Search Results (687)

This study evaluates and corrects ECMWF precipitation forecasts (Set VI-ENS extended) over the confluence of Asian monsoons and westerlies, deriving a time series of correction factors for medium- and long-term hydrological forecasting. Based on a 15-year dataset (2008–2023), a dominant spatial and temporal bias pattern was identified: ~50% of the study area—in particular, the entire Tibetan Plateau—experienced overestimated precipitation, with larger relative errors in dry seasons than in wet seasons. Daily correction factors were derived using the linear scaling method and applied to distributed hydrological models for the Mekong, Salween, and Brahmaputra river basins. The results demonstrated substantial efficacy in correcting streamflow forecasts, particularly in the Brahmaputra basin at the Nuxia station, where the relative error in the total water volume over a 32-day period was reduced from 25% to 10% during the calibration period (2008–2020) and from 20% to 9% in the validation period (2021–2023). Furthermore, over 90% (calibration) and 85% (validation) of hydrological forecast events were successfully corrected at Nuxia. Comparable improvements were observed in key stations across the Salween and Mekong basins, with the combined success rates exceeding 70% and 65%, demonstrating the method’s regional robustness. Challenges remain in areas with weak linear relationships between forecasted and observed data, highlighting the need for further investigation. Full article

The Ili River Basin is characterized by complex topography and diverse climatic zones with limited in situ observations. This study evaluates the performance of six widely used precipitation datasets, CHIRPS (Climate Hazards Group InfraRed Precipitation with Station data), ERA5_Land (European Centre for Medium-Range Weather Forecasts—ECMWF Reanalysis 5_Land), GPCC (Global Precipitation Climatology Centre), IMERG (Integrated Multi-satellite Retrievals for GPM), PERSIANN (Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks), and TerraClimate, against ground-based data from 2001 to 2023. The evaluation is conducted across multiple spatial scales and temporal resolutions. At the basin scale, most datasets exhibit strong correlations with in situ observations across all temporal scales (r > 0.7), except for PERSIANN, which demonstrates a relatively weaker performance during summer and winter (r < 0.6). All datasets except ERA5_ Land show low annual and monthly bias (<5%), although larger errors are observed during summer, particularly for IMERG and PERSIANN. Dataset performance generally declines with increasing elevation. Basin-wide gridded evaluations reveal distinct spatial variations across all elevation zones, with CHIRPS showing the strongest ability to capture orographic precipitation gradients throughout the basin. All datasets correctly identified 2008 as a drought year and 2016 as a wet year, even though the magnitude and spatial resolution of the anomalies varied among them. These findings highlight the importance of selecting precipitation datasets that are suited to the complex topographic and climatic characteristics of transboundary basins. Our study provides valuable insights for improving hydrological modeling and can be used for water sustainability and flood–drought mitigation support activities in the Ili River Basin. Full article

The online coupling of aerosols and clouds and its effect on surface global horizontal irradiance (GHI) has not yet been thoroughly investigated in the Weather Research and Forecasting Model with Solar extensions (WRF-Solar), despite its potential significance for solar energy applications. This study addresses this critical gap by implementing a computationally efficient, coupled aerosol–cloud scheme and evaluating its impacts on GHI predictability. Simulations with online aerosol–cloud coupling are systematically compared to uncoupled simulations during March 2021, a period marked by two distinct pollution episodes over north China. The online coupling enhances aerosol optical depth (AOD) simulations, increasing the correlation coefficient from 0.19 to 0.51 while reducing the absolute bias from 0.54 to 0.48 and root mean square error from 0.82 to 0.72, compared to uncoupled simulations. Enhanced cloud microphysics (droplet concentration, water path) yields better cloud optical depth estimates, reducing all-sky GHI bias by 14.5% (63.5 W/m² for the uncoupled scenario and 54.3 W/m² for the coupled scenario) through improved aerosol–cloud–meteorology interactions. Notably, the simultaneous spatiotemporal improvement of both AOD and GHI suggests enhanced internal consistency in aerosol–cloud–radiation interactions, which is crucial for operational solar irradiance forecasting in pollution-prone regions. The results also highlight the practical value of incorporating online aerosol coupling in solar forecasting models. Full article

