Search Results (191)

Coastal freak waves (CFWs) are sudden and hazardous wave events that occur near shorelines and can pose serious threats to coastal visitors and infrastructure. Due to the complex interactions among coastal bathymetry, wave dynamics, and environmental conditions, the mechanisms governing CFW formation remain poorly understood, making reliable prediction difficult. This study investigates the feasibility of applying machine learning techniques to predict CFW occurrences using observational environmental data. Three machine learning algorithms, the Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Network (ANN), were developed to generate probability-based predictions of CFW events. Environmental variables derived from buoy observations, including wave characteristics, wind conditions, swell parameters, wave grouping indicators, and nonlinear wave interaction indices, were used as model inputs. Hyperparameters were optimized using grid search combined with k-fold cross-validation. The results show that all three models achieved comparable predictive performance, with AUC values close to 0.80 and overall prediction accuracy around 74%. The ANN model achieved the highest recall, indicating strong capability in detecting CFW events, while the RF and SVM models showed more balanced precision and recall. Analysis of high-probability prediction events suggests that CFW occurrences are associated with swell-dominated conditions, strong wave grouping behavior, and enhanced nonlinear wave interactions. These results demonstrate that machine learning provides a promising framework for probabilistic prediction of coastal freak waves and has potential applications in coastal hazard assessment and early warning systems. Full article

The safety and stability of underground coal mining are largely determined by the structural features of coal seams and surrounding rocks. Geological heterogeneities such as faults, fracture zones, and lithological variations strongly influence the distribution of rock pressure and the occurrence of geodynamic hazards. This highlights the need for reliable geophysical methods capable of identifying such zones under mining conditions. Electrical prospecting represents a promising diagnostic approach, as it is highly sensitive to changes in the physical properties of rocks. Unlike conventional geological mapping, it enables the detection of hidden structures and weakened zones often invisible to direct observation. Advances in instrumentation and data processing have further expanded the applicability of electrical methods in complex environments. This study introduces a methodology of electrical prospecting observations for the diagnosis of coal seams. The analysis focuses on conductivity anomalies that reflect tectonic disturbances, fracture systems, and lithological heterogeneities. Field investigations demonstrated the sensitivity of the method to local environmental variations. Comparison with geological records confirmed the validity of the approach: the identified anomalous zones correlated well with documented tectonic features. The methodology showed a stable performance and revealed potential for integration into mine monitoring systems. It allows the identification of areas associated with elevated rock pressure and possible geodynamic activity, thereby contributing to safer underground operations. In the longer term, electrical prospecting may be applied to other coal deposits, including those with a high gas content and complex structure. The development of automated interpretation tools and machine learning algorithms could further increase processing efficiency and improve predictive reliability. Overall, the results confirm that electrical prospecting in mining environments can become an effective instrument for enhancing safety and building more accurate geological–geophysical models of coal seams. Full article

The main objective of this study is to automatically detect real-time snow-related road surface conditions using imagery captured from existing roadside webcams along interstate freeways. Blowing snow is considered one of the most hazardous roadway weather phenomena because it significantly reduces driver visibility and adversely affects vehicle operation. A comprehensive image preprocessing and reduction process was conducted to construct two reference datasets. The first dataset consisted of two categories (blowing snow and no blowing snow), while the second dataset included five surface condition categories: blowing snow, dry, slushy, snow covered, and snow patched. Eight pre-trained convolutional neural networks (CNNs), including AlexNet, SqueezeNet, ShuffleNet, ResNet18, GoogleNet, ResNet50, MobileNet-V3, and EfficientNet-B0, were evaluated for roadway surface condition classification. For Dataset 1, ResNet50 achieved the highest detection accuracy of 97.88%, while AlexNet demonstrated competitive performance with 97.56% accuracy and significantly shorter training time. Among the lightweight architectures, MobileNet-V3 achieved 95.56% accuracy, demonstrating strong computational efficiency. EfficientNet-B0 achieved 93.56% accuracy while maintaining reduced model complexity. For Dataset 2, ResNet18 achieved the highest multi-class detection accuracy of 96.10%, while AlexNet required the shortest training time among the evaluated models. A comparative analysis between deep CNN models and traditional machine learning approaches showed that deep CNNs significantly outperform feature-based methods in detecting blowing snow conditions. The proposed framework provides an automated, accurate, and scalable solution for roadway surface condition monitoring and supports real-time applications in intelligent transportation systems. Full article

