Search Results (3,716)

Precise monitoring of damage evolution in coal-rock mass during mining emerges as a paramount requirement for developing accurate early warning systems for coal burst hazards. However, limited research has demonstrated the integrated damage characteristics of the coal-rock mass under static and dynamic loads during longwall mining. Therefore, in this paper, two novel seismic monitoring approaches, the Seismic Cluster Index (CI) and the Number of High Ground Motions (NHGMs), are developed to study the evolution of coal-rock mass damage during longwall mining under static and dynamic loads, respectively. Two months of monitored seismic data from a burst-prone longwall are used for analysis. The results show that CI can depict coal-rock damage conditions under static load, which identifies coalescence of fractures based on seismic source sizes and inter-event distances. Ground motion intensity has a positive correlation with seismic energy. The induced dynamic disturbance to roadways can further weaken the coal-rock mass, depending on the distance from the seismic sources. High-intensity dynamic disturbances, as indicated by elevated NHGMs and accelerated increments, strongly correlate with coal-burst damage. The proposed CI and NHGMs framework evaluate coal-rock mass damage and forecasts coal burst hazards, validated by the correlation between high CI/NHGMs values and actual burst locations. Full article

Agricultural regions in humid tropical climates are often assumed to be water secure due to high annual rainfall, yet periodic drought remains a major constraint on production. This study demonstrates the application of the Normalized Difference Drought Index (NDDI) to identify drought-affected agricultural land in West Sumatera, Indonesia. Despite mean annual rainfall exceeding 3000 mm, rice yields in the Batang Anai Subdistrict declined from 5.28 t/ha in 2018 to 4.20 t/ha in 2022, suggesting an increased drought stress. A spatial analysis integrated administrative boundaries, land use maps, monthly rainfall records (2014–2023), and MOD09A1 V6 MODIS imagery. The NDDI was derived sequentially from the Normalized Difference Vegetation Index (NDVI) and the Normalized Difference Water Index (NDWI). The results show that 51.65% of agricultural land (7175 ha) exhibited average NDDI values of 0.09–0.14 over 2018–2023, with the highest drought intensity in 2022, when 4441 ha were classified as moderate drought. Land use under drought conditions was dominated by plantations (58.6%), rice fields (39.5%), and dry fields (1.9%). The NDDI method can more effectively capture localized drought impacts, making it valuable for operational drought monitoring systems. These findings highlight the vulnerability of humid tropical agricultural systems to drought and underscore the need for sustainable water management and early warning strategies based on remote sensing. Full article

Zoonotic diseases represent an important interface between socio-environmental change and public health, yet integrative assessments linking ecological and social determinants remain limited in tropical regions. This study mapped how socio-environmental drivers have shaped research patterns on zoonotic diseases in Brazil. We integrated socio-environmental data from empirical evidence with statistical modeling to evaluate temporal trends, thematic associations, and geographic distribution across six major zoonoses: leishmaniasis, Chagas disease, leptospirosis, yellow fever, Brazilian spotted fever, and hantavirus infection. Research output increased after 2010, particularly for leishmaniasis, Chagas disease, and leptospirosis, reflecting growing recognition of land-use change and socioeconomic vulnerability as key drivers of disease risk. Network analyses revealed strong thematic connections between zoonoses and land-use or socioeconomic factors, whereas climate change remained underrepresented. Spatially, research efforts were concentrated in the Amazon and Cerrado biomes, underscoring both ecological significance and persistent regional disparities in knowledge production. These findings demonstrate that Brazil’s zoonotic research landscape mirrors broader socio-environmental pressures, where deforestation, poverty, and climatic variability jointly influence disease dynamics. Strengthening geographically inclusive and environmentally informed research frameworks that integrate climate, land-use, and surveillance data will be essential to improve early-warning systems and guide sustainable, cross-sectoral public health policies. Full article