Phylogenetic diversity serves as a critical complement to traditional species diversity metrics. However, the performance variations among different computational models in simulating phylogenetic diversity within plant communities in the alpine grasslands of the Qinghai-Xizang Plateau remain insufficiently characterized. Here, we evaluated nine modeling approaches—random forest (RF), generalized boosting regression (GBR), multiple linear regression (MLR), artificial neural network (ANN), generalized linear regression (GLR), conditional inference tree (CIT), extreme gradient boosting (eXGB), support vector machine (SVM), and recursive regression tree (RRT)—for predicting three key phylogenetic diversity metrics [Faith’s phylogenetic diversity (PD), mean pairwise distance (MPD), mean nearest taxon distance (MNTD)] using climate variables and NDVImax. Our comprehensive analysis revealed distinct model performance patterns under grazing vs. fencing regimes. The eXGB algorithm demonstrated superior accuracy for fencing conditions, achieving the lowest relative bias (−0.08%) and RMSE (9.54) for MPD, along with optimal performance for MNTD (bias = 2.95%, RMSE = 44.86). Conversely, RF emerged as the most robust model for grazing scenarios, delivering the lowest bias (−1.63%) and RMSE (16.89) for MPD while maintaining strong predictive capability for MNTD (bias = −1.09%, RMSE = 27.59). Notably, scatterplot analysis revealed that only RF, GBR, and eXGB maintained symmetrical distributions along the 1:1 line, while other models showed problematic one-to-many value mappings or asymmetric patterns. These findings show that machine learning (especially RF and eXGB) enhances phylogenetic diversity predictions by integrating climate and NDVI data, though model performance varies by metric and management context. This study offers a framework for ecological forecasting, emphasizing multi-metric validation in biodiversity modeling. Full article

The acquisition of high-precision spatiotemporal precipitation data with long-term continuity plays an irreplaceable role in supporting agricultural modeling, hydrological forecasting, disaster prevention, and climate research. This study evaluates and corrects daily precipitation from satellite products (GPM, PERSIANN-CDR, CMORPH, GSMaP), merged datasets (GPCP, MSWEP, CHIRPS), and reanalysis products (ERA5, GLDAS) over the Huang-Huai-Hai Plain from 2000 to 2020. The study proposes a two-stage “error correction and residual correction” optimization framework. The error correction stage integrates machine learning with statistical methods (RF-DQDM), while the residual correction stage uses ground observations to dynamically adjust systematic biases. Results show that all corrected products outperform their original versions in spatial patterns and statistical metrics. Original precipitation data exhibit significant systematic errors modulated by topography, with eastern lowlands showing smaller errors. After correction, correlation coefficients rise above 0.8, and RMSE reductions average 60%. And product responses diverge significantly. CHIRPS improves from weakest to top performer, while model limitations constrain GLDAS enhancements. This framework establishes a transferable monsoon region optimization paradigm. This study provides a transferable bias correction framework for monsoon regions and builds a homogenized high-precision precipitation benchmark. It also recommends using CHIRPS or ERA5 for extreme rainfall analysis and MSWEP or GPCP for hydrological applications. Full article

Extremely persistent flash heavy rainfalls (EPHRs) over the Sichuan Basin in China are influenced by both multiscale weather systems and complex underlying surfaces, making it difficult to understand the favorable dynamic mechanisms and to further improve operational numerical forecasting skills. In this study, EPHRs from 2010 to 2024 are objectively identified and then classified into three categories based on the SOM method. Precipitating characteristics for each category are further investigated from the perspective of the diurnal cycle and spatial features with the use of rain-gauge-based observations. Evaluations of the ERA5 reanalysis dataset, MSWX bias-corrected meteorological product, and CMORPH satellite-based precipitation product are performed to determine their capabilities in representing precipitating characteristics of different EPHR categories at different stages. The following results are obtained. During EPHR events, CMORPH outperforms MSWX and ERA5 in capturing heavy precipitation distribution, diurnal cycles, and evolution over the central basin. Both MSWX and ERA5 miss the central precipitation core, with MSWX showing premature peaks and ERA5 generating secondary evening peaks while overestimating precipitation duration. During events influenced by small-scale weather systems, all three products exhibit minimal false alarms but show the largest errors in intensity and diurnal variation. Under certain circulation types, MSWX and ERA5 significantly underestimate precipitation development with comparable metrics, while CMORPH achieves superior accuracy in precipitation intensity and correlations, yet it underestimates nighttime precipitation occurrences in steep western terrain. This study may help to facilitate not only theoretical studies but also numerical model developments for precipitation extremes. Full article

