Search Results (151)

With the exponential growth of textual data, traditional topic modeling methods based on static analysis demonstrate limited effectiveness in tracking the dynamics of thematic content. This research aims to develop a method for quantifying the dynamics of topics within text corpora using a thematic signal (TS) function that accounts for temporal changes and semantic relationships. The proposed method combines associative tokens with original lexical units to reduce thematic entropy and information noise. Approaches employed include topic modeling (LDA), vector representations of texts (TF-IDF, Word2Vec), and time series analysis. The method was tested on a corpus of news texts (5000 documents). Results demonstrated robust identification of semantically meaningful thematic clusters. An inverse relationship was observed between the level of thematic significance and semantic diversity, confirming a reduction in entropy using the proposed method. This approach allows for quantifying topic dynamics, filtering noise, and determining the optimal number of clusters. Future applications include analyzing multilingual data and integration with neural network models. The method shows potential for monitoring information flows and predicting thematic trends. Full article

As an extreme event driven by global climate change, drought poses a severe threat to terrestrial ecosystems. The Yangtze River Basin (YZRB) and Yellow River Basin (YRB) are key ecological barriers and economic zones in China, holding strategic importance for exploring the evolution of drought patterns and their ecological impacts. Using meteorological station data and Climatic Research Unit Gridded Time Series (CRU TS) data, this study analyzed the spatiotemporal characteristics of drought evolution in the YZRB and YRB from 1961 to 2021 using the standardized precipitation evapotranspiration index (SPEI) and run theory. Additionally, this study examined drought effects on ecosystem carbon sequestration (CS) at the city, county, and pixel scales. The results revealed the following: (1) the CRU data effectively captured precipitation (annual r = 0.94) and temperature (annual r = 0.95) trends in both basins, despite significantly underestimating winter temperatures, with the optimal SPEI calculation accuracy found at the monthly scale; (2) both basins experienced frequent autumn–winter droughts, with the YRB facing stronger droughts, including nine events which exceeded 10 months (the longest lasting 25 months), while the mild droughts increased in frequency and extreme intensity; and (3) the drought impacts on CS demonstrated a significant threshold effect, where the intensified drought unexpectedly enhanced CS in western regions, such as the Garzê Autonomous Prefecture in Sichuan Province and Changdu City in the Xizang Autonomous Region, but suppressed CS in the midstream and downstream plains. The CS responded positively under weak drought conditions but declined once the drought intensity surpassed the threshold. This study revealed a nonlinear relationship between drought and CS across climatic zones, thereby providing a scientific foundation for enhancing ecological resilience. Full article

This study introduces a Multiscale Dual-Attention U-Net (TS-MSDA U-Net) model for long-term time series synthesis. By integrating multiscale temporal feature extraction and dual-attention mechanisms into the U-Net backbone, the model captures complex temporal dependencies more effectively. The model was evaluated in two distinct applications. In the first, using multivariate datasets from 70 real-world electric vehicle (EV) trips, TS-MSDA U-Net achieved a mean absolute error below 1% across key parameters, including battery state of charge, voltage, acceleration, and torque—representing a two-fold improvement over the baseline TS-p2pGAN. While dual-attention modules provided only modest gains over the basic U-Net, the multiscale design enhanced overall performance. In the second application, the model was used to reconstruct high-resolution signals from low-speed analog-to-digital converter data in a prototype resonant CLLC half-bridge converter. TS-MSDA U-Net successfully learned nonlinear mappings and improved signal resolution by a factor of 36, outperforming the basic U-Net, which failed to recover essential waveform details. These results underscore the effectiveness of transformer-inspired U-Net architectures for high-fidelity multivariate time series modeling in both EV analytics and power electronics. Full article