In recent years, financial statement fraud schemes have evolved to become markedly more sophisticated and concealed, thereby posing severe threats to both social stability and economic health. Traditional detection methods, which rely primarily on fragmented corporate data, exhibit significant limitations in capturing the dynamic evolution and spatial diffusion characteristics of fraudulent behaviors over time and space. To address this issue, in this study, we undertake a thorough analysis of the intrinsic nature of fraud risk from a sociotechnical systems perspective and construct a multi-level indicator system to comprehensively quantify risk elements. Furthermore, recognizing the dynamic evolution nature and propagating characteristics of fraud risk, we propose a novel financial statement fraud detection framework to capture behavior patterns in temporal and spatial dimensions. Experiments on A-share-listed companies of high-risk industries in China demonstrate that the proposed framework significantly outperforms other mainstream machine learning and deep learning techniques. In addition, we open the “black box” of the detection framework and empirically validate fraud risk patterns with respect to social–technical elements by leveraging explainable AI techniques. Practically, the proposed framework and interpretable analysis are capable of providing precise early warnings and supervision. Full article

This study presents a sociotechnical framework for mitigating ethnic violent conflicts by integrating information and communication technologies (ICTs) with community-based social capital. Drawing on longitudinal case studies from three conflict-prone regions in Kenya, Mt. Elgon, Muhoroni, and the Turkana–West Pokot borderlands, the research examines how ICT-enabled peace networks, particularly the Early Warning and Early Response System (EWERS), mobilize bonding, bridging, and linking social capital to reduce violence. The study employs a multi-phase qualitative design, combining retrospective analysis, key informant interviews, focus group discussions, action participation, and thematic coding of EWERS data collected between 2009 and 2021. This approach enabled the reconstruction of system evolution, stakeholder dynamics, and community responses across diverse socio-political contexts. Findings demonstrate that embedding ICTs within trusted social structures fosters inter-ethnic collaboration, inclusive decision-making, and trust-building. EWERS facilitated confidential reporting, timely alerts, and coordinated interventions, leading to reductions in livestock theft, improved leadership accountability, emergence of inter-ethnic business networks, and enhanced visibility and response to gender-based violence. The system’s effectiveness was amplified by faith-based legitimacy, local governance integration, and adaptive training strategies. The study argues that ICTs can become effective enablers of peace when sensitively contextualized within local norms, relationships, and community trust. Operationalizing social capital through digital infrastructure strengthens community resilience and supports inclusive, sustainale peacebuilding. These insights offer a scalable model for ICT-integrated violence mitigation in low- and middle-income countries. This is among the first studies to operationalize bonding, bridging, and linking social capital within ICT-enabled peace networks in rural African contexts. By embedding digital infrastructure into trusted community relationships, the framework offers an analytical approach that can inform inclusive violence mitigation strategies across low- and middle-income settings. While the framework demonstrates potential for scalability, its outcomes depend on contextual adaptation and cannot be assumed to replicate uniformly across all environments. Full article

This study presents a practical early-warning approach for heavy rainfall detection using the temporal dynamics of satellite-derived Cloud-Top Temperature (CTT). A rapid rise followed by a sharp fall in CTT is identified as a precursor signal of convective intensification. By quantifying the $rise-peak-fall-trough$ pattern and the $peak$-to-$trough$ amplitude ($swing$), a $\mathrm{W}\mathrm{A}\mathrm{T}\mathrm{C}\mathrm{H}$ window—representing a potential heavy-rainfall candidate period—is defined. The observed lead time between the onset of CTT decline and the subsequent radar-observed rainfall surge is calculated, while an estimated lead time is inferred from the steepness of CTT fall in the absence of a surge. Application to eight heavy rainfall events in Korea (July 2025) yielded a probability of detection (POD) of 87.5%, indicating that potential heavy rainfall could be detected approximately 1.3–8.6 h in advance. Compared with radar-based nowcasting, the CTT $\mathrm{W}\mathrm{A}\mathrm{T}\mathrm{C}\mathrm{H}$ method retained predictive skill up to 3 h before numerical model guidance became effective, suggesting that satellite-based signals can bridge the forecast gap in short-term prediction. This work demonstrates a clear methodological novelty by introducing a physical interpretable, pattern-based metric. Quantitatively, the $\mathrm{W}\mathrm{A}\mathrm{T}\mathrm{C}\mathrm{H}$ method improves early-warning capability by providing 1–3 h of additional lead time relative to radar nowcasting in rapidly evolving convective environments. Overall, this framework provides an interpretable, low-cost module suitable for operational early-warning systems and flood preparedness applications. Full article