This systematic review examines how machine learning (ML) and generative AI (GenAI) have been integrated into learning analytics (LA) in higher education (2018–2025). Following PRISMA 2020, we screened 9590 records and included 101 English-language, peer-reviewed empirical studies that applied ML or GenAI within LA contexts. Records came from 12 databases (last search 15 March 2025), and the results were synthesized via thematic clustering. ML approaches dominate LA tasks, such as engagement prediction, dropout-risk modelling, and academic-performance forecasting, whereas GenAI—mainly transformer models like GPT-4 and BERT—is emerging in real-time feedback, adaptive learning, and sentiment analysis. Studies spanned world regions. Most ML papers (n = 75) examined engagement or dropout, while GenAI papers (n = 26) focused on adaptive feedback and sentiment analysis. No formal risk-of-bias assessment was conducted due to heterogeneity. While ML methods are well-established, GenAI applications remain experimental and face challenges related to transparency, pedagogical grounding, and implementation feasibility. This review offers a comparative synthesis of paradigms and outlines future directions for responsible, inclusive, theory-informed AI use in education. Full article

The formulation of touristic policies is a time-consuming process that consists of a wide range of steps and procedures. These policies are highly dependent on the number of tourists and visitors to an area to be as effective as possible. The estimation of this number is not always easy to achieve, since there is a lack of the corresponding data (i.e., number of visitors per day). Hence, this estimation must be achieved by utilizing alternative data sources. To this end, in this paper, the authors propose a neural network architecture that is trained on waste management data to estimate the number of visitors and tourists in the highly touristic municipality of Vari-Voula-Vouliagmeni, Greece. Full article

Sepsis remains a leading global cause of mortality, with delayed recognition and empirical antibiotic overuse fueling poor outcomes and rising antimicrobial resistance. This systematic scoping review evaluates the current landscape of artificial intelligence (AI) and machine learning (ML) applications in sepsis care, focusing on early detection, personalized antibiotic management, and resistance forecasting. Literature from 2019 to 2025 was systematically reviewed following PRISMA-ScR guidelines. A total of 129 full-text articles were analyzed, with study quality assessed via the JBI and QUADAS-2 tools. AI-based models demonstrated robust predictive performance for early sepsis detection (AUROC 0.68–0.99), antibiotic stewardship, and resistance prediction. Notable tools, such as InSight and KI.SEP, leveraged multimodal clinical and biomarker data to provide actionable, real-time support and facilitate timely interventions. AI-driven platforms showed potential to reduce inappropriate antibiotic use and nephrotoxicity while optimizing outcomes. However, most models are limited by single-center data, variable interpretability, and insufficient real-world validation. Key challenges remain regarding data integration, algorithmic bias, and ethical implementation. Future research should prioritize multicenter validation, seamless integration with clinical workflows, and robust ethical frameworks to ensure safe, equitable, and effective adoption. AI and ML hold significant promise to transform sepsis management, but their clinical impact depends on transparent, validated, and user-centered deployment. Full article

Stock price forecasting remains a persistent challenge in time series analysis due to complex inter-stock relationships and dynamic textual signals such as financial news. While Graph Neural Networks (GNNs) can model relational structures, they often struggle with capturing higher-order dependencies and are sensitive to noise. Moreover, sentiment signals are typically aggregated using fixed time windows, which may introduce temporal bias. To address these issues, we propose DASF-Net (Diffusion-Aware Sentiment Fusion Network), a multimodal framework that integrates structural and textual information for robust prediction. DASF-Net leverages diffusion processes over two complementary financial graphs—one based on industry relationships, the other on fundamental indicators—to learn richer stock representations. Simultaneously, sentiment embeddings extracted from financial news using FinBERT are aggregated over an empirically optimized window to preserve temporal relevance. These modalities are fused via a multi-head attention mechanism and passed to a temporal forecasting module. DASF-Net integrates daily stock prices and news sentiment, using a 3-day sentiment aggregation window, to forecast stock prices over daily horizons (1–3 days). Experiments on 12 large-cap S&P 500 stocks over four years demonstrate that DASF-Net outperforms competitive baselines, achieving up to 91.6% relative reduction in Mean Squared Error (MSE). Results highlight the effectiveness of combining graph diffusion and sentiment-aware features for improved financial forecasting. Full article

This study evaluated the wind speed simulation performance of the Weather Research and Forecasting (WRF) model at three resolutions in Hebei Province based on wind speed data from 2022. The results show that the simulation effectiveness of the WRF model for wind speeds at different heights varies significantly under different seasons and topographic conditions. In general, the model simulates the wind speed at the high level most accurately, followed by the mid level, and the simulation of low level wind speed shows the largest bias. Increasing the model resolution significantly improves the simulation of low-level wind speed, and the 5 km resolution performs best at most stations; while for the mid-level and high-level wind speeds, increasing the resolution does not significantly improve the simulation effect, and the high-resolution simulation has a greater bias at some stations. In terms of topographic features, wind speeds are generally better simulated in mountainous areas than in the plains during spring, summer, and autumn, while the opposite is true in winter. These findings provide scientific reference for WRF model optimal resolution selection and wind resource assessment. Full article