Background/Objectives: The surgical management of trigeminal schwannomas (TSs) has evolved considerably, with increasing interest in minimally invasive approaches. We performed a meta-regression analysis to characterise temporal trends in surgical strategies for TS and to explore factors influencing outcomes. Methods: This systematic review and meta-regression followed the PRISMA 2020 guidelines. Comparative studies published in English reporting surgical treatment of TS were included. Outcomes assessed were the extent of resection (EOR), improvement or worsening of trigeminal symptoms, and postoperative complications. Meta-analyses of pooled frequencies were performed, and meta-regression analyses evaluated associations between surgical approach, tumour localization, year of publication, and outcomes. Surgical approaches were categorized as microsurgical antero-lateral (M-AL-Apr), retrosigmoid (RSA), endoscopic endonasal (EEA), and endoscopic transorbital (ETOA). Tumour localization was stratified using the Samii classification. Results: Fifteen studies (583 surgeries) were included. Endoscopic approaches accounted for 20.1% of cases, with increasing use over time (β = 0.12—p < 0.001), largely driven by transorbital access for Samii type A and C tumours. The use of M-AL-Apr declined. The pooled gross-total resection (GTR) rate was 73% (I² = 78.8%). The stratified meta-regression identified a temporal decrease in GTR for Samii type C tumours alone, while resection rates for types A, B, and D remained stable, likely reflecting the increasing proportion of anatomically complex cases in recent series Trigeminal impairment improved postoperatively in 17% (I² = 84.5%), while worsening of trigeminal symptoms was rare (β = 0.07%—I² = 0%). Complication rates were 11.6% (I² = 32.7%) but with a temporal increase (β = 0.041, p = 0.047). Tumour type was the dominant predictor of EOR, functional outcomes, and complications. Conclusions: Surgical management of TS has evolved towards minimally invasive techniques, particularly endoscopic routes, reflecting advances in technology and a focus on functional preservation. Tumour anatomy remains the key determinant of surgical outcomes, highlighting the importance of tailored, anatomy-driven surgical planning. Full article

Phenological parameters extracted from time series (TS) of spectral indices are essential to characterizing crops. However, the lack of data in the TS can affect their accuracy. The Copernicus Land Monitoring Service (CLMS) provides these parameters and their temporal quality. This paper evaluates the impact of missing vegetation index data on phenological parameters, namely, SOS, EOS, and MAX, for extensive arable crop between 2018 and 2023. The TSGenerator package was developed to download, process, and analyze the data. We used 252 images from the BIOPAR-VI module, 6 phenology parameters, and 2025 plots of barley and maize in Monegros and Zaidín, Spain. In barley, SOS and MAX showed 42.9% and 40.9% of missing data, while in maize, SOS and EOS showed 36.6% and 41.0%. The correlation between the Copernicus VPP quality parameter and the proposed one was r = 0.89 for barley and r = 0.74 for maize. This study advances the understanding of the effect of missing data on SOS, EOS, and MAX. Full article

This article presents the results of the conducted research work related to the dynamic forecasting of the difference values for the Polish Time Scale UTC(PL) for real measurement data, prepared in the form of the time series TS1 and TS2. For the presented time period (the whole year of 2024), the differences between the UTC(PL) and UTC does not exceed ±4.4 ns. The analogous differences for the interval exceeding 2 years are within the range of ±5 ns. Additionally, the obtained forecast results for the last day of forecasting in a given week are very consistent with the forecast results for the first day of the new forecasting week, which illustrates the very good quality of the forecasting and the universality of the forecasting procedure developed by the author using the GMDH-type neural network. Full article

According to the FAO, wheat, corn, and rice are staple crops that support global food security, providing 50% of the world’s dietary energy. The ability to predict accurately these key food crop agricultural commodity prices is important in stabilizing markets, supporting policymaking, and informing stakeholders’ decisions. To this aim, machine learning (ML), ensemble learning (EL), deep learning (DL), and time series methods (TS) have been increasingly used for forecasting due to the rapid development of computational power and data availability. This study presents a systematic literature review (SLR) of peer-reviewed original research articles focused on forecasting the prices of wheat, corn, and rice using machine learning (ML), deep learning (DL), ensemble learning (EL), and time series techniques. The results of the study help uncover suitable forecasting methods, such as hybrid deep learning models that consistently outperform traditional methods, and they identify important limitations in model interpretability and the use of region-specific datasets, highlighting the need for explainable and generalizable forecasting solutions. This systematic review adheres to the PRISMA 2020 reporting guidelines. Full article

