VAS scores. Conclusions: Labor pain perception was associated with selected sociodemographic, obstetric, and cultural characteristics. The findings support the importance of individualized, culturally sensitive, and trauma-informed midwifery care in disaster-affected regions. Personality-related findings should be interpreted cautiously because the corrected reliability analysis showed low internal consistency for Agreeableness, Emotional Stability, and Openness to Experience, although Extraversion showed high internal consistency and Conscientiousness showed relatively better but still limited internal consistency. Disaster-related findings should also be interpreted cautiously because post-disaster context was assessed using only limited proxy indicators; current place of residence was independently associated with VAS scores in the adjusted model, whereas earthquake experience was not. Because of the observational design, causal interpretations cannot be made. Full article

The humid coastal Lingnan region of South China, including the Chaoshan area of eastern Guangdong, is frequently exposed to disaster-prone weather conditions such as high humidity, typhoon-related winds, heavy rainfall, and salt-laden coastal air. These long-term environmental exposures may contribute to surface deterioration risks of architectural heritage. Located in Shantou, Yingchuan Shijia has shown five visible surface deterioration types—cracks, staining, saltpetering, plants, and spalling—under the combined influence of environmental exposure, material aging, previous disturbance, and insufficient maintenance. To address the limitations of manual inspection, this study explores a conservation-oriented intelligent workflow integrating YOLO-based detection, digital documentation, and screening-level conservation interpretation. Digital documentation used UAV imagery, mobile LiDAR scanning, measured drawings, and SketchUp-based three-dimensional modeling. The dataset was built in three stages: a 99-image preliminary dataset, where YOLOv8 showed only basic learning capability with low performance metrics, including Precision of 33.0 ± 3.0%, Recall of 28.0 ± 1.0%, mAP50 of 25.0 ± 1.0%, and mAP50-95 of 11.0 ± 1.0%; a 362-image non-augmented case-study dataset, where YOLOv8 still showed limited performance, with mAP50 of 20.0 ± 1.0% and mAP50-95 of 8.0 ± 1.0%; and a final YOLO-format case-study dataset of 2000 images after training-set-only augmentation using 11 geometric and photometric transformation methods. After augmentation, YOLOv8 mAP50 increased to 62.0 ± 2.0%. Under the same augmented-data condition, YOLOv13 showed Precision of 89.0 ± 1.0%, Recall of 77.0 ± 1.0%, mAP50 of 84.0 ± 1.0%, and mAP50-95 of 65.0 ± 1.0%, indicating relatively higher validation performance than YOLOv8. In the normalized confusion matrix, the background missed-detection values for cracks and saltpetering were 0.29 and 0.22, respectively, indicating that weak-feature and low-contrast deterioration types remained challenging. Based on YOLOv13, a mini program was developed to organize detection outputs and provide field-oriented preliminary conservation hints. Overall, this study provides a preliminary workflow linking digital collection, image-based deterioration detection, Grad-CAM visualization, and assisted field recording for the preventive conservation of Chaoshan overseas-Chinese residences in humid coastal heritage environments. Full article

Modern smart cities increasingly depend on resilient and intelligent energy infrastructures to maintain critical urban services during large-scale disturbances and multi-fault conditions. Conventional restoration approaches are often limited by centralized operation, delayed response, and inadequate coordination of distributed energy resources (DERs) under emergency conditions. To address these challenges, this paper proposes a Federated AI-Driven Urban Energy Resilience Framework for Smart City Critical Infrastructure Restoration using Virtual Power Plant (VPP) coordination, blockchain-enabled peer-to-peer (P2P) energy trading, and intelligent distributed energy management. The proposed framework is validated on the IEEE 118-bus radial distribution system under severe dual-fault outage conditions, representing urban disaster-induced infrastructure interruptions. Critical urban service zones, including healthcare support systems, emergency loads, smart residential sectors, and EV charging corridors, are considered during the restoration process. The Seagull Optimization Algorithm (SOA) is employed to optimize DER dispatch and improve restoration performance under operational constraints. A progressive restoration strategy comprising conventional outage conditions, VPP-assisted restoration, blockchain-enabled decentralized energy trading, and AI-driven coordinated restoration is analyzed. Simulation results demonstrate that the proposed framework significantly enhances urban energy resilience by increasing load restoration from 55.05% to 94.20%, reducing Energy Not Supplied (ENS), improving voltage stability, and lowering interruption-related economic losses. The minimum bus voltage improves to 0.965 p.u. under the proposed coordinated restoration strategy. The results show that coordinated VPP operation and blockchain-based energy sharing can support reliable restoration of critical urban infrastructure during major outage conditions. The results indicate that integrating AI-assisted VPP coordination with secure decentralized energy trading can effectively support smart city critical infrastructure continuity during extreme outage conditions. The proposed framework provides a scalable and resilient solution for future intelligent urban energy systems and disaster-resilient smart city applications. Full article

