Search Results (5,969)

Accurate and timely precipitation forecasting is critical for climate risk management, agriculture, and hydrological regulation. However, this task remains challenging due to the dynamic evolution of atmospheric systems, heterogeneous environmental factors, and frequent missing data in multi-source observations. To address these issues, we propose DAHG, a novel long-term precipitation forecasting framework based on dynamic augmented heterogeneous graphs with reinforced graph generation, contrastive representation learning, and long short-term memory (LSTM) networks. Specifically, DAHG constructs a temporal heterogeneous graph to model the complex interactions among multiple meteorological variables (e.g., precipitation, humidity, wind) and remote sensing indicators (e.g., NDVI). The forecasting task is formulated as a dynamic spatiotemporal regression problem, where predicting future precipitation values corresponds to inferring attributes of target nodes in the evolving graph sequence. To handle missing data, we present a reinforced dynamic graph generation module that leverages reinforcement learning to complete incomplete graph sequences, enhancing the consistency of long-range forecasting. Additionally, a self-supervised contrastive learning strategy is employed to extract robust representations of multi-view graph snapshots (i.e., temporally adjacent frames and stochastically augmented graph views). Finally, DAHG integrates temporal dependency through long short-term memory (LSTM) networks to capture the evolving precipitation patterns and outputs future precipitation estimations. Experimental evaluations on multiple real-world meteorological datasets show that DAHG reduces MAE by % and improves R² by .02 over state-of-the-art baselines (p < 0.01), confirming significant gains in accuracy and robustness, particularly in scenarios with partially missing observations (e.g., due to sensor outages or cloud-covered satellite readings). Full article

In dense crowds and complex electromagnetic environments of metro stations, UWB-based seamless payment suffers from limited positioning accuracy and insufficient stability. A promising solution is to incorporate the vision modality, thereby enhancing localization robustness through cross-modal trajectory alignment. Nevertheless, high similarity among passenger trajectories, modality imbalance between vision and UWB, and UWB drift in crowded conditions collectively pose substantial challenges to trajectory alignment in metro stations. To address these issues, this paper proposes a multi-modal trajectory progressive alignment algorithm under modality imbalance. Specifically, a progressive alignment mechanism is introduced, which leverages the alignment probabilities from previous time steps to exploit the temporal continuity of trajectories, thereby gradually increasing confidence in alignments while mitigating the uncertainty of individual matches. In addition, contrastive learning with the InfoNCE loss is employed to enhance the model’s ability to learn from scarce but critical positive samples and to ensure stable matching on the UWB modality. Experimental results demonstrate that the proposed method consistently outperforms baseline approaches in both off-peak and peak periods, with its matching error rate reduced by 68% compared to the baseline methods during peak periods. Full article

The integration of photovoltaic (PV) energy into the power grid requires precise forecasting due to its dependence on the variability of weather conditions. This study explores the effectiveness of neural network models for predicting PV energy generation using historical meteorological and temporal data from Austria over a two-year period. We implement and compare multiple neural machine learning approaches, including Multilayer Perceptrons (MLPs), Recurrent Neural Networks (RNNs), and Convolutional Neural Networks (CNNs), against traditional statistical models such as Decision Trees (DTs), Linear Regression (LR), and Random Forest (RF). Our methodology introduces novel data preprocessing techniques, including cyclical encoding of time features, to improve prediction accuracy. Results demonstrate that RNN models outperform other architectures in single-step forecasting, achieving a Mean Squared Error (MSE) of 0.045 and a Mean Absolute Error (MAE) of 0.0427, while CNNs prove superior for multi-step predictions. These findings highlight the potential benefits of applying predictive deep learning techniques for optimal PV energy management, contributing to grid stability and sustainability. This study systematically compares the effectiveness of traditional and deep learning models for photovoltaic energy prediction under the same data preprocessing conditions, including the cyclical encoding of temporal features that provides a continuous representation of the time frame allowing its use as an input feature. This study identifies the specific strengths of each model (RNN for single-step prediction, CNN for multi-step prediction) for Central European climates, validated on Austria’s unique meteorological dataset. Full article