The utilization of tannery sludge (TS) in construction materials not only effectively reduces pollution and resource consumption associated with waste disposal, but also promotes low carbon transformation in the building materials sector, further advancing sustainable development of green construction. This study aims to investigate the impact of sludge-based geopolymer gel on cementitious material performance, revealing the evolution mechanisms of material fluidity, setting time, hydration process, and compressive strength under the coupled effects of tannery sludge and alkali activation, thereby providing a reusable technical pathway to address the resource utilization challenges of similar special solid wastes. A series of alkali-activated composite cementitious materials (AACC) were prepared in the study by partially substituting cement with alkaline activators, TS, and fly ash (FA), through adjustments in TS–FA ratios and alkali equivalent (AE) variations. The workability, hydration process, and compressive strength evolution of AACC were systematically investigated. The experimental results indicated that as the TS content increased from 0% to 100%, the fluidity of fresh AACC decreased from 147 mm to 87 mm, while the initial and final setting times exhibited an exponential upward trend. The incorporation of TS was found to inhibit cement hydration, though this adverse effect could be mitigated by alkaline activation. Notably, 20–40% sludge dosages (SD) enhanced early-age compressive strength. Specifically, the compressive strength of the 0% TS group at 3 d age was 24.3 MPa, that of the 20% TS group was 25.9 MPa (an increase rate of 6.58%), and that of the 40% TS group was 24.5 MPa (an increase rate of 0.82%), whereas excessive additions resulted in the reduction of hydration products content and diminished later stage strength development. Furthermore, the investigation into AE effects revealed that maximum compressive strength (37.4 MPa) was achieved at 9% AE. These findings provide critical data support for realizing effective utilization of industrial solid wastes. Full article

With the advancement of deep learning, its application in financial market forecasting has become a research hotspot. This paper proposes an innovative Multi-Scale TsMixer model for predicting stock index futures in the A-share market, covering SSE50, CSI300, and CSI500. By integrating Multi-Scale time-series features across the short, medium, and long term, the model effectively captures market fluctuations and trends. Moreover, since stock index futures reflect the collective movement of their constituent stocks, we introduce a novel approach: predicting individual constituent stocks and merging their forecasts using three fusion strategies (average fusion, weighted fusion, and weighted decay fusion). Experimental results demonstrate that the weighted decay fusion method significantly improves the prediction accuracy and stability, validating the effectiveness of Multi-Scale TsMixer. Full article

To mitigate the limited accuracy of the Simplified General Perturbations 4 (SGP4) model in predicting medium-orbit satellite trajectories, we propose an enhanced methodology integrating deep learning with traditional algorithms. The developed BiLSTM-TS forecasting framework comprises a Bidirectional Long Short-Term Memory (BiLSTM) network, trend analysis module (T), and seasonal decomposition module (S). This architecture effectively captures sequential dependencies, trend variations, and periodic patterns within time series data, thereby improving prediction interpretability. In our experimental validation, we chose Beidou-2 M6 (C14), GSAT0203 (GALILEO 7), and the Global Positioning System (GPS) satellite named GPS BIIR-13 (PRN 02) as representative satellites. Satellite position data derived from conventional orbital models were input into the BiLSTM-TS framework for statistical learning to predict orbital deviations. These predicted errors were subsequently combined with SGP4 model outputs obtained through Two-Line Element set (TLE) data analysis to minimize overall trajectory inaccuracies. Using BeiDou-2 M6 (C14) as a case study, results indicated that the BiLSTM-TS implementation achieved significant error reduction; mean-squared error along the X-axis was reduced to 0.0309 km², with mean absolute error of 0.1245 km, and maximum absolute error was constrained to 0.4448 km. Full article

