Search Results (127)

While space weather indices (e.g., F10.7, Dst index) are commonly employed to characterize ionospheric activity levels, the Global Mean Electron Content (GMEC) provides a more direct and comprehensive indicator of the global ionospheric state. This metric demonstrates greater potential than space weather indices for calibrating empirical ionospheric models such as IRI-2020. The COSMIC-2 constellation enables continuous, all-weather global ionospheric monitoring via radio occultation, unimpeded by land–sea distribution constraints, with over 8000 daily occultation events suitable for GMEC modeling. This study developed two lightweight GMEC models using COSMIC-2 data: (1) a POD GMEC model based on slant TEC (STEC) extracted from Level 1b podTc2 products and (2) a PROF GMEC model derived from vertical TEC (VTEC) calculated from electron density profiles (EDPs) in Level 2 ionPrf products. Both backpropagation neural network (BPNN)-based models generate hourly GMEC outputs as global spatial averages. Critically, GMEC serves as an essential intermediate step that addresses the challenges of utilizing spatially irregular occultation data by compressing COSMIC-2’s ionospheric information into an integrated metric. Building on this compressed representation, we implemented a convolutional neural network (CNN) that incorporates GMEC as an auxiliary feature to calibrate IRI-2020’s global ionospheric maps. This approach enables computationally efficient correction of systemic IRI TEC errors. Experimental results demonstrate (i) 48.5% higher accuracy in POD/PROF GMEC relative to IRI-2020 GMEC estimates, and (ii) the calibrated global IRI TEC model (designated GCIRI TEC) reduces errors by 50.15% during geomagnetically quiet periods and 28.5% during geomagnetic storms compared to the original IRI model. Full article

Over the past decade, the field of object detection has advanced remarkably, especially in the accurate recognition of medium- and large-sized objects. Nevertheless, detecting small objects is still difficult because their low-resolution appearance provides insufficient discriminative features, and they often suffer severe occlusions, particularly in the safety-critical context of autonomous driving. Conventional detectors often fail to extract sufficient information from shallow feature maps, which limits their ability to detect small objects with high precision. To address this issue, we propose the ECAN-Detector, an efficient context-aggregation method designed to enrich the feature representation of shallow layers, which are particularly beneficial for small-object detection. The model first employs an additional shallow detection layer to extract high-resolution features that provide more detailed information for subsequent stages of the network, and then incorporates a dynamic scaled transformer (DST) that enriches spatial perception by adaptively fusing global semantics and local context. Concurrently, a context-augmentation module (CAM) embedded in the shallow layer complements both global and local features relevant to small objects. To further boost the average precision of small-object detection, we implement a faster method utilizing two reparametrized convolutions in the detection head. Finally, extensive experiments conducted on the VisDrone2012-DET and VisDrone2021-DET datasets verified that our proposed method surpasses the baseline model, and achieved a significant improvement of 3.1% in AP and 3.5% in $A{P}_s$. Compared with recent state-of-the-art (SOTA) detectors, ECAN Detector delivers comparable accuracy yet preserves real-time throughput, reaching 54.3 FPS. Full article

Multi-source domain adaptation (MSDA) in remote sensing (RS) scene classification has recently gained significant attention in the visual recognition community. It leverages multiple well-labeled source domains to train a model capable of achieving strong generalization on the target domain with little to no labeled data from the target domain. However, the distribution shifts among multiple source domains make it more challenging to align the distributions between the target domain and all source domains concurrently. Moreover, relying solely on global alignment risks losing fine-grained information for each class, especially in the task of RS scene classification. To alleviate these issues, we present a Multi-Source Subdomain Distribution Alignment Network (MSSDANet), which introduces novel network structures and loss functions for subdomain-oriented MSDA. By adopting a two-level feature extraction strategy, this model attains better global alignment between the target domain and multiple source domains, as well as alignment at the subdomain level. First, it includes a pre-trained convolutional neural network (CNN) as a common feature extractor to fully exploit the shared invariant features across one target and multiple source domains. Secondly, a dual-domain feature extractor is used after the common feature extractor, which maps the data from each pair of target and source domains to a specific dual-domain feature space and performs subdomain alignment. Finally, a dual-domain feature classifier is employed to make predictions by averaging the outputs from multiple classifiers. Accompanied by the above network, two novel loss functions are proposed to boost the classification performance. Discriminant Semantic Transfer (DST) loss is exploited to force the model to effectively extract semantic information among target and source domain samples, while Class Correlation (CC) loss is introduced to reduce the feature confusion from different classes within the target domain. It is noteworthy that our MSSDANet is developed in an unsupervised manner for domain adaptation, indicating that no label information from the target domain is required during training. Extensive experiments on four common RS image datasets demonstrate that the proposed method achieves state-of-the-art performance for cross-domain RS scene classification. Specifically, in the dual-source and three-source settings, MSSDANet outperforms the second-best algorithm in terms of overall accuracy (OA) by 2.2% and 1.6%, respectively. Full article

