Search Results (2,240)

Particulate matter (PM) concentration, especially PM_2.5, is a major culprit of environmental pollution from unreasonable energy system emissions that significantly affects visibility, climate, and public health. The prediction of PM_2.5 concentration holds significant importance in the early warning and management of severe air pollution, since it enables the provision of guidance for scientific decision-making through the estimation of impending PM_2.5 concentration. However, due to diversified human activities, seasonal factors and industrial emissions, the air quality data not only show local anomalous mutability, but also global dynamic change characteristics. This hinders existing PM_2.5 prediction models from fully capturing the aforementioned characteristics, thereby deteriorating the model performance. To address these issues, this study proposes a framework integrating multi-scale temporal convolutional networks (TCNs) and a transformer network (called MSTTNet) for PM_2.5 concentration prediction. Specifically, MSTTNet uses multi-scale TCNs to capture the local correlations of meteorological and pollutant data in a fine-grained manner, while using transformers to capture the global temporal relationships. The proposed MSTTNet’s performance has been validated on various air quality benchmark datasets in the cities of China, including Beijing, Shanghai, Chengdu, and Guangzhou, by comparing to its eight compared models. Comprehensive experiments confirm that the MSTTNet model can improve the prediction performance of 2.42%, 2.17%, 2.87%, and 0.34%, respectively, with respect to four evaluation indicators (i.e., Mean Absolute Error, Root Mean Square Error, Mean Absolute Percentage Error, and R-square), relative to the optimal baseline model. These results confirm MSTTNet’s effectiveness in improving the accuracy of PM_2.5 concentration prediction. Full article

Conventional academic warning systems in higher education often rely on end-of-semester grades, which severely limits opportunities for timely intervention. To address this, our interdisciplinary study developed and validated a comprehensive socio-technical framework that integrates social-cognitive theory with learning analytics. The framework combines educational data mining with culturally responsive, personalized interventions tailored to a non-Western context. A two-phase mixed-methods design was employed: first, predictive models were built using Learning Management System (LMS) data from 2,856 students across 64 courses. Second, a quasi-experimental trial (n = 48) was conducted to evaluate intervention efficacy. Historical academic performance, attendance, and assignment submission patterns were the strongest predictors, achieving a Balanced Area Under the Curve (AUC) of 0.85. The intervention, specifically adapted to Confucian educational values, yielded remarkable results: 73% of at-risk students achieved passing grades, with a large effect size for academic improvement (Cohen’s d = 0.91). These findings empirically validate a complete prediction–intervention–evaluation cycle, demonstrating how algorithmic predictions can be effectively integrated with culturally informed human support networks. This study advances socio-technical systems theory in education by bridging computer science, psychology, and educational research. It offers an actionable model for designing ethical and effective early warning systems that balance technological innovation with human-centered pedagogical values. Full article

With the rapid advancement of artificial intelligence technology, the widespread application of deep learning in computer vision is driving the transformation of agricultural pest detection and control toward greater intelligence and precision. This paper systematically reviews the evolution of agricultural pest detection and control technologies, with a special focus on the effectiveness of deep-learning-based image recognition methods for pest identification, as well as their integrated applications in drone-based remote sensing, spectral imaging, and Internet of Things sensor systems. Through multimodal data fusion and dynamic prediction, artificial intelligence has significantly improved the response times and accuracy of pest monitoring. On the control side, the development of intelligent prediction and early-warning systems, precision pesticide-application technologies, and smart equipment has advanced the goals of eco-friendly pest management and ecological regulation. However, challenges such as high data-annotation costs, limited model generalization, and constrained computing power on edge devices remain. Moving forward, further exploration of cutting-edge approaches such as self-supervised learning, federated learning, and digital twins will be essential to build more efficient and reliable intelligent control systems, providing robust technical support for sustainable agricultural development. Full article