Understanding the interactions among ecosystem services (ESs) and their spatiotemporal dynamics is pivotal for sustainable ecosystem management, particularly in arid regions where water scarcity imposes significant constraints. This study focuses on the Ili River Valley, a representative arid region, to investigate the evolution of ESs, their trade-offs and synergies, and the underlying driving mechanisms from a water-resource-constrained perspective. We assessed five key ESs—soil retention (SR), habitat quality (HQ), water purification (WP), carbon sequestration (CS), and water yield (WY)—utilizing multi-source remote sensing and statistical data spanning 2000 to 2020. Employing the Integrated Valuation of Ecosystem Services and Tradeoffs (InVEST) model, Spearman correlation analysis, Geographically Weighted Regression (GWR), and the Geodetector method, we conducted a comprehensive analysis at both sub-watershed and 500 m grid scales. Our findings reveal that, except for SR and WP, the remaining three ESs exhibited an overall increasing trend over the two-decade period. Trade-off relationships predominantly characterize the ESs in the Ili River Valley; however, these interactions vary temporally and across spatial scales. Natural factors, including precipitation, temperature, and soil moisture, primarily drive WY, CS, and SR, whereas anthropogenic factors significantly influence HQ and WP. Moreover, the impact of these driving factors exhibits notable differences across spatial scales. The study underscores the necessity for ES management strategies tailored to specific regional characteristics, accounting for scale-dependent variations and the dual influences of natural and human factors. Such strategies are essential for formulating region-specific conservation and restoration policies, providing a scientific foundation for sustainable development in ecologically vulnerable arid regions. Full article

Surface electromyographic (sEMG) signals result from the interaction between motor unit action potentials (MUAPs) and neural spike trains, yet how specific features of spike timing shape the sEMG spectrum is not fully understood. Using a simplified convolutional model, we simulated sEMG by combining synthetic spike trains with MUAP templates, varying firing rate, temporal jitter, and motor unit synchronization to examine their effects on spectral characteristics. Rather than addressing a particular experimental condition such as fatigue or workload, the main goal of this study is to provide a framework that clarifies how variability in neural timing and muscle properties affects the observed sEMG spectrum. We introduce extractability indices to measure how clearly neural activity appears in the spectrum. Results show that MUAPs act as spectral filters, reducing components outside their bandwidth and limiting the detection of high firing rates. Temporal jitter spreads spectral energy and blunts frequency peaks, while moderate synchronization improves spectral visibility, partially countering jitter effects. These findings offer a reference for interpreting how neural and muscular factors shape sEMG signals, supporting a more informed use of spectral analysis in both experimental and applied neuromuscular studies. Full article

Background and Objectives: While pemphigus vulgaris (PV) and bullous pemphigoid (BP) have been linked to autoimmune comorbidities, the spectrum and specificity of these associations remain uncertain. We aimed to investigate the prevalence and patterns of autoimmune diseases (AIDs) in patients with PV and BP compared with age- and sex-matched controls. Materials and Methods: We conducted a bicenter, retrospective case–control study including 287 PV patients with 1148 matched controls and 284 BP patients with 1137 matched controls. Autoimmune comorbidities were identified through medical record review, and disease-specific as well as system-level associations between PV, BP, and AIDs were assessed. Results: Overall AID prevalence was lower in PV (9.4%) and BP (8.1%) than in controls (18% and 15%, respectively; p < 0.001 and p = 0.002). PV was associated with Graves’ disease (adjusted OR: 3.16, 95% CI: 1.24–8.06), especially in females. BP was associated with Hashimoto thyroiditis (adjusted OR: 2.51, 95% CI: 1.33–4.75), particularly in males. System-level analyses revealed that cutaneous and multisystem AIDs were less frequent in both PV and BP (p < 0.001 for each and p = 0.001 for each, respectively), whereas endocrine AIDs were more frequent in BP (p = 0.038). Thyroid antibody positivity did not differ significantly between patients and controls. Limitations include retrospective design, possible overrepresentation of cutaneous AIDs in dermatology-based controls, and lack of external validation. Conclusions: Our findings suggest that PV and BP may be associated with selective, sex- and phenotype-specific autoimmune comorbidity patterns rather than a generalized autoimmune burden. Further prospective studies are needed to confirm these exploratory associations and clarify their temporal relationships. Full article