Named entity recognition (NER) in marine meteorological disaster texts is essential for automated information extraction and disaster management. However, disaster-chain descriptions often contain nested entities that are difficult for conventional flat NER models to represent. This paper proposes PRSpan, a position-role-aware span classification model for nested NER. PRSpan incorporates Rotary Position Embedding (RoPE)-enhanced attention for relative position-aware boundary modeling and uses Conditional Layer Normalization (CLN) to generate role-specific Head, Mid, and Tail token features. A Positional Role Pooling strategy further aggregates these features into span representations to preserve boundary cues and internal semantic coherence. To support evaluation, we construct MMD-NER, a domain-specific dataset containing 1899 sentences, 17,017 entities in 11 categories, and 2978 nested entity pairs through a four-step LLM-assisted pipeline. Experimental results show that PRSpan achieves Micro-F1 and Macro-F1 scores of 94.58% and 93.47%, outperforming the strongest baseline by 3.61 and 3.93 percentage points, respectively. Additional analyses verify the effectiveness of RoPE-enhanced attention, role-specific feature generation, and Positional Role Pooling. Cross-domain transfer and LLM prompting comparisons further demonstrate the practical value of PRSpan for nested entity extraction in low-resource Earth science domains. Full article

The recent seismic activity in southeastern Turkey in February 2023 again emphasized the critical need to promptly evaluate structural damage to assist in emergency response operations. This study introduces a comprehensive ensemble deep learning approach to structural damage classification following earthquake events, based on a dataset containing 13,270 high-resolution images with 15 different damage classes. Six different state-of-the-art convolutional neural network models (VGG16, ResNet50, InceptionV3, DenseNet121, EfficientNetB0, and MobileNetV2) are combined using a weighted voting approach to handle extreme class imbalance using weighted categorical cross-entropy loss. An integrated explainability component is incorporated into the trained convolutional neural network models to highlight the image regions that contribute to the predicted damage class, thereby improving the interpretability of deep learning decisions in safety-critical post-disaster assessment scenarios. The performance evaluation results show that the ensemble model achieves a test accuracy of 93.77%, with an increase of 2.67% compared to the best performing model individually. Notably, the ensemble model improves performance in minority classes like collapsed buildings. The proposed framework can be used to provide a powerful approach to structural damage evaluation, balancing accuracy with interpretability, to assist structural engineers in post-earthquake evaluation procedures. Full article

Natural and human-made disasters can severely impair terrestrial communication infrastructures and disrupt emergency response coordination in modern smart cities. To address these challenges, this paper introduces the Weighted Average Yo-Yo-based Clustering and Routing (WAY-CR) scheme, an adaptive, secure, and energy-efficient drone-assisted solution for post-disaster network recovery and emergency response. WAY-CR integrates three main components: First, a novel WAY-based metaheuristic optimizer incorporates the concept of Yo-Yo Motion into the conventional Weighted Average Algorithm (WAA), improving the balance between exploration and exploitation during CH selection and clustering. Second, a secure communication model combines the Paillier Homomorphic Cryptosystem (PHC) with a trust evaluation model to provide end-to-end security and authenticity, ensuring that only authenticated and trustworthy drones participate in communication and routing. Third, a Trust-Aware Boltzmann Path Selection method introduces probabilistic decision-making into routing, allowing adaptive selection of secure and energy-efficient routing paths. WAY-CR formulates a multi-objective optimization model that minimizes communication cost and energy consumption while maximizing trust, link stability, and coverage. Stage 1 addresses secure intra-Ground Control Station (GCS) clustering, authentication, and trust management, whereas Stage 2 restores inter-GCS connectivity through a Secure Relay Discovery and Verification procedure based on Boltzmann Path Selection. An adaptive maintenance mechanism further supports dynamic reconfiguration in response to CH failures, mobility, or trust degradation, thereby preserving stable network performance under disaster-induced disruptions. Extensive simulation results show that WAY-CR outperforms state-of-the-art Flying Ad Hoc Network (FANET) baselines in energy efficiency, cluster stability, trust accuracy, and end-to-end packet delivery, highlighting its potential as a resilient, scalable, and secure solution for post-disaster smart-city environments. Full article

Critical infrastructure restoration (CIR) is a disaster-management and sustainability challenge because prolonged disruption of energy, water, transport, communications, healthcare, and public-administration services can amplify social, economic, and environmental losses. This PRISMA 2020-reported systematic review synthesizes post-2016 scientific literature and official policy, legal, standards, and technical documents on CIR and AI decision support. The review identified 55 records, removed 1 duplicate, excluded 1 ineligible record, and retained 53 core sources for qualitative synthesis, including 31 scholarly publications and 22 official documents. Manual screening was used; no automated screening or AI-assisted exclusion tools were applied. The results are organized around four research questions covering regulatory frameworks, recovery practices, supporting systems, and AI model families. The synthesis shows that CIR is shaped by layered governance through NIS2, the CER Directive, the AI Act, and national measures; by operational recovery practices such as continuity planning, cyber crisis coordination, interdependency mapping, and model-supported restoration; by digital platforms including SCADA/ICS, IoT sensing, GIS/common operating pictures, decision-support systems, simulation environments, and digital twins; and by AI methods ranging from classical machine learning and computer vision to reinforcement learning and generative assistants. However, evidence maturity remains uneven, with many AI applications still simulation-based, sector-specific, or weakly validated in real restoration settings. The review contributes an integrated CIR-oriented framework showing that AI creates practical value when embedded in interoperable, human-supervised, regulation-aware, and empirically validated restoration architectures that support sustainable service continuity rather than isolated automation. Full article