High-precision total electron content (TEC) prediction can improve the accuracy of the Global Navigation Satellite System (GNSS)-based applications. The existing deep learning models for TEC prediction mainly include long short-term memory (LSTM), convolutional long short-term memory (ConvLSTM), and their variants, which contain only one temporal memory. These models may result in fuzzy prediction results due to neglecting spatial memory, as spatial memory is crucial for capturing the correlations of TEC within the TEC neighborhood. In this paper, we draw inspiration from the predictive recurrent neural network (PredRNN), which has dual memory states to construct a TEC prediction model named Multichannel ED-PredRNN. The highlights of our work include the following: (1) for the first time, a dual memory mechanism was utilized in TEC prediction, which can more fully capture the temporal and spatial features; (2) we modified the n vs. n structure of original PredRNN to an encoder–decoder structure, so as to handle the problem of unequal input and output lengths in TEC prediction; and (3) we expanded the feature channels by extending the Kp, Dst, and F10.7 to the same spatiotemporal resolution as global TEC maps, overlaying them together to form multichannel features, so as to fully utilize the influence of solar and geomagnetic activities on TEC. The proposed Multichannel ED-PredRNN was compared with COPG, ConvLSTM, and convolutional gated recurrent unit (ConvGRU) from multiple perspectives on a data set of 6 years, including comparisons at different solar activities, time periods, latitude regions, single stations, and geomagnetic storm periods. The results show that in almost all cases, the proposed Multichannel ED-PredRNN outperforms the three comparative models, indicating that it can more fully utilize temporal and spatial features to improve the accuracy of TEC prediction. Full article

Background and Objectives: Heart failure (HF) among patients with type 2 diabetes (T2DM) is linked to significant morbidity and mortality, despite the increased availability of new drug therapy. This study aims to investigate subclinical changes in patients with HF stage A (at risk for HF) and B (Pre-HF) and T2DM treated with oral semaglutide. Materials and Methods: In a prospective, observational, single-center study, 50 T2DM patients were assessed at baseline and one-year follow-up for changes in spectral Doppler, tissue Doppler, and speckle-tracking (2DST) and metabolic parameters. Results: Correlation and regression analyses identified predictors of Δ GLS. In correlation analysis, Δ GLS showed a negative correlation with Δ VAI (rho = −0.3, p = 0.02), Δ LAP (rho = −0.3, p = 0.04), Δ FPG (rho = −0.3, p = 0.009), Δ TG (rho = −0.4, p = 0.004), and Δ TyG (rho = −0.3, p = 0.02). In linear stepwise regression analysis, the most accurate model, with a p-value < 0.001, was M₃, explaining 70% of the variance in Δ GLS (adjusted R² = 0.7); this model included Δ FPG (beta −0.4, p = 0.001), Δ CRR (beta −1.3, p < 0.001), and Δ LDLc (beta 0.6, p = 0.01). Conclusions: These findings show that improved subclinical left ventricular systolic dysfunction is associated with improved glycemic control, visceral adiposity, and reduced insulin resistance, respectively, with improved lipid profiling. Full article

The temporal variations and spatial variations in the ionosphere during geomagnetic storms are exceptionally complex and drastic, significantly complicating ionospheric model construction. In this study, we present a multi-site, high-precision ionospheric vertical total electron content ($VTEC$) estimation method by constraining the $VTEC$ when the locations of ionospheric pierce points (IPPs), determined by multiple sites, are nearby. The root mean square error (RMSE) relative to the global ionospheric map (GIM) $VTEC$ is 3.22 TEC units (TECU), with a correlation coefficient of 0.98. This method enables the high-precision estimation of $VTEC$ at IPPs. Utilizing the Gauss–Markov Kalman filter data assimilation algorithm, we consider the relationship between various Dst indices and the ionospheric temporal scales, achieving a regional ionospheric total electron content $\left(TEC\right)$ Map during geomagnetic storms. This approach effectively monitors the impact of geomagnetic storms on the ionospheric total electron content $\left(TEC\right)$ and provides a more accurate representation of ionospheric changes during geomagnetic storms compared to the GIM $TEC$ Map and the International Reference Ionosphere (IRI)-2020 model. Full article