Accurate prediction of wind speed is critical for wind power generation and bias correction serves as an effective tool to enhance the precision of climate model forecasts. This study evaluates the effectiveness of three bias correction methods—Quantile Regression at the 50th percentile (QR50), Linear Regression (LR), and Optimal Threat Score (OTS)—for improving wind speed predictions at a height of 70 m from the NCEP CFSv2 model in Shanxi Province, China. Using observational data from nine wind towers (2021–2024) and corresponding model hindcasts, we analyze systematic biases across lead times of 1–45 days. Results reveal persistent model errors: overestimation of low wind speeds (<6 m/s) and underestimation of high wind speeds (>6 m/s), with the Root Mean Square Error (RMSE) exceeding 1.5 m/s across all lead times. Among the correction methods, QR50 demonstrates the most robust performance, reducing the mean RMSE by 11% in October 2023 and 10% in February 2024. Correction efficacy improves significantly at longer lead times (>10 days) and under high RMSE conditions. These findings underscore the value of regression-based approaches in complex terrain while emphasizing the need for dynamic adjustments during extreme wind events. Full article

Battery-swapping stations (BSSs) are pivotal for supplying energy to electric heavy-duty trucks. However, their operations face challenges in accurate demand forecasting for battery-swapping and fair revenue allocation. This study proposes an optimization strategy for the economic operation of BSSs that optimizes revenue allocation and load balancing to enhance financial viability and grid stability. First, factors including geographical environment, traffic conditions, and truck characteristics are incorporated to simulate swapping behaviors, supporting the construction of an accurate demand-forecasting model. Second, an optimization problem is formulated to maximize the weighted difference between BSS revenue and squared load deviations. An economic operations strategy is proposed based on an adaptive Shapley value. It enables precise evaluation of differentiated member contributions through dynamic adjustment of bias weights in revenue allocation for a strategy that aligns with the interests of multiple stakeholders and market dynamics. Simulation results validate the superior performance of the proposed algorithm in revenue maximization, peak shaving, and valley filling. Full article

This study examines the role of AI tools in improving public communication via social media analysis. It reviews five of the top platforms—Google Cloud Natural Language, IBM Watson NLU, Hootsuite Insights, Talkwalker Analytics, and Sprout Social—to determine their accuracy in detecting sentiment, predicting trends, optimally timing content, and enhancing messaging engagement. Adopting a structured model approach and Partial Least Squares Structural Equation Modeling (PLS-SEM) via SMART PLS, this research uses 500 influencer posts from five Arab countries. The results demonstrate the impactful relationships between AI tool functions and communication outcomes: the utilization of text analysis tools significantly improved public engagement (β = 0.62, p = 0.001), trend forecasting tools improved strategic planning decisions (β = 0.74, p < 0.001), and timing optimization tools enhanced message efficacy (β = 0.59, p = 0.004). Beyond the technical dimensions, the study addresses urgent ethical considerations by outlining a five-principle ethical governance model that encourages transparency, fairness, privacy, human oversee of technologies, and institutional accountability considering data bias, algorithmic opacity, and over-reliance on automated solutions. The research adds a multidimensional framework for propelling AI into digital public communication in culturally sensitive and linguistically diverse environments and provides a blueprint for improving AI integration. Full article

Accurate wind resource assessment is essential for offshore wind energy development, particularly in nearshore sites where atmospheric stability and internal boundary layers significantly influence the horizontal wind distribution. In this study, we investigated wind estimation methods using a high-resolution, 100 m grid Weather Research and Forecasting (WRF) model and coastal onshore wind measurement data. Five estimation methods were evaluated, including a control WRF simulation without on-site measurement data (CTRL), observation nudging (NDG), two offline methods—temporal correction (TC) and the directional extrapolation method (DE)—and direct application of onshore measurement data (DA). Wind speed and direction data from four nearshore sites in Japan were used for validation. The results indicated that TC provided the most accurate wind speed estimate results with minimal bias and relatively high reproducibility of temporal variations. NDG exhibited a smaller standard deviation of bias and a slightly higher correlation with the measured time series than CTRL. DE could not reproduce temporal variations in the horizontal wind speed differences between points. These findings suggest that TC is the most effective method for assessing nearshore wind resources and is thus recommended for practical use. Full article