Seawater intrusion into coastal river systems poses increasing challenges for freshwater availability and estuarine ecosystem integrity, especially under evolving climatic and anthropogenic pressures. This study presents a multidisciplinary investigation of marine intrusion dynamics within the Magra River estuary (Northwest Italy), integrating field monitoring, isotopic tracing (δ¹⁸O; δD), and multivariate statistical modeling. Over an 18-month period, 11 fixed stations were monitored across six seasonal campaigns, yielding a comprehensive dataset of water electrical conductivity (EC) and stable isotope measurements from fresh water to salty water. EC and oxygen isotopic ratios displayed strong spatial and temporal coherence (R² = 0.99), confirming their combined effectiveness in identifying intrusion patterns. The mass-balance model based on δ¹⁸O revealed that marine water fractions exceeded 50% in the lower estuary for up to eight months annually, reaching as far as 8.5 km inland during dry periods. Complementary δD measurements provided additional insight into water origin and fractionation processes, revealing a slight excess relative to the local meteoric water line (LMWL), indicative of evaporative enrichment during anomalously warm periods. Multivariate regression models (PLS, Ridge, LASSO, and Elastic Net) identified river discharge as the primary limiting factor of intrusion, while wind intensity emerged as a key promoting variable, particularly when aligned with the valley axis. Tidal effects were marginal under standard conditions, except during anomalous events such as tidal surges. The results demonstrate that marine intrusion is governed by complex and interacting environmental drivers. Combined isotopic and machine learning approaches can offer high-resolution insights for environmental monitoring, early-warning systems, and adaptive resource management under climate-change scenarios. Full article

Rainfall-induced landslide deformation is governed by both intrinsic geological conditions and external dynamic triggers. However, many existing predictive models rely primarily on rainfall inputs, which limits their interpretability and robustness. To address these shortcomings, this study introduces a group-based data augmentation method informed by displacement curve morphology and proposes a multi-slope predictive framework that integrates static geological attributes with dynamic triggering factors. Using monitoring data from 274 sites across China, the framework was implemented with a Temporal Fusion Transformer (TFT) and benchmarked against baseline models, including SVR, XGBoost, and LSTM models. The results demonstrate that group-based augmentation enhances the stability and accuracy of predictions, while the integrated dynamic–static TFT framework delivers superior accuracy and improved interpretability. Statistical significance testing further confirms consistent performance improvements across all groups. Collectively, these findings highlight the framework’s effectiveness for short-term landslide forecasting and underscore its potential to advance early warning systems. Full article

Cyber coercion, where legitimate users are forced to perform actions under duress, poses a serious insider threat to modern organizations, especially to critical infrastructure. Traditional security controls and monitoring tools struggle to distinguish coerced actions from normal user actions. In this paper, we propose a cyber coercion detection system that analyzes a user’s activity using an integrated large language model (LLM) to evaluate contextual cues from user commands or actions and current policies and procedures. If the LLM indicates coercion, behavioral methods, such as keystroke dynamics and mouse usage patterns, and physiological signals such as heart rate are analyzed to detect stress or anomalies indicative of duress. Experimental results show that the LLM-assisted multimodal approach shows potential in detecting coercive activity with and without detected coercive communication, where multimodal biometrics assist the confidence of the LLM in cases in which it does not detect coercive communication. The proposed system may add a critical detection capability against coercion-based cyber-attacks, providing early warning signals that could inform defensive responses before damage occurs. Full article

Global Navigation Satellite System (GNSS) meteorology has emerged as a valuable tool for atmospheric monitoring, providing high-resolution, near-real-time data that can significantly improve precipitation nowcasting. This study aims to enhance short-term precipitation forecasting by integrating GNSS-derived Precipitable Water Vapor (PWV)—a key indicator of atmospheric moisture—with traditional meteorological observations. A novel two-step machine learning framework is proposed that combines a Random Forest (RF) model and a Long Short-Term Memory (LSTM) neural network. The RF model first estimates current precipitation based on PWV, surface weather parameters, and auxiliary atmospheric variables. Then, the LSTM network leverages temporal dependencies within the data to predict precipitation for the subsequent hour. This hybrid method capitalizes on the RF’s ability to model complex nonlinear relationships and the LSTM’s strength in handling time series data. The results demonstrate that the proposed approach improves forecasting accuracy, particularly during extreme weather events such as intense rainfall and thunderstorms, outperforming conventional models. By integrating GNSS meteorology with advanced machine learning techniques, this study offers a promising tool for meteorological services, early warning systems, and disaster risk management. The findings highlight the potential of GNSS-based nowcasting for real-time decision-making in weather-sensitive applications. Full article