Road disasters such as subsidence and bridge failures pose severe threats to traffic safety. Existing warning distance calculation methods typically assume homogeneous traffic flow and overlook the spatial heterogeneity of vehicle responses across different vehicle types, limiting their applicability for geospatial early warning systems. This paper proposes a dynamic warning distance model that integrates mixed-traffic flow composition—comprising human-driven vehicles (HDVs), Level 2 advanced driver-assistance system vehicles (ADASVs), and automated vehicles (AVs) of Level 3 and above—within a geospatial risk propagation framework. The model introduces vehicle-type weighting coefficients to quantify response differences, incorporates interaction delays calibrated through SUMO microsimulations, and accounts for cascading reaction delays caused by abrupt HDV braking. The methodology is illustrated using a counterfactual reconstruction of the 2024 Meizhou–Dapu Expressway collapse in China (52 fatalities). Based on reconstructed traffic conditions (80% HDVs, 15% ADASVs, 5% AVs; average speed 27.5 m/s; flow 1800 veh/h), the calculated dynamic warning distance is 153 m, which is 12% shorter than the speed-matched conventional stopping sight distance of 174 m (computed under consistent wet-pavement assumptions). Sensitivity analyses reveal that warning distance decreases substantially with increasing AV penetration (to 42 m in AV-dominated scenarios, a potential reduction of up to 74% compared with the HDV-dominated baseline, provided that residual HDVs are supported by V2X-based alerting) and varies monotonically with traffic flow, demonstrating the model’s adaptive capability. The proposed framework provides a theoretical foundation for adaptive geospatial disaster warning strategies and offers practical guidance for infrastructure development in the era of mixed-traffic automation. Full article

Vision–language models (VLMs) hold considerable potential for interpreting large-scale remote sensing (RS) archives, which are critical for applications such as environmental monitoring, disaster response, and urban planning. However, general-purpose VLMs primarily target optical imagery and often underperform on RS tasks, while existing RS-specific VLMs still struggle with fine-grained understanding. To address these limitations, we propose GeoPilot, a tool-augmented multimodal assistant tailored for RS scenarios. GeoPilot interprets user instructions, autonomously determines whether to invoke external tools, and synthesizes their outputs to generate precise responses. A key capability of our approach is its ability to process both optical and Synthetic Aperture Radar (SAR) imagery, supporting representative tasks such as visual grounding, object detection, segmentation, and cross-domain reasoning. To support this setting, we construct a novel large-scale RS instruction dataset that jointly supports optical and SAR imagery together with explicit tool use reasoning traces, addressing the critical challenge of task-specific data scarcity. We also introduce GeoPilotBench, a benchmark for cross-domain, multi-task dialogue and tool-aware evaluation in RS, and use it to assess GeoPilot across representative tasks. Experimental results show that GeoPilot achieves strong task planning accuracy (92.6% overall planning accuracy) and competitive performance on VQA, SAR understanding, and referring object detection. End-to-end evaluation further confirms that GeoPilot’s learned tool policy introduces only limited overhead compared to standalone tool execution, demonstrating its practical value as a tool-augmented RS assistant. Full article

Natural disasters are devastating occurrences that have a major influence on the well-being of numerous individuals on a global scale. The primary goal of this study is to facilitate the rapid, transparent, and safe delivery of various aid such as food and clothing to people in disaster areas. For this purpose, a system has been established using blockchain technology in cooperation with institutions and humanitarian organizations. This system is designed to be accountable and reliable; it will supervise all processes from the source of aid materials to their distribution while protecting the personal information of disaster victims. The assistance process is improved using Smart Contracts in order to provide fast, effective, and coordinated assistance. Unlike existing humanitarian frameworks that rely on permissionless networks such as Bitcoin or Ethereum, this study proposes Hyperledger Fabric to ensure beneficiary privacy and eliminate per-transaction fees for end-users, thereby offering a more sustainable economic model for high-frequency aid distribution compared to public blockchains. The proposed system (Chainguard) addresses the ’efficiency gap’ in the current literature JSON Web Token (JWT)-based authentication layer. The results showed that Chainguard achieves a stable throughput of ~180 TPS with an end-to-end latency of less than 1.5 s, outperforming traditional heavy-cryptography models in terms of scalability and resource efficiency during real-time disaster response. Full article