Mine-induced surface subsidence threatens infrastructure and can trigger cascading geohazards, so accurate and computationally efficient monitoring and forecasting are essential for early warning. We integrate Persistent Scatterer InSAR (PS-InSAR) time series with a Bayesian-optimized CNN–LSTM designed for spatiotemporal prediction. The CNN extracts spatial deformation patterns, the LSTM models temporal dependence, and Bayesian optimization selects the architecture, training hyperparameters, and the most informative exogenous drivers. Groundwater level and backfilling intensity are encoded as multichannel inputs. Endpoint anchoring with affine calibration aligns the historical series and the forward projections. PS-InSAR indicates a maximum subsidence rate of 85.6 mm yr⁻¹, and the estimates are corroborated against nearby leveling benchmarks and FLAC^3D simulations. Cross-site comparisons show acceleration followed by deceleration after backfilling and groundwater recovery, which is consistent with geological engineering conditions. A symmetry-aware preprocessing step exploits axial regularities of the deformation field through mirroring augmentation and documents symmetry-breaking hotspots linked to geological heterogeneity. These choices improve generalization to shifted and oscillatory patterns in both the spatial CNN and the temporal LSTM branches. Short-term forecasts from the BO–CNN–LSTM indicate subsequent stabilization with localized rebound, highlighting its practical value for operational planning and risk mitigation. The framework combines automated hyperparameter search with physically consistent objectives, reduces manual tuning, enhances reproducibility and generalizability, and provides a transferable quantitative workflow for forecasting mine-induced deformation in complex goaf systems. Full article

Extreme heat disrupts labour, infrastructure, and health systems, yet most response frameworks intervene after clinical impact is confirmed. This review analyzes documented cases across sectors and regions to determine where heat effects are first detected and why intervention timing varies. The analysis used institutional reports, epidemiological summaries and occupational data to map how early functional signals appear across systems. A conceptual matrix is proposed to permit action to be authorized at the earliest sign of functional stress, using mortality, productivity, service instability, vulnerability, and adaptive capacity as operational inputs rather than retrospective outcomes. The analysis suggests that heat becomes observable first through reduced work capacity or infrastructure strain, not through hospital data, and that systems with predefined activation criteria engage earlier and with less irreversible loss. The matrix provides a transferable basis for integrating occupational, infrastructural, and clinical information into a unified heat response mechanism. This approach supports a transition from post-impact validation to forward-based decision logic, particularly in settings where vulnerable workers remain outside formal surveillance. Full article

This study assessed the effectiveness of vegetation index change metrics (ΔVI = Post − Pre) derived from Sentinel-2 imagery for detecting landslide-affected areas and evaluating their relationship with rainfall intensity, thereby enhancing the early-warning potential. The analysis focused on Sancheong-gun, Gyeongsangnam-do, South Korea, where intense rainfall in July 2025 triggered multiple landslides. Pre- and post-event Sentinel-2 Level-2A images (10 m spatial resolution) were used to compute changes in the Normalized Difference Vegetation Index (ΔNDVI), Soil-Adjusted Vegetation Index (ΔSAVI), Modified Soil-Adjusted Vegetation Index (ΔMSAVI), Normalized Difference Moisture Index (ΔNDMI), and Global Vegetation Moisture Index (ΔGVMI) over the landslide-affected post-disaster (PD) and non-damaged (ND) areas. Sensitivity was assessed based on the differences in mean ΔVI between the PD and ND areas, Welch’s t-statistics, and Cohen’s d values. All indices exhibited significant differences between the PD and ND areas (p < 0.001), with ΔMSAVI showing the highest sensitivity (MSAVI > GVMI ≈ SAVI > NDVI > NDMI). Correlation analysis revealed that ΔMSAVI had the strongest positive association with rainfall accumulation (72 h: r = 0.54; 7 days: r = 0.49), indicating that greater rainfall corresponded to stronger vegetation degradation signals. These findings highlight ΔMSAVI as a robust and responsive indicator of rainfall-triggered landslides, supporting its integration into satellite-based early-warning and rapid damage detection systems for improved landslide monitoring and response. Full article