Arthritis and arthrosis are prevalent joint diseases that cause pain and disability, and their early diagnosis is crucial for preventing irreversible damage. Conventional diagnostic methods such as X-ray, ultrasound, and MRI have limitations in early detection, prompting interest in alternative techniques. This work presents the design and clinical evaluation of a prototype device for non-invasive early diagnosis of arthritis (inflammatory joint disease) and arthrosis (osteoarthritis) using infrared thermography and deep neural networks. The portable prototype integrates a Raspberry Pi 4 microcomputer, an infrared thermal camera, and a touchscreen interface, all housed in a 3D-printed PLA enclosure. A custom Flask-based application enables two operational modes: (1) thermal image acquisition for training data collection, and (2) automated diagnosis using a pre-trained ResNet50 deep learning model. A clinical study was conducted at a university clinic in a temperature-controlled environment with 100 subjects (70% with arthritic conditions and 30% healthy). Thermal images of both hands (four images per hand) were captured for each participant, and all patients provided informed consent. The ResNet50 model was trained to classify three classes (healthy, arthritis, and arthrosis) from these images. Results show that the system can effectively distinguish healthy individuals from those with joint pathologies, achieving an overall test accuracy of approximately 64%. The model identified healthy hands with high confidence (100% sensitivity for the healthy class), but it struggled to differentiate between arthritis and arthrosis, often misclassifying one as the other. The prototype’s multiclass ROC (Receiver Operating Characteristic) analysis further showed excellent discrimination between healthy vs. diseased groups (AUC, Area Under the Curve ~1.00), but lower performance between arthrosis and arthritis classes (AUC ~0.60–0.68). Despite these challenges, the device demonstrates the feasibility of AI-assisted thermographic screening: it is completely non-invasive, radiation-free, and low-cost, providing results in real-time. In the discussion, we compare this thermography-based approach with conventional diagnostic modalities and highlight its advantages, such as early detection of physiological changes, portability, and patient comfort. While not intended to replace established methods, this technology can serve as an early warning and triage tool in clinical settings. In conclusion, the proposed prototype represents an innovative application of infrared thermography and deep learning for joint disease screening. With further improvements in classification accuracy and broader validation, such systems could significantly augment current clinical practice by enabling rapid and non-invasive early diagnosis of arthritis and arthrosis. Full article

Air quality is crucial for public health and the environment, which makes it important to both monitor and forecast the level of pollution. Polluted air, containing harmful substances such as particulate matter, nitrogen oxides, or ozone, can lead to serious respiratory and circulatory diseases, especially in people at risk. Air quality forecasting allows for early warning of smog episodes and taking actions to reduce pollutant emissions. In this article, we review air pollutant concentration forecasting methods, analyzing both classical statistical approaches and modern techniques based on artificial intelligence, including deep models, neural networks, and machine learning, as well as advanced sensing technologies. This work aims to present the current state of research and identify the most promising directions of development in air quality modeling, which can contribute to more effective health and environmental protection. According to the reviewed literature, deep learning–based models, particularly hybrid and attention-driven architectures, emerge as the most promising approaches, while persistent challenges such as data quality, interpretability, and integration of heterogeneous sensing systems define the open issues for future research. Full article

Desertification threatens the sustainability of dryland ecosystems, yet many existing monitoring frameworks rely on static maps, coarse spatial resolution, or lack temporal forecasting capacity. To address these limitations, this study introduces PyGEE-ST-MEDALUS, a novel spatiotemporal framework combining the full MEDALUS desertification model with deep learning (CNN, LSTM, DeepMLP) and machine learning (RF, XGBoost, SVM) techniques on the Google Earth Engine (GEE) platform. Applied across Tebessa Province, Algeria (2001–2028), the framework integrates MODIS and Sentinel-1/-2 data to compute four core indices—climatic, soil, vegetation, and land management quality—and create the Desertification Sensitivity Index (DSI). Unlike prior studies that focus on static or spatial-only MEDALUS implementations, PyGEE-ST-MEDALUS introduces scalable, time-series forecasting, yielding superior predictive performance (R² ≈ 0.96; RMSE < 0.03). Over 71% of the region was classified as having high to very high sensitivity, driven by declining vegetation and thermal stress. Comparative analysis confirms that this study advances the state-of-the-art by integrating interpretable AI, near-real-time satellite analytics, and full MEDALUS indicators into one cloud-based pipeline. These contributions make PyGEE-ST-MEDALUS a transferable, efficient decision-support tool for identifying degradation hotspots, supporting early warning systems, and enabling evidence-based land management in dryland regions. Full article