High-quality observational data play a crucial role in deepening the investigation of the Tibetan Plateau’s influence on the Asian climate. This study employs eight machine learning models (support vector regression (SVR), k-nearest neighbors (KNN), extreme gradient boosting (XGBoost), random forest (RF), long short-term memory (LSTM), gated recurrent unit (GRU), Transformer, and Transformer–convolutional neural network (Transformer-CNN)) to interpolate missing observational data on surface net radiation (Rn), soil surface temperature (Ts), soil water content (SWC), air temperature (Ta), relative humidity (RH), and wind speed (WS) from the QOMS observation site. The data covers the period from 1 January 2007 through to 31 December 2016. A comparative evaluation of these models shows that the Transformer-CNN model consistently outperforms the other models in terms of prediction accuracy. On the test dataset, the coefficients of determination for the interpolated results of Ta, RH, WS, SWC, Ts, and Rn were 0.97, 0.92, 0.97, 0.79, 0.93, and 0.98, respectively. Secondly, the Transformer-CNN model was then applied to generate a complete meteorological dataset for the full period. A time series analysis of this dataset reveals statistically significant trends over the past decade: air temperature (Ta) increased by 0.60 °C (p = 0.022) and soil temperature (Ts) by 1.85 °C (p = 1.37 × 10⁻⁵). Meanwhile, wind speed (WS), soil water content (SWC), and net radiation (Rn) declined by 0.42 m/s (p = 1.18 × 10⁻¹²), 1.24% (p < 0.001), and 9.21 W/m² (p = 8.81 × 10⁻⁶), respectively. Full article

Land cover dynamics play a critical role in understanding environmental changes, but accurately modeling these dynamics remains a challenge due to the complex interactions between temporal and spatial factors. In this study, we propose a novel temporal–spatial partial differential equation (TS-PDE) modeling method combining sparse regression to uncover the governing equations behind long-term satellite image time series. By integrating temporal and spatial differential terms, the TS-PDE framework captures the intricate interactivity of these factors, overcoming the limitations of traditional pixel-wise prediction methods. Our approach leverages $1\times 1$ convolutional kernels within a convolutional neural network (CNN) solver to approximate derivatives, enabling the discovery of interpretable equations that generalize across temporal–spatial domains. Using MODIS and Planet satellite data, we demonstrate the effectiveness of the TS-PDE method in predicting the value of the normalized difference vegetation index (NDVI) and interpreting the physical significance of the derived equations. The numerical results show that the model achieves good performance, with mean structural similarity index (SSIM) values exceeding 0.82, mean peak signal-to-noise ratio (PSNR) values ranging from 28.5 to 32.8, and mean mean squared error (MSE) values approximating $9\times {10}^{-4}$ for low-resolution MODIS images. For high-resolution Planet images, this study emphasizes the efficacy of TS-PDE in terms of PSNR, SSIM, and MSE metrics, with all datasets exhibiting an average SSIM value of over 0.81, an average PSNR maximum of 30.9, and an average MSE of less than 0.0042. The experimental findings demonstrate the capability of TS-PDE in deriving governing equations and providing effective predictions for the regional-scale dynamics of these time series images. The findings of this study provide potential insights into the mathematical modeling of land cover dynamics. Full article