Low Earth Orbit (LEO) constellations support the transmission of various communication services and have been widely applied in fields such as global Internet access, the Internet of Things, remote sensing monitoring, and emergency communication. With the surge in traffic volume, the quality of user services has faced unprecedented challenges. Achieving accurate low Earth orbit constellation network traffic prediction can optimize resource allocation, enhance the performance of LEO constellation networks, reduce unnecessary costs in operation management, and enable the system to adapt to the development of future services. Ground networks often adopt methods such as machine learning (support vector machine, SVM) or deep learning (convolutional neural network, CNN; generative adversarial network, GAN) to predict future short- and long-term traffic information, aiming to optimize network performance and ensure service quality. However, these methods lack an understanding of the high-dynamics of LEO satellites and are not applicable to LEO constellations. Therefore, designing an intelligent traffic prediction model that can accurately predict multi-service scenarios in LEO constellations remains an unsolved challenge. In this paper, in light of the characteristics of high-dynamics and the high-frequency data streams of LEO constellation traffic, the authors propose a DST-LEO satellite-traffic prediction model (a dynamic spatio-temporal low Earth orbit satellite traffic prediction model). This model captures the implicit features among satellite nodes through multiple attention mechanism modules and processes the traffic volume and traffic connection/disconnection data of inter-satellite links via a multi-source data separation and fusion strategy, respectively. After splicing and fusing at a specific scale, the model performs prediction through the attention mechanism. The model proposed by the authors achieved a short-term prediction RMSE of 0.0028 and an MAE of 0.0018 on the Abilene dataset. For long-term prediction on the Abilene dataset, the RMSE was 0.0054 and the MAE was 0.0039. The RMSE of the short-term prediction on the dataset simulated by the internal low Earth orbit constellation business simulation system was 0.0034, and the MAE was 0.0026. For the long-term prediction, the RMSE reached 0.0029 and the MAE reached 0.0022. Compared with other time series prediction models, it decreased by 22.3% in terms of the mean squared error and 18.0% in terms of the mean absolute error. The authors validated the functions of each module within the model through ablation experiments and further analyzed the effectiveness of this model in the task of LEO constellation network traffic prediction. Full article

On 10 May 2024 at 17 h:07 UTC, the simultaneous arrival of several solar coronal mass ejections (CMEs) generated the strongest geomagnetic storm of the last twenty years, with a minimum Dst = −412 nT, usually referred to as the Mother’s Day event. On 10 October 2024, the second strongest event of solar cycle 25 appeared with a Dst = −335 nT, preceded on 8 October by an event with a Dst = −153 nT. In the present work, with measurements of the vertical total electron content and with ionosonde observations from Europe, USA, and South Korea, we show that the ionization of the upper atmosphere shortly increased at the arrival of the CME for these different events, followed by a fast decrease at all latitudes. The ionization remained very low for more than a full day. While the recovery started at the beginning of the second day after the onset for both events in October, the sudden recovery in the middle of the second day on 12 May is much more unusual. The analysis of the observations at different latitudes and longitudes shows that the causes of the ionization variations during the superstorms were mainly due to strong perturbations in the ionospheric F layer, amplified by the plasmasphere’s influence on the vertical total electron content (VTEC). The erosion of the plasmasphere during these two strong events led to a plasmapause located at exceptionally low radial distances smaller than 2 Re (Earth’s radii) in the post-midnight sector and a rotating plume in the afternoon–dusk sector clearly visible in the BSPM plasmasphere model. It took several days after the storms to recover normal ionization rates. Full article