Landslide hazard potential is high across the St. Lawrence lowlands of Québec, Canada, due to sensitive glaciomarine clay deposits and the presence of moderate seismic activity, causing slope failures in the region. The main objectives of the study are to develop a working database for landslides in the region and use that database to improve regional landslide susceptibility analysis. Using high-resolution (1 m by 1 m cells) digital terrain models dated from 2009 and validated with satellite photogrammetry from 2012, a landslide inventory of 263 cases related to the 2010 Val-des-Bois earthquake (moment magnitude 5.0) is created. Relationships between landslide susceptibility factors, such as slope angle, and seismic conditioning factors, such as peak ground acceleration, are examined through machine learning methods. For landslide detection, an overall accuracy of approximately 85% (AUC 0.914) is achieved using random forest and logistic regression models cross-validated through 5-fold analysis, showing improvement over the currently employed Hazus method, which achieves an accuracy of approximately 67%. From a regional perspective, the developed inventory and resultant susceptibility models are unique and form the foundation for future studies to improve the understanding of earthquake-induced landslides in the Western Québec Seismic Zone, which historically lacks detailed landslide inventories. Full article

Underground mining environments pose significant challenges for automated hazard detection due to low illumination, restricted visibility, and the absence of Global Navigation Satellite System (GNSS) coverage. These factors limit situational awareness and delay inspection efforts, particularly after disruptive events when rapid assessment is essential for safety. This study addresses this problem by developing a dual-pipeline framework for 2D–3D detection that uses 360° imaging and LiDAR-based machine learning to identify people, vehicles, and positional changes in underground settings without requiring personnel to re-enter hazardous areas. The objective was to create a system capable of recognizing objects and monitoring spatial changes under real underground mine conditions. The 2D component used a Ricoh Theta Z1 camera to collect panoramic images, and a YOLO (You Only Look Once) v8n model was fine-tuned using datasets representing low light, shadowed underground scenes. The 3D component employed an Ouster OS1-070-64 LiDAR sensor, and point clouds were processed through denoising, ICP alignment, surface reconstruction, manual annotation, and 2D projection. A YOLO-based model was then trained to detect objects and measure displacement between LiDAR scans. Results demonstrated strong performance for both components. The fine-tuned YOLOv8n model reliably detected personnel and vehicles despite challenging lighting and visual clutter, while the 3D pipeline localized objects in the registered LiDAR frame and quantified vehicle displacement between consecutive scans by comparing 3D bounding-box centroids after ICP alignment (displacement vector and magnitude). These findings indicate that the combined 2D–3D system can effectively support automated hazard recognition and environmental monitoring in GNSS-denied underground spaces. Full article

Safety in the operation of Unmanned Aerial Vehicles (UAVs) is emerging as an increasingly important requirement to avoid accidents or possible hazards, because of the growing number and variety of applications that make use of such systems. Consequently, the ability to detect and classify damages occurring on UAV components becomes critical, so that appropriate countermeasures can be applied on time. In this paper, a two-step methodology is proposed to detect damage to UAV propellers, and to classify its severity, so that the most appropriate response can be implemented. In fact, a first step is carried out onboard drone, in real-time, taking advantage of the acoustic emissions of the propeller and the potential of edge processing: a tiny Machine Learning (ML) classifier assesses the severity of the damage and, when deemed critical, the UAV is directed towards a ground station hosting a radar-based system, to discriminate the severity of the fault based on contactless vibration displacement and frequency measurements. The combination of both detection approaches realizes a diagnostic system that is time-responsive and accurate in defining the type, the amount, and the location of the damage. Damage classification performance values over 99% are provided by the embedded audio-based ML model; the radar-based step can further differentiate and measure the location of the propeller cut, which could eventually lead to forced landing of the UAV. Full article