Pilot visual behavior safety assessment is a cross-disciplinary technology that analyzes pilots’ gaze behavior and neurocognitive responses. This paper proposes a multimodal analysis method for pilot visual behavior safety, specifically for cognitive state decoding. This method aims to achieve a quantitative and efficient assessment of pilots’ observational behavior. Addressing the subjective limitations of traditional methods, this paper proposes an observational behavior detection model that integrates facial images to achieve dynamic and quantitative analysis of observational behavior. It addresses the “Midas contact” problem of observational behavior by constructing a cognitive analysis method using multimodal signals. We propose a bidirectional long short-term memory (LSTM) network that matches physiological signal rhythmic features to address the problem of isolated features in multidimensional signals. This method captures the dynamic correlations between multiple physiological behaviors, such as prefrontal theta and chest-abdominal coordination, to decode the cognitive state of pilots’ observational behavior. Finally, the paper uses a decision-level fusion method based on an improved Dempster–Shafer (DS) evidence theory to provide a quantifiable detection strategy for aviation safety standards. This dual-dimensional quantitative assessment system of “visual behavior–neurophysiological cognition” reveals the dynamic correlations between visual behavior and cognitive state among pilots of varying experience. This method can provide a new paradigm for pilot neuroergonomics training and early warning of vestibular-visual integration disorders. Full article

The purpose of this study was to examine the role of traditional fire management practices in the general mitigation of wildfire risk in Greece. Major emphasis was placed on assessing people’s opinions about the perceived effectiveness of traditional fire management strategies that were historically and culturally employed by local communities—such as weather condition monitoring, prescribed burning, proper land use planning, and mosaic burning—in the general mitigation of wildfire risks. An online questionnaire was used to collect data from 397 environmental experts in Greece. The study shows that traditional fire control methods reduce wildfire risk. First, weather monitoring was found to be crucial to wildfire forecasting and prevention. The results showed that early warning, successful firefighting, and fire prevention depend on meteorological data. Additionally, prescribed burning was revealed to have reduced wildfire risk. Respondents accepted that they could reduce unprescribed fires, protect natural ecosystems, remove wildfire-prone areas, and regulate flame intensity. This suggests that scheduled burning in Greece may reduce wildfire damage. The study underlines the importance of including conventional fire management in the wildfire mitigation strategy of Greece. The aforementioned activities may help the environment and civilization progress by safeguarding ecosystems and reducing wildfire damage. These techniques, combined with community engagement and improved early warning systems, may help manage climate change-induced wildfires. Overall, the study contributes to wildfire management in Greece and other Mediterranean countries. The study emphasizes the need to incorporate traditional fire practices into Greece’s wildfire risk reduction strategies. Taking into account the success rates of these practices in other areas, as well as Greece’s old tradition of conducting fire, this paper stresses that further studies and policy developments be made in order to reinstate these practices in today’s wildfire management. Full article

Crimean-Congo hemorrhagic fever virus (CCHFV) is a tick-borne zoonotic pathogen of growing public health concern in southeastern Europe. This study provides the first serological evidence of CCHFV circulation in Croatia, based on testing 1473 serum samples from farm and companion animals, including sheep, horses, cattle, goats, dogs, and cats. A total of 109 samples (7.4%) tested positive for CCHFV antibodies using a commercially available enzyme-linked immunosorbent assay (ELISA) kit. The highest seroprevalence was recorded in sheep (28.3%), followed by horses (4.3%) and a single cat (0.5%), with no antibodies detected in cattle, goats, or dogs. Almost all seropositive animals originated from coastal and subcoastal Croatia, where Hyalomma ticks are present. Only two seropositive cases were detected in continental areas. Sheep samples from several farms in Zadar County showed intra-farm seropositivity rates of up to 85.7%, suggesting localised virus circulation likely influenced by vector distribution and farm-level practices. No viral ribonucleic acid (RNA) was detected by quantitative reverse transcription polymerase chain reaction (qRT-PCR), consistent with the transient nature of viremia in most animal hosts. These findings confirm the silent circulation of CCHFV in Croatia and reinforce the need for targeted, regionally adapted surveillance strategies that integrate multiple hosts and support early warning systems aligned with the One Health concept. Full article