Early life adversity (ELA) is a known risk factor for psychopathology, including stress-related anxiety and depressive disorders. The underlying mechanisms and developmental changes remain poorly understood. A likely underpinning is the impact of ELA on the development of stress response systems, including the hypothalamic–pituitary–adrenal (HPA) axis. Our group studied a translational ELA model of spontaneous infant maltreatment by the mother in rhesus macaques, where we used a cross-fostering design to randomly assign infant macaques to either Control or Maltreating (MALT) foster mothers at birth to examine the impact of adverse caregiving on the development of the HPA axis, while controlling for the confounding effects of heritable and prenatal factors. We previously reported higher levels of plasma and hair cortisol (CORT) across the first 6 postnatal months (equivalent to the first 2 years of life in humans) in the MALT than in the Control infants. Here, we followed the same cohort of infants longitudinally to assess the long-term developmental impact of this adverse experience on HPA axis function during the juvenile (12, 18 months) and late adolescent (~5 years) periods. For this, we collected measurements of diurnal CORT rhythm and glucocorticoid negative feedback using the dexamethasone suppression test (DST). At 12 months, we found higher diurnal CORT secretion in MALT females compared to Control females, and impaired negative feedback in response to the DST in both sexes in the MALT group. However, ELA group differences in the HPA axis function disappeared by 18 months and late adolescence, while sex differences in diurnal CORT rhythm emerged or became stronger. These results suggest that infant maltreatment causes dysregulation of the HPA axis during the first year of life, with HPA axis function normalizing later, during the pre-pubertal juvenile period and adolescence. This suggests that the impact of maltreatment on HPA axis function may be transient, at least if the adverse experience stops. Our findings are consistent with human evidence of recalibration/normalization of HPA axis function during adolescence in children that switch from adverse/deprived environments to supportive adoptive families. This research has broad implications regarding the biological processes that translate ELA to psychopathology during development and the pathways to resiliency. Full article

Due to the unique imaging mechanism of SAR, targets in SAR images present complex scattering characteristics. As a result, intelligent target detection in SAR images has been facing many challenges, which mainly lie in the insufficient exploitation of target characteristics, inefficient characterization of scattering features, and inadequate reliability of decision models. In this respect, we propose an intelligent target detection method based on multi-level fusion, where pixel-level, feature-level, and decision-level fusions are designed for enhancing scattering feature mining and improving the reliability of decision making. The pixel-level fusion method through the channel fusion of original images and their features after scattering feature enhancement represents an initial exploration of image fusion. Two feature-level fusion methods are conducted using respective migratable fusion blocks, namely DBAM and FDRM, presenting higher-level fusion. Decision-level fusion based on DST can not only consolidate complementary strengths in different models but also incorporate human or expert involvement in proposition for guiding effective decision making. This represents the highest-level fusion integrating results by proposition setting and statistical analysis. Experiments of different fusion methods integrating different features were conducted on typical target detection datasets. As shown in the results, the proposed method increases the mAP by 16.52%, 7.1%, and 3.19% in ship, aircraft, and vehicle target detection, demonstrating high effectiveness and robustness. Full article

In the early stages of offshore low-permeability oil field development, it is crucial to ascertain the productivity of production wells to select high-production, high-quality reservoirs, which affects the design of the development plan. Therefore, accurate evaluation of well productivity is essential. Drill Stem Testing (DST) is the only way to obtain the true productivity of offshore reservoirs, but conducting DST in offshore oilfields is extremely costly. This article introduces a novel productivity evaluation method for horizontal wells in offshore low-permeability reservoirs based on an improved theoretical model, which relieves the limitations of traditional methods. Firstly, a new horizontal well productivity evaluation theoretical model is derived, with the consideration of the effects of the threshold pressure gradient, stress sensitivity, skin factor, and formation heterogeneity on fluid flow in low-permeability reservoirs. Then, the productivity profiles are classified based on differences in the permeability distribution of horizontal well sections. Thirdly, the productivity evaluation equation is modified by calculating correction coefficients to maximize the model’s accuracy. Based on the overdetermined equation concepts and existing DST productivity data, the derived correction coefficients in this paper are x₁ = 3.3182, x₂ = 0.7720, and x₃ = 1.0327. Finally, the proposed method is successfully applied in an offshore low-permeability reservoir with nine horizontal wells, increasing the productivity evaluation accuracy from 65.80% to 96.82% compared with the traditional Production Index (PI) method. This technology provides a novel approach to evaluating the productivity of horizontal wells in offshore low-permeability reservoirs. Full article