This review synthesizes the state of the art on the integration of digital technologies, particularly machine learning, the Internet of Things (IoT), and advanced image processing techniques, for enhanced hazard monitoring. Focusing on air pollution, earthquakes, floods, and fires, we analyze articles selected from Scopus published between 2015 and 2024. This study classifies the selected articles based on hazard type, digital technology application, geographical location, and research methodology. We assess the effectiveness of various approaches in improving the accuracy and efficiency of hazard detection, monitoring, and prediction. The review highlights the growing trend of leveraging multi-sensor data fusion, deep learning models, and IoT-enabled systems for real-time monitoring and early warning. Furthermore, we identify key challenges and future directions in the development of robust and scalable hazard monitoring systems, emphasizing the importance of data-driven solutions for sustainable environmental management and disaster resilience. Full article

The unpredictable nature of outdoor settings introduces numerous safety concerns, making hazard detection crucial for safe navigation. To address this issue, this paper proposes a sidewalk hazard detection system that combines a Variational Autoencoder (VAE) with a One-Class Support Vector Machine (OCSVM), using a wearable RGB camera as the primary sensing modality to enable low-cost, portable deployment and provide visual detail for detecting surface irregularities and unexpected objects. The VAE is trained exclusively on clean, obstruction-free sidewalk data to learn normal appearance patterns. At inference time, the reconstruction error produced by the VAE is used to identify spatial anomalies within each frame. These flagged anomalies are passed to an OCSVM, which determines whether they constitute a non-hazardous anomaly or a true hazardous anomaly that may impede navigation. To support this approach, we introduce a custom dataset consisting of over 20,000 training images of normal sidewalk scenes and 8000 testing frames containing both hazardous and non-hazardous anomalies. Experimental results demonstrate that the proposed VAE + OCSVM model achieves an AUC of 0.92 and an F1 score of 0.85, outperforming baseline anomaly detection models for outdoor sidewalk navigation. These findings indicate that the hybrid method offers a robust solution for sidewalk hazard detection in real-world outdoor environments. Full article

Sea fog is a major meteorological hazard that severely disrupts maritime transportation and economic activities in the South China Sea. As China’s next-generation geostationary meteorological satellite, Fengyun-4B (FY-4B) supplies continuous observations that are well suited for sea fog monitoring, yet a satellite-specific recognition method has been lacking. A key obstacle is the radiometric inconsistency between the Advanced Geostationary Radiation Imager (AGRI) sensors on FY-4A and FY-4B, compounded by the cessation of Cloud–Aerosol Lidar with Orthogonal Polarization (CALIOP) observations, which prevents direct transfer of fog labels. To address these challenges and fill this research gap, we propose a machine learning framework that integrates cross-satellite radiometric recalibration and physical mechanism constraints for robust daytime sea fog detection. First, we innovatively apply a radiation recalibration transfer technique based on the radiative transfer model to normalize FY-4A/B radiances and, together with Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observation (CALIPSO) cloud/fog classification products and ERA5 reanalysis, construct a highly consistent joint training set of FY-4A/B for the winter-spring seasons since 2019. Secondly, to enhance the model’s physical performance, we incorporate key physical parameters related to the sea fog formation process (such as temperature inversion, near-surface humidity, and wind field characteristics) as physical constraints, and combine them with multispectral channel sensitivity and the brightness temperature (BT) standard deviation that characterizes texture smoothness, resulting in an optimized 13-dimensional feature matrix. Using this, we optimize the sea fog recognition model parameters of decision tree (DT), random forest (RF), and support vector machine (SVM) with grid search and particle swarm optimization (PSO) algorithms. The validation results show that the RF model outperforms others with the highest overall classification accuracy (0.91) and probability of detection (POD, 0.81) that surpasses prior FY-4A-based work for the South China Sea (POD 0.71–0.76). More importantly, this study demonstrates that the proposed FY-4B framework provides reliable technical support for operational, continuous sea fog monitoring over the South China Sea. Full article