Low, small, and slow (LSS) unmanned aerial vehicles (UAVs) pose great challenges for conventional guidance methods. However, existing deep reinforcement learning (DRL)-based interception guidance law has mostly focused on simplified two-dimensional planes and requires strict initial launch scenarios (constructing collision triangles). Designing more robust guidance laws has therefore become a key research focus. In this paper, we propose a novel recurrent proximal policy optimization (RPPO)-based guidance law framework. Specifically, we first design initial launch conditions in three-dimensional space that are more applicable and realistic, without requiring to form a collision triangle at the initial launch. Then, considering the temporal continuity of the seeker’s observations, we introduce the long short-term memory (LSTM) networks into the proximal policy optimization (PPO) algorithm to extract hidden temporal information from the observation sequences, thus supporting the policy training. Finally, we propose a reward function based on velocity prediction and overload constraints. Simulation experiments show that the proposed RPPO framework achieves an interception rate of 95.3% and a miss distance of 1.2935 m under broader launch conditions. Moreover, the framework demonstrates strong generalization ability, effectively coping with unknown maneuvers of UAVs. Full article

The power system, as a critical national infrastructure, faces stealthy and persistent intrusions from Advanced Persistent Threat (APT) attacks. These attack chains span multiple stages and components, while heterogeneous data sources lack unified semantics, limiting the interpretability of current detection methods. To address this, we combine the W3C PROV-DM standard with power-specific semantics to map generic provenance data into standardized provenance graphs. On this basis, we propose a graph neural network framework that jointly models temporal dependencies and structural features. The framework constructs unified provenance graphs with snapshot partitioning, applies Functional Time Encoding (FTE) for temporal modeling, and employs a graph attention autoencoder with node masking and edge reconstruction to enhance feature representations. Through pooling, graph-level embeddings are obtained for downstream detection. Experiments on two public datasets show that our method outperforms baselines across multiple metrics and exhibits clear inter-class separability. In the context of scarce power-domain APT data, this study improves model applicability and interpretability, and it provides a practical path for provenance graph-based intelligent detection in critical infrastructure protection. Full article

Background: The assessment of emotion recognition holds growing significance in research on the brain–computer interface and human–computer interaction. Among diverse physiological signals, electroencephalography (EEG) occupies a pivotal position in affective computing due to its exceptional temporal resolution and non-invasive acquisition. However, EEG signals are inherently complex, characterized by substantial noise contamination and high variability, posing considerable challenges to accurate assessment. Methods: To tackle these challenges, we propose a Triple Attention Network (TANet), a triple-attention EEG emotion recognition framework that integrates Conformer, Convolutional Block Attention Module (CBAM), and Mutual Cross-Modal Attention (MCA). The Conformer component captures temporal feature dependencies, CBAM refines spatial channel representations, and MCA performs cross-modal fusion of differential entropy and power spectral density features. Results: We evaluated TANet on two benchmark EEG emotion datasets, DEAP and SEED. On SEED, using a subject-specific cross-validation protocol, the model reached an average accuracy of 98.51 ± 1.40%. On DEAP, we deliberately adopted a segment-level splitting paradigm—in line with influential state-of-the-art methods—to ensure a direct and fair comparison of model architecture under an identical evaluation protocol. This approach, designed specifically to assess fine-grained within-trial pattern discrimination rather than cross-subject generalization, yielded accuracies of 99.69 ± 0.15% and 99.67 ± 0.13% for the valence and arousal dimensions, respectively. Compared with existing benchmark approaches under similar evaluation protocols, TANet delivers substantially better results, underscoring the strong complementary effects of its attention mechanisms in improving EEG-based emotion recognition performance. Conclusions: This work provides both theoretical insights into multi-dimensional attention for physiological signal processing and practical guidance for developing high-performance, robust EEG emotion assessment systems. Full article