Addressing the limitations of restricted coding capacity and material dependency in acoustic identity tags for autonomous underwater vehicles (AUVs), this study introduces a novel passive acoustic identification tag (AID) design based on multilayered elastic cylindrical shells. By developing a Normal Mode Series (NMS) analytical model and validating it through finite element method (FEM) simulations, the work elucidates how material layering strategies regulate far-field target strength (TS) and establishes a time-domain multi-peak echo-based encoding framework. Results demonstrate that optimizing material impedance contrasts achieves 99% detection success at a 3 dB signal-to-noise ratio. Jaccard similarity analysis of 3570 material combinations reveals a system-wide average recognition error rate of 0.41%, confirming robust encoding reliability. The solution enables the combinatorial expansion of coding capacity with structural layers, yielding 210, 840, and 2520 unique codes for three-, four-, and five-layer configurations, respectively. These findings validate a scalable, hull-integrated acoustic identification system that overcomes material constraints while providing high-capacity encoding for compact AUVs, significantly advancing underwater acoustic tagging technologies through physics-driven design and systematic performance validation. Full article

Rice serves as a fundamental staple food for a significant portion of the global population, and accurate monitoring of paddy rice cultivation is essential for achieving Sustainable Development Goal (SDG) 2–Zero Hunger. This study proposed two models, RiceLSTM and RiceTS, designed for the precise extraction of paddy rice areas in Hainan Island using time-series Synthetic Aperture Radar (SAR) data. The RiceLSTM model leverages a Bidirectional Long Short-Term Memory (BiLSTM) network to capture temporal variations in SAR backscatter and integrates an attention mechanism to enhance sensitivity to paddy rice phenological changes. This model achieves classification accuracies of 0.9182 and 0.9245 for early and late paddy rice, respectively. The RiceTS model extends RiceLSTM by incorporating a U-Net architecture with MobileNetV2 as its backbone, further improving the classification performance, with accuracies of 0.9656 and 0.9808 for early and late paddy rice, respectively. This enhancement highlights the model’s capability to effectively integrate both spatial and temporal features, leading to more precise paddy rice mapping. To assess the model’s generalizability, the RiceTS model was applied to map paddy rice distributions for the years 2020 and 2023. The results demonstrate strong spatial and temporal transferability, confirming the model’s adaptability across varying environmental conditions. Additionally, the extracted rice distribution patterns exhibit high consistency with statistical data, further validating the model’s effectiveness in accurately delineating paddy rice areas. This study provides a robust and reliable approach for paddy rice mapping, particularly in regions that are characterized by frequent cloud cover and heavy rainfall, where optical remote sensing is often limited. Full article

Effective monitoring and management of potato late blight (PLB) is essential for sustainable agriculture. This study describes a methodology to improve PLB identification on a large scale. The method combines unsupervised and supervised machine learning algorithms. To improve the monitoring accuracy of the PLB regression model, the study used the K-Means algorithm in conjunction with morphological operations to identify potato growth areas. Input data consisted of monthly NDVI from Sentinel-2 and VH bands from Sentinel-1 (covering the year 2021). The identification results were validated on 221 field survey samples with an F1 score of 0.95. To monitor disease severity, we compared seven machine learning models: CART decision trees (CART), Gradient Tree Boosting (GTB), Random Forest (RF), single optical data Random Forest Time series model (TS–RF), single radar data Random Forest Time series model (STS–RF), multi-source data Gradient Tree Boosting Time series model (MSTS–GTB), and multi-source data Random Forest Time series model (MSTS–RF). The MSTS–RF model was the best performer, with a validation RMSE of 20.50 and an R² of 0.71. The input data for the MSTS–RF model consisted of spectral indices (NDVI, NDWI, NDBI, etc.), radar features (VH-band and VV-band), texture features, and Sentinel-2 bands synthesized as a monthly time series from May to September 2021. The feature importance analysis highlights key features for disease identification: the NIR band (B8) for Sentinel-2, DVI, SAVI, and the VH band for Sentinel-1. Notably, the blue band data (458–523 nm) were critical during the month of May. These features are related to vegetation health and soil moisture are critical for early detection. This study presents for the first time a large-scale map of PLB distribution in China with an accuracy of 10 m and an RMSE of 26.52. The map provides valuable decision support for agricultural disease management, demonstrating the effectiveness and practical potential of the proposed method for large-scale monitoring. Full article