State estimation of batteries is crucial in battery management systems (BMSs), particularly for accurately predicting the state of charge (SOC), which ensures safe and efficient battery operation. This paper proposes a joint SOC estimation method based on a fractional-order model, utilizing a multi-innovation full-tracking adaptive unscented Kalman filter (FOMIST-AUKF-EKF) combined with an extended Kalman filter (EKF) for online parameter updates. The fractional-order model more effectively represents the battery’s dynamic characteristics compared to traditional integer-order models, providing a more precise depiction of electrochemical processes and nonlinear behaviors. It offers superior modeling for long-memory effects, complex dynamics, and aging processes, enhancing adaptability to aging and nonlinear characteristics. Comparative results indicate a maximum end-voltage error reduction of 0.002 V with the fractional-order model compared to the integer-order model. The multi-innovation technology increases filter robustness against noise by incorporating multiple historical observations, while the full-tracking adaptive strategy dynamically adjusts the noise covariance matrix based on real-time data, thus enhancing estimation accuracy. Furthermore, EKF updates battery parameters (e.g., resistance and capacitance) in real time, correcting model errors and improving SOC prediction accuracy. Simulation and experimental validation show that the proposed method significantly outperforms traditional UKF-based SOC estimation techniques in accuracy, stability, and adaptability. Specifically, under varying conditions such as NEDC and DST, the method demonstrates excellent robustness and practicality, with maximum SOC estimation errors of 0.27% and 0.67%, respectively. Full article

The ability to quickly and accurately estimate the state of charge (SOC) of lithium batteries is a key function of the battery management system (BMS). To enhance the accuracy of SOC estimation for lithium batteries, we propose a method that combines the dynamic factor recursive least squares (DFFRLS) algorithm and the strong tracking H-infinity filtering (STF-HIF) algorithm. To address the issue of fixed forgetting factors in recursive least squares (RLS) that struggle to maintain both fast convergence and stability in battery parameter identification, we introduce dynamic forgetting factors. This approach adjusts the forgetting factor based on the residuals between the model’s estimated and actual values. To improve the H-infinity filtering (HIF) algorithm’s poor performance in tracking sudden state changes, we propose a combined STF-HIF algorithm, integrating HIF with strong tracking filtering (STF). Simulation experiments indicate that, compared to the HIF algorithm, the STF-HIF algorithm achieves a maximum absolute SOC estimation error (MaxAE) of 0.69%, 0.72%, and 1.22%, with mean absolute errors (MAE) of 0.27%, 0.25%, and 0.38%, and root mean square errors (RMSE) of 0.33%, 0.30%, and 0.46% under dynamic stress testing (DST), federal urban driving schedules (FUDS), and Beijing dynamic stress testing (BJDST) conditions, respectively. Full article

Electric vehicles (EVs) are becoming popular around the world. Making a lithium battery (LIB) pack with a robust battery management system (BMS) for an EV to operate under different complex environments is both a challenge and a requirement for engineers. A BMS can intelligently manage LIB systems by estimating the battery state of charge (SoC). Due to the nonlinear characteristics of LIB, influenced by factors such as the harsh environment and data corruption caused by electromagnetic interference (EMI) inside electric vehicles, SoC estimation should consider available capacity, model parameters, operating temperature and reductions in data sampling time. The widely used model-based algorithms, such as the extended Kalman filter (EKF) have limitations. Therefore, a detailed review of the balance between temperature, data sampling time, and different model-based algorithms is necessary. Firstly, a state of charge—open-circuit voltage (SoC-OCV) curve of LIB is obtained by the polynomial curve fitting (PCF) method. Secondly, a first-order RC (1-RC) equivalent circuit model (ECM) is applied to identify the battery parameters using a forgetting factor-based recursive least squares algorithm (FF-RLS), ensuring accurate internal battery parameters for the next step of SoC estimation. Thirdly, different model-based algorithms are utilized to estimate the SoC of LIB under various operating temperatures and data sampling times. Finally, the experimental data by dynamic stress test (DST) is collected at temperatures of 10 °C, 25 °C, and 40 °C, respectively, to verify and analyze the impact of operating temperature and data sampling time to provide a practical reference for the SoC estimation. Full article

Cross-domain dialogue state tracking (DST) focuses on using labeled data from source domains to train a DST model for target domains. It is of great significance for transferring a dialogue system into new domains. Most of the existing cross-domain DST models track each slot independently, which leads to poor performances caused by not considering the correlation among different slots, as well as low efficiency of training and inference. This paper, therefore, proposes a prompt-based end-to-end cross-domain DST method for efficiently tracking all slots simultaneously. A dynamic prompt template shuffle method is proposed to alleviate the bias of the slot order, and a dynamic prompt template sampling method is proposed to alleviate the bias of the slot number, respectively. The experimental results on the MultiWOZ 2.0 and MultiWOZ 2.1 datasets show that our approach consistently outperforms the state-of-the-art baselines in all target domains and improves both training and inference efficiency by at least 5 times. Full article