The year 2024 has been recorded as the warmest year on record, with global temperatures temporarily exceeding the 1.5 °C threshold owing to rising anthropogenic greenhouse gas emissions. This has intensified global attention on heatwaves, which are a major public health threat linked to increased morbidity and mortality rates. This study conducted a bibliometric analysis of 901 Web of Science-indexed journal articles (2004–2024) using the term “heat wave health.” The findings revealed a significant increase in global temperatures, with an increasing frequency, intensity, and duration of extreme heat events. Heatwaves have been linked to higher rates of injuries, mental health disorders, and mortality, particularly in urban areas, due to ozone pollution, atmospheric contaminants, and the urban heat island effect, leading to increased emergency hospitalisation. Rural populations, especially outdoor labourers, face occupational heat stress and a higher risk of fatality. Adaptation measures, including early warning systems, heat indices, air conditioning, white and green roofs, and urban cooling strategies, offer some mitigation but are inadequate in the long term. Significant knowledge gaps persist regarding regional vulnerabilities, adaptation effectiveness, and socio-economic disparities, underscoring the urgent need for interdisciplinary research to inform heat-resilient public health policies and climate adaptation strategies. This study highlights the urgent need for further interdisciplinary research and targeted policy interventions to enhance heatwave resilience, particularly in under-researched and highly vulnerable regions of the world. Full article

With the rapid development of industries such as construction and port hoisting, the operational safety of truck cranes in crowded areas has become a critical issue. Under complex working conditions, traditional monitoring methods are often plagued by issues such as compromised image quality, increased parallax computation errors, delayed fence response times, and inadequate accuracy in dynamic target recognition. To address these challenges, this study proposes a personnel intrusion detection system based on multimodal sensor fusion and dynamic prediction. The system utilizes the combined application of a binocular camera and a lidar, integrates the spatiotemporal attention mechanism and an improved LSTM network to predict the movement trajectory of the crane boom in real time, and generates a dynamic 3D fence with an advance margin. It classifies intrusion risks by matching the spatiotemporal prediction of pedestrian trajectories with the fence boundaries, and finally generates early warning information. The experimental results show that this method can significantly improve the detection accuracy of personnel intrusion under complex environments such as rain, fog, and strong light. This system provides a feasible solution for the safety monitoring of truck crane operations and significantly enhances operational safety. Full article

Stress detection is an effective way to prevent pipeline failure, but stress recognition alone can hardly meet the safety and maintenance requirements of pipelines. Rather, improving the accuracy of stress detection and quantification has long been a top priority in the engineering sector. In the present study, stress detection models for pipelines were developed under varying magnetic excitation intensities, and the influence of a changing magnetic excitation field on stress recognition capacity was investigated. The variation law of the accuracy of stress detection under different excitation intensities was determined and validated experimentally. The results showed that at an excitation intensity of 2.5 of kA/m, the polarity of weak magnetic signals flipped when used to detect stress below 40 MPa, making the stress quantification difficult. The stress recognition capacity was the greatest under an excitation intensity of 7.5 kA/m for the stress below 40 MPa and the greatest under an excitation intensity of 5 kA/m for the stress of 40–160 MPa. Our research findings offer theoretical clues for choosing an appropriate excitation intensity for stress detection. The findings provide technical support for pipeline integrity assessment and risk warning, playing an important role in ensuring the safe operation of oil and gas transportation systems. Full article

Harmful Algal Blooms (HABs) in large river systems present significant challenges for water quality monitoring, with traditional in-situ sampling methods limited by spatial and temporal coverage. This study evaluates the effectiveness of machine learning techniques applied to Landsat spectral data for detecting and quantifying HABs in the Ohio River system, with particular focus on the unprecedented 2015 bloom event. Our methodology combines Google Earth Engine (GEE) for satellite data processing with an ensemble machine learning approach incorporating Support Vector Regression (SVR), Neural Networks (NN), and Extreme Gradient Boosting (XGB). Analysis of Landsat 7 and 8 data revealed that the 2015 HAB event had both broader spatial extent (636.5 river miles) and earlier onset (5–7 days) than detected through conventional monitoring. The ensemble model achieved a correlation coefficient of 0.85 with ground-truth measurements and demonstrated robust performance in detecting varying bloom intensities (R² = 0.82). Field validation using ORSANCO monitoring stations confirmed the model’s reliability (Nash-Sutcliffe Efficiency = 0.82). The integration of multispectral indices, particularly the Floating Algae Index (FAI) and Normalized Difference Chlorophyll Index (NDCI), enhanced detection accuracy by 23% compared to single-index approaches. The GEE-based framework enables near real-time processing and automated alert generation, making it suitable for operational deployment in water management systems. These findings demonstrate the potential for satellite-based HAB monitoring to complement existing ground-based systems and establish a foundation for improved early warning capabilities in large river systems through the integration of remote sensing and machine learning techniques. Full article