Solid tumors collectively drive the global cancer burden, with profound molecular heterogeneity demanding precision and molecularly informed management. Advances in sequencing technologies have established molecular taxonomy as a cornerstone of clinical oncology, progressively superseding traditional histopathological classifications. Sanger sequencing remains the gold standard for validating guideline mandated actionable variants. Next-generation sequencing (NGS) has revolutionized early cancer detection through liquid biopsy applications and enabled the reclassification of diagnostically challenging tumor subtypes. Emerging long-read platforms offer unique capabilities to resolve complex genomic rearrangements, structural variants, and therapy-induced epigenetic remodeling. Consequently, therapeutic strategies are shifting from organ-centric approaches to mutation-specific interventions, exemplified by non-small-cell lung cancer, where molecular stratification drives substantial improvements in treatment response. Nevertheless, temporal tumor heterogeneity, biological contamination, and computational limitations highlight the urgent need for robust, integrated verification systems. Collectively, this evolution positions sequencing as the operational backbone of adaptive precision oncology across solid tumors. Here, we synthesize our laboratory findings with the current literature to comprehensively review the diagnostic, therapeutic, and prognostic applications of first- through fourth-generation sequencing technologies and discuss future directions in this rapidly evolving field. Full article

Entropy calculation provides meaningful insight into the dynamics and complexity of temporal signals, playing a crucial role in classification tasks. These measures are able to describe intrinsic characteristics of temporal series, such as regularity, complexity or predictability. Depending on the characteristics of the signal under study, the performance of entropy as a feature for classification may vary, and not any kind of entropy calculation technique may be suitable for that specific signal. Therefore, we aim to increase entropy’s classification accuracy performance, specially in the case of Slope Entropy (SlpEn), by enhancing the information content of the patterns present in the data before calculating the entropy, with downsampling techniques. More specifically, we will be using both uniform downsampling (UDS) and non-uniform downsampling techniques. In the case of non-uniform downsapling, the technique used is known as Trace Segmentation (TS), which is a non-uniform downsampling scheme that is able to enhance the most prominent patterns present in a temporal series while discarding the less relevant ones. SlpEn is a novel method recently proposed in the field of time series entropy estimation that in general outperforms other methods in classification tasks. We will combine it both with TS or UDS. In addition, since both techniques reduce the number of samples that the entropy will be calculated on, it can significantly decrease the computation time. In this work, we apply TS or UDS to the data before calculating SlpEn to assess how downsampling can impact the behaviour of SlpEn in terms of performance and computational cost, experimenting on different kinds of datasets. In addition, we carry out a comparison between SlpEn and one of the most commonly used entropy calculation methods: Permutation Entropy (PE). Results show that both uniform and non-uniform downsampling are able to enhance the performance of both SlpEn and PE when used as the only features in classification tasks, gaining up to 13% and 22% in terms of accuracy, respectively, when using TS and up to 10% and 21% when using UDS. In addition, when downsampling to 50% of the original data, we obtain a speedup around ×2 with individual entropy calculations, while, when incorporating the downsampling algorithms into time count, speedups with UDS are between ×1.2 and ×1.7, depending on the dataset. With TS, these speedups are above ×2, while maintaining accuracy levels similar to those obtained when using the 100% of the original data. Our findings suggest that most temporal series, specially medical ones, have been measured using a sampling frequency above the optimal threshold, thus obtaining unnecessary information for classification tasks, which is then discarded when performing downsampling. Downsampling techniques are potentially beneficial to any kind of entropy calculation technique, not only those used in the paper. It is able to enhance entropy’s performance in classification tasks while reducing its computation time, thus resulting in a win-win situation. We recommend to downsample to percentages between 20% and 45% of the original data to obtain the best results in terms of accuracy in classification tasks. Full article

Based on five years of data (2017–2021) from the China National Lightning Detection Network (CNLDN), this study compares and analyzes the temporal and spatial distribution characteristics of cloud-to-ground (CG) lightning activities in the Hengduan Mountain region and its surroundings. It explores the relationship between CG lightning occurrences and altitude, topography, and various meteorological elements. Our findings reveal a stark east–west divide: high lightning density in the Sichuan Basin and the central Yungui Plateau contrasts sharply with lower densities over the eastern Tibetan Plateau and Hengduan Mountains. This geographical dichotomy extends to the diurnal cycle, where positive cloud-to-ground (PCG) lightning activities are more prevalent in the western part of the study area, while significant nocturnal activity defines the eastern basin and plateau. The study also finds that the relationship between CG lightning activities in the four sub-regions and 2 m temperature, precipitation, convective available potential energy, and Bowen ratio (the ratio of sensible heat flux to latent heat flux) exhibits similarities. Furthermore, we show that the relationship between lightning frequency and altitude is highly region-specific, with each area displaying a unique signature reflecting its underlying topography: a normal distribution over the eastern Tibetan Plateau, a bimodal pattern in the Hengduan Mountains, a sharp low-altitude peak in the Sichuan Basin, and a complex trimodal structure on the Yungui Plateau. These distinct regional patterns highlight the intricate interplay between large-scale circulation, complex terrain, and local meteorology in modulating lightning activity. Full article