Eutrophication of water bodies and the bloom of toxin-producing cyanoprokaryotes raise health concerns. Various cyanoprokaryotes species, including Microcystis, Raphidiopsis, Nodularia, and Chrysosporum, release toxins into the aquatic environment, which can reach concentrations toxic to humans and animals. Rising temperatures and human activities are primary drivers behind the increasing frequency of toxic cyanobacterial blooms. The Word Health Organization (WHO) has established provisional guideline values for cyanotoxins in drinking water and water used for other purposes in daily human activities, and has published guidance for identifying hazards and managing risks posed by cyanobacteria and their toxins. There are currently no acceptable limit values for cyanotoxins. To address monitoring needs, contemporary strategies now incorporate molecular genetics, immunoassays, biochemical profiling, and emerging machine-learning frameworks. This paper reviews current early detection methods for harmful cyanobacterial blooms, highlighting their practical advantages and drawbacks. Full article

With the advancement of industrial systems toward greater complexity and higher asset value, unexpected equipment failures now risk severe production interruptions, substantial economic costs, and critical safety hazards. Conventional maintenance strategies, which are primarily reactive or schedule-based, have proven inadequate in preventing unplanned downtime, underscoring a pressing demand for more intelligent monitoring solutions. In this context, intelligent spectral detection has arisen as a transformative methodology to bridge this gap. This review explores the integration of spectroscopic techniques with machine learning for equipment defect diagnosis and prognosis, with a particular focus on applications such as hydrogen leak detection and transformer oil aging assessment. Key aging indicators derived from spectral data are systematically evaluated to establish a robust basis for condition monitoring. The paper also identifies prevailing challenges in the field, including spectral data scarcity, limited model interpretability, and poor generalization across different operational scenarios. Future research directions emphasize the construction of large-scale, annotated spectral databases, the development of multimodal data fusion frameworks, and the optimization of lightweight algorithms for practical, real-time deployment. Ultimately, this work aims to provide a clear roadmap for implementing predictive maintenance paradigms, thereby contributing to safer, more reliable, and more efficient industrial operations. Full article

Understanding the spatial and temporal structure of crustal deformation is essential for identifying tectonic blocks, assessing seismic hazard, and detecting precursory deformation associated with major megathrust earthquakes. In this study, we analyze twenty years of continuous GNSS observations from the Japanese Islands to identify coherent deformation domains and anomalous regions using an integrated time-dependent clustering framework. The workflow combines six machine learning algorithms (Hierarchical Agglomerative Clustering, K-means, Gaussian Mixture Models, Spectral Clustering, HDBSCAN and consensus clustering) and constructs a set of deformation-related features including steady-state velocities, strain rates, co-seismic and post-seismic displacements, and spatial distance metrics. Optimal cluster numbers are determined by validity metrics, and the most robust segmentation is obtained using a consensus approach. The resulting spatiotemporal domains reveal clear segmentation associated with major geological structures such as the Fossa Magna graben, the Median Tectonic Line, and deformation belts related to Pacific Plate subduction. The method also highlights deformation patterns potentially associated with the preparation stages of megathrust earthquakes. Our results demonstrate that machine learning-based clustering of long-term GNSS time series provides a powerful data-driven tool for quantifying deformation heterogeneity and improving the understanding of active geodynamic processes in subduction zones. Full article