In order to address challenges in small object recognition for remote sensing imagery—including high model complexity, overfitting with small samples, and insufficient cross-scenario generalization—this study proposes CAGM-Seg, a lightweight recognition model integrating multi-attention mechanisms. The model systematically enhances the U-Net architecture: First, the encoder adopts a pre-trained MobileNetV3-Large as the backbone network, incorporating a coordinate attention mechanism to strengthen spatial localization of min targets. Second, an attention gating module is introduced in skip connections to achieve adaptive fusion of cross-level features. Finally, the decoder fully employs depthwise separable convolutions to significantly reduce model parameters. This design embodies a symmetry-aware philosophy, which is reflected in two aspects: the structural symmetry between the encoder and decoder facilitates multi-scale feature fusion, while the coordinate attention mechanism performs symmetric decomposition of spatial context (i.e., along height and width directions) to enhance the perception of geometrically regular small targets. Regarding training strategy, a hybrid loss function combining Dice Loss and Focal Loss, coupled with the AdamW optimizer, effectively enhances the model’s sensitivity to small objects while suppressing overfitting. Experimental results on the Xingtai black and odorous water body identification task demonstrate that CAGM-Seg outperforms comparison models in key metrics including precision (97.85%), recall (98.08%), and intersection-over-union (96.01%). Specifically, its intersection-over-union surpassed SegNeXt by 11.24 percentage points and PIDNet by 8.55 percentage points; its F1 score exceeded SegFormer by 2.51 percentage points. Regarding model efficiency, CAGM-Seg features a total of 3.489 million parameters, with 517,000 trainable parameters—approximately 80% fewer than the baseline U-Net—achieving a favorable balance between recognition accuracy and computational efficiency. Further cross-task validation demonstrates the model’s robust cross-scenario adaptability: it achieves 82.77% intersection-over-union and 90.57% F1 score in landslide detection, while maintaining 87.72% precision and 86.48% F1 score in cloud detection. The main contribution of this work is the effective resolution of key challenges in few-shot remote sensing small-object recognition—notably inadequate feature extraction and limited model generalization—via the strategic integration of multi-level attention mechanisms within a lightweight architecture. The resulting model, CAGM-Seg, establishes an innovative technical framework for real-time image interpretation under edge-computing constraints, demonstrating strong potential for practical deployment in environmental monitoring and disaster early warning systems. Full article

Wildfires are a recurring dry-season hazard in northern Thailand, contributing to severe air pollution and trans-boundary haze. However, the region lacks the ground-based measurements necessary for monitoring Live Fuel Moisture Content (LFMC), a key variable influencing vegetation flammability. This study presents a preliminary framework for near-real-time (NRT) LFMC estimation using Sentinel-2 multispectral imagery. The system integrates normalized vegetation and moisture-related indices, including the Normalized Difference Vegetation Index (NDVI), the Normalized Difference Infrared Index (NDII), and the Moisture Stress Index (MSI) with an NDVI-derived evapotranspiration fraction (ETf) within a heuristic modeling approach. The workflow includes cloud and shadow masking, weekly to biweekly compositing, and pixel-wise normalization to address the persistent cloud cover and heterogeneous land surfaces. Although currently unvalidated, the LFMC estimates capture the relative spatial and temporal variations in vegetation moisture across northern Thailand during the 2024 dry season (January–April). Evergreen forests maintained higher moisture levels, whereas deciduous forests and agricultural landscapes exhibited pronounced drying from January to March. Short-lag responses to rainfall suggest modest moisture recovery following precipitation, although the relationship is influenced by additional climatic and ecological factors not represented in the heuristic model. LFMC-derived moisture classes reflect broad seasonal dryness patterns but should not be interpreted as direct fire danger indicators. This study demonstrates the feasibility of generating regional LFMC indicators in a data-scarce tropical environment and outlines a clear pathway for future calibration and validation, including field sampling, statistical optimization, and benchmarking against global LFMC products. Until validated, the proposed NRT LFMC estimation product should be used to assess relative vegetation dryness and to support the refinement and development of future operational fire management tools, including early warnings, burn-permit regulation, and resource allocation. Full article