Climate change is intensifying hydrological extremes, posing growing threats to the safety and operational reliability of embankment dams worldwide, particularly those in regions susceptible to heavy rainfall and flooding. This study evaluates the overtopping risk for Batu Dam, a critical flood mitigation and water supply structure near Kuala Lumpur, Malaysia, under future climate scenarios, with the aim of informing risk-informed dam safety strategies. Using historical hydrological data (1975–2020) and downscaled climate projections from the CMIP5 database under three Representative Concentration Pathways (RCP4.5, RCP6.0, RCP8.5), we conducted flood routing simulations and probabilistic risk assessments employing the iPRESAS software. Our results demonstrate that the annual probability of overtopping increases substantially under higher-emission scenarios, reaching up to 0.08% by the late century under RCP8.5, driven by increased frequency and intensity of extreme rainfall events. These projections highlight significant spillway capacity limitations and underscore the heightened risk of downstream consequences, including economic losses exceeding RM 200 million and potential loss of life surpassing 2900 individuals in worst-case scenarios. The findings confirm the urgent need for both structural adaptations, such as spillway expansion and crest elevation, and non-structural measures, including enhanced real-time monitoring and early warning systems. This integrated approach offers a robust and replicable framework for strengthening dam safety under evolving climate conditions. Full article

Inadequate screening of features and insufficient extraction of multi-source time-series data potentially result in insensitivity to historical noise and poor extraction of features for PM_2.5 concentration prediction models. Precipitable water vapor (PWV) data obtained from the Global Navigation Satellite System (GNSS), along with air quality and meteorological data collected in Suzhou city from February 2021 to July 2023, were employed in this study. The Spearman correlation analysis and Random Forest (RF) feature importance assessment were used to select key input features, including PWV, PM₁₀, O₃, atmospheric pressure, temperature, and wind speed. Based on RF, Long Short-Term Memory (LSTM), and Multilayer Perceptron (MLP) algorithms, four PM_2.5 concentration prediction models were developed using sliding window and fusion algorithms. Experimental results show that the root mean square error (RMSE) of the 1 h PM_2.5 concentration prediction model using the RF-LSTM fusion algorithm is 4.36 $\mathsf{\mu }\mathrm{g}/{\mathrm{m}}^3$, while its mean absolute error (MAE) and mean absolute percentage error (MAPE) values are 2.63 $\mathsf{\mu }\mathrm{g}/{\mathrm{m}}^3$ and 9.3%. Compared to the individual LSTM and MLP algorithms, the RMSE of the RF-LSTM PM_2.5 prediction model improves by 34.7% and 23.2%, respectively. Therefore, the RF-LSTM fusion algorithm significantly enhances the prediction accuracy of the 1 h PM_2.5 concentration model. As for the 2 h, 3 h, 6 h, 12 h, and 24 h PM_2.5 prediction models using the RF-LSTM fusion algorithm, their RMSEs are 5.6 $\mathsf{\mu }\mathrm{g}/{\mathrm{m}}^3$, 6.9 $\mathsf{\mu }\mathrm{g}/{\mathrm{m}}^3$, 9.9 $\mathsf{\mu }\mathrm{g}/{\mathrm{m}}^3$, 12.6 $\mathsf{\mu }\mathrm{g}/{\mathrm{m}}^3$, and 15.3 $\mathsf{\mu }\mathrm{g}/{\mathrm{m}}^3$, and their corresponding MAPEs are 13.8%, 18.3%, 28.3%, 38.2%, and 48.2%, respectively. Their prediction accuracy decreases with longer forecasting time, but they can effectively capture the fluctuation trends of future PM_2.5 concentrations. The RF-LSTM PM_2.5 prediction models are efficient and reliable for early warning systems in Suzhou city. Full article