Accurately forecasting the operating temperature of lithium-ion batteries (LIBs) is essential for preventing thermal runaway, extending service life, and ensuring the safe operation of electric vehicles and stationary energy-storage systems. This work introduces a unified, physics-informed, and data-driven temperature-prediction framework that integrates mathematically governed preprocessing, electrothermal decomposition, and sequential deep learning architectures. The methodology systematically applies the governing relations to convert raw temperature measurements into trend, seasonal, and residual components, thereby isolating long-term thermal accumulation, reversible entropy-driven oscillations, and irreversible resistive heating. These physically interpretable signatures serve as structured inputs to machine learning and deep learning models trained on temporally segmented temperature sequences. Among all evaluated predictors, the Bidirectional Long Short-Term Memory (BiLSTM) network achieved the highest prediction fidelity, yielding an RMSE of 0.018 °C, a 35.7% improvement over the conventional Long Short-Term Memory (LSTM) (RMSE = 0.028 °C) due to its ability to simultaneously encode forward and backward temporal dependencies inherent in cyclic electrochemical operation. While CatBoost exhibited the strongest performance among classical regressors (RMSE = 0.022 °C), outperforming Random Forest, Gradient Boosting, Support Vector Regression, XGBoost, and LightGBM, it remained inferior to BiLSTM because it lacks the capacity to represent bidirectional electrothermal dynamics. This performance hierarchy confirms that LIB thermal evolution is not dictated solely by historical load sequences; it also depends on forthcoming cycling patterns and entropic interactions, which unidirectional and memoryless models cannot capture. The resulting hybrid physics-data-driven framework provides a reliable surrogate for real-time LIB thermal estimation and can be directly embedded within BMS to enable proactive intervention strategies such as predictive cooling activation, current derating, and early detection of hazardous thermal conditions. By coupling physics-based decomposition with deep sequential learning, this study establishes a validated foundation for next-generation LIB thermal-management platforms and identifies a clear trajectory for future work extending the methodology to module- and pack-level systems suitable for industrial deployment. Full article

In recent years, video-based monitoring systems have been widely adopted across multiple domains and have become particularly vital in geohazard monitoring and early warning. These systems overcome the inherent limitations of conventional monitoring techniques by enabling real-time, non-contact, and intuitive visual observation of geologically hazardous sites. With the integration of machine learning and other advanced analytical methods, video-based systems can process and interpret image data in real time, thereby supporting rapid detection and timely early warning of potential geohazards. This substantially improves both the efficiency and accuracy of monitoring efforts. Drawing on domestic and international research, this article provides a comprehensive review of video-based monitoring technologies, machine learning–driven video image processing, and multi-source data fusion approaches. It systematically summarizes their underlying technical principles and applications in geohazard monitoring and early warning, and offers an in-depth analysis of their practical advantages and future development trends. This review aims to serve as a valuable reference for advancing research and innovation in this field. Full article

Rapid and accurate landslide detection is important for minimizing loss of life and property. Supervised machine learning has shown promise for automating landslide mapping, but it often requires thousands of labeled instances, which is impractical for timely emergency responses. Margin sampling active learning (MS) has proven effective for rapid landslide mapping by querying the most “informative” instances. However, it is still unclear how the choice of the landslide modeling algorithm influences the effectiveness of MS. This study assessed MS with four common landslide modeling algorithms, i.e., random forest, support vector machine, a generalized additive model, and an artificial neural network, using an open-source landslide inventory from Iburi, Japan. The results showed that all four combinations obtained > 0.90 the area under the ROC curve (AUROC) with 150 to 400 training instances. In particular, MS integrated with random forest performed best overall, with a mean AUROC of 0.91 and correct delineation of about 60 percent of the mapped landslide area using only 150 training instances. Precision-recall analysis within the ranked susceptibility maps showed that MS integrated with random forest and support vector machine generally outperformed the generalized additive model and artificial neural network. In addition, we developed a graphical user interface using R Shiny that integrates the MS active learning workflow with all four modeling options. Overall, these findings advance machine learning in rapid hazard mapping and provide tools to support decision-makers in emergency response. Full article