Climate and climate variability conditions determine crop suitability and the agricultural potential within a climatic region. Specifically, meteorological parameters, such as precipitation and temperature, are the primary factors determining which crops can successfully grow in a particular climatic region. The objective of agroclimatic classification and zoning is to identify optimal agricultural productivity zones based on efficient use of natural resources. This study aims to develop and present an agroclimatic classification and zoning methodology using Geographic Information Systems (GIS) and advanced remote sensing data and techniques. The agroclimatic methodology is implemented in three steps: First, Water-limited Growth Environment (WLGE) zones are developed to assess water availability based on drought and aridity indices. Second, soil and land use features are evaluated alongside water adequacy to develop the non-crop specific agroclimatic zoning. Third, crop parameters are integrated with the non-crop specific agroclimatic zones to classify areas into specific crop suitability zones. The methodology is implemented in three study regions: Évora-Portalegre in Portugal, Crau in France, and Thessaly in Greece. The study reveals that inadequate rainfall in semi-arid regions constrains the viability of irrigated crops. Nonetheless, the findings show promising potential compared to existing cropping patterns in all regions. Moreover, the use of high-resolution spatial and temporal remotely sensed data via web platforms enables up-to-date and field-level agroclimatic zoning. Full article

This study provides the first integrated spatio-temporal assessment of water quality in Lakes Tonga and Oubeira, two adjacent Ramsar-designated wetlands within El Kala National Park (Algeria). The objective was to identify major pollution sources and inform targeted conservation strategies. Physico-chemical, microbiological, and heavy metal analyses were performed on water samples collected monthly over one year (September 2022–August 2023) from two sites per lake. Applying robust statistical analyses (ANOVA, Kruskal–Wallis, PCA, boxplots) and high-resolution spatial mapping, we revealed significant spatio-temporal heterogeneity and distinct pollution profiles between the two lakes. Specifically, Lake Tonga exhibited higher concentrations of organic and bacterial pollutants, likely linked to agricultural runoff and domestic discharge, while Lake Oubeira was characterized by elevated heavy metal concentrations and higher mineralization. The calculated Water Quality Index (WQI) classified the water quality of both lakes predominantly as “Moderate”, with punctual “Poor” quality episodes. Numerous parameters consistently exceeded water quality standards, indicating substantial ecological and health risks. Spatial distribution maps clearly pinpointed pollution hotspots, guiding lake-specific management measures. These findings underscore the urgent need for differentiated, targeted management interventions and an integrated, multidisciplinary approach for the effective conservation of these valuable wetland ecosystems. Full article

A sensor network based on 10 stationary nodes distributed in Bari (Southern Italy) has been deployed for urban air quality (AQ) monitoring. The low-cost sensor systems have been installed in specific sites (e.g., buildings, offices, schools, streets, ports, and airports) to enhance environmental awareness of the citizens and to supplement the expensive official air-monitoring stations with cost-effective sensor nodes at high spatial and temporal resolution. Continuous measurements were performed by low-cost electrochemical gas sensors (CO, NO₂, O₃), optical particle counter (PM₁₀), and NDIR infrared sensor (CO₂), including micro-sensors for temperature and relative humidity. The sensors are operated to assess the performance during a campaign (July 2015–December 2017) of several months for citizen science in sustainable smart cities. Typical values of CO₂, measured by distributed nodes, varied from 312 to 494 ppm (2016), and from 371 to 527 ppm (2017), depending on seasonal micro-climate change and site-specific conditions. The results of the AQ-monitoring long-term campaign for selected sensor nodes are presented with a relative error of 26.2% (PM₁₀), 21.7% (O₃), 25.5% (NO₂), and 79.4% (CO). These interesting results suggest a partial compliance, excluding CO, with Data Quality Objectives (DQO) by the European Air Quality Directive (2008/50/EC) for Indicative (Informative) Measurements. Full article