Search Results (3,952)

A globally applicable and fully automated simulation method based on satellite-derived Earth Observation (EO) data and global circulation models was developed and validated. Inputs to the simulation are DSM/DTM layers, surface roughness layer, forest canopy layer, and single-level point data from the European Centre for Medium-Range Weather Forecasts fifth-generation ECMWF reanalysis (ECMWF ERA5, a global circulation model produced by the Copernicus Climate Change Service (C3S)). High-resolution roughness length maps are produced by deep learning from optical satellite data. Velocity fields are predicted by fluid dynamics simulations in OpenFOAM using the IDDES turbulence model, a 3D resolved tree canopy implemented as isotropic momentum sinks, and a corrector step based on sub-grid-scale dynamic downscaling of ERA5 data. No calibration data from wind measurements close to the target are necessary to achieve results accurate enough for site assessments and wind park planning. The presented method is suitable for the prediction of average wind speeds and average power densities in complex terrain with high ruggedness indices for WEC (wind energy converter) installations closer to the ground and at hub heights of typical large-scale WECs. Full article

Effective management of infectious healthcare waste at the Military Medical Academy (VMA) depends on reliable forecasting in order to ensure adequate treatment capacity (e.g., sterilization facilities), optimize logistics, maintain regulatory compliance, and minimize environmental impact. However, conventional statistical approaches often struggle to capture the complex and heterogeneous patterns of waste generation observed across clinical departments with different medical specializations. The aim of this study is to develop and comparatively evaluate six models for predicting annual infectious waste generation across 24 clinical departments of the Military Medical Academy in Belgrade, Serbia. The analysis is based on an 11-year real-world panel dataset (2011–2021), which is further used to produce forecasts for the period 2022–2031. The modeling framework includes both traditional statistical methods (OLS, Ridge, and Lasso regression) and machine learning techniques (Random Forest, Gradient Boosting, and Multilayer Perceptron). Model performance is assessed using k-fold cross-validation and standard evaluation metrics (RMSE, MAE, and R²). The results indicate that machine learning models, particularly Gradient Boosting and Random Forest, achieve better predictive performance compared to traditional approaches. Although the findings are based on data from a single hospital complex, they offer a useful empirical basis for understanding and forecasting infectious healthcare waste in large, multi-department healthcare institutions. Full article

Severe and unpredictable wind conditions significantly disrupt flight safety, mission planning, and scheduling. Traditional wind forecasting methods rely on low-resolution mesoscale models or resource-intensive instrumentation. This study evaluates the accuracy of 40 m Large-Eddy Simulations (LESs), nested within a mesoscale framework, to better resolve hazardous wind phenomena over GrandSKY, North Dakota, the first large-scale commercial Uncrewed Aircraft System (UAS) test park in the United States, serving as a hub for UAS innovation and Beyond Visual Line of Sight operations. Using low-altitude airborne observations from Meteodrone flights, satellite data, and ground-based measurements, we assess the model’s accuracy in predicting wind speed and direction during both summer and winter. Results demonstrate that the 40 m LES provides improved predictions of wind gust variability compared to the 1 km forecast, and the impact on flight safety is quantified. The LES also reveals notable discrepancies in UAS flyability predictions, which result in up to a 17% reduction in operational windows during the summer. This study’s novelty lies in using a 40 m resolution LES nested within a 1 km WRF simulation, combined with multi-source observations, to resolve low-altitude turbulence and quantify its impact on UAS operations. A 10–18% correction factor can be applied to TKE (or derived wind variability) in coarser WRF runs to better estimate maximum wind speeds without LES. The findings highlight the potential of high-resolution LES modeling to support reliable UAS operations in weather-sensitive environments, laying the groundwork for broader integration of advanced simulation techniques in national airspace management systems. Full article

The accuracy of numerical weather prediction largely depends on the quality of the initial conditions. Global Navigation Satellite System radio occultation (GNSS-RO) observations, with their high vertical resolution, play an important role in reducing initial condition errors. In this study, multiple simulations with different initialization times were conducted during the development of Typhoon BEBINCA using the WRF-GSI assimilation system to evaluate the impact of YunYao GNSS-RO observations on improving extreme weather simulation performance and to investigate the sensitivity of refractivity assimilation to different cloud microphysics parameterization schemes. The results show that assimilating YunYao GNSS-RO data significantly improves the consistency between the model initial fields and observations and enhances the analysis quality in the middle and upper troposphere. Compared with ERA5 reanalysis data, the assimilation experiments better reproduce the spatial and temporal evolution of key atmospheric variables, and the improvements persist from 36 h to 120 h forecast lead time. Statistical results from multiple initializations show that the maximum RMSE reductions exceed 0.2 K for temperature, 0.1 m s⁻¹ for wind speed, and geopotential height shows consistent improvements throughout the entire atmosphere. In addition, the assimilation experiments improve the simulation of Typhoon BEBINCA’s track and intensity. Statistical results from multiple initializations indicate that the 84 h track error is reduced by approximately 30 km on average, and the minimum central pressure bias is also reduced. Sensitivity experiments further show that the WSM6 microphysics scheme performs better in track forecasting, while the Thompson scheme is more suitable for intensity forecasting. Overall, YunYao GNSS-RO assimilation effectively improves typhoon forecast accuracy and demonstrates strong potential for operational applications. Full article

Post-processing of numerical weather prediction (NWP) models constitutes a pivotal link in enhancing forecast performance. Despite their recognition as cutting-edge point-based post-processing techniques, systematic comparative evaluations of ecPoint (ECWMF for point forecasts) and Ensemble Model Output Statistics (EMOS)—particularly assessments of their applicability outside Europe and to Chinese ensemble forecasting systems—remain sparse. In this study, we evaluate two advanced post-processing techniques—EMOS and the ecPoint—for calibrating ensemble precipitation forecasts. A comprehensive assessment of the performance of these ensemble post-processing methods is conducted using the CMA-GEPS (China Meteorological Administration’s Global Ensemble Forecasting System forecast over eastern China. The results demonstrate that both methods significantly mitigate systematic biases and improve the reliability and dispersion of ensemble forecasts. Notably, improvement in forecast accuracy is observed even under convective weather conditions and early-warning capability of extreme precipitation events is improved. Overall, while both methods show comparable performance, they exhibit distinct behaviours across different regions. The ecPoint method slightly outperforms EMOS in terms of Continuous Ranked Probability Score (CRPS) and provides improved resolution and early-warning capabilities at various precipitation thresholds. Full article

We propose an exploratory framework based on Topological Digital Twins (TDTs) for the monitoring and short-term forecasting of spatial dynamical systems. The approach represents the system through a reduced state built from topological descriptors obtained via persistent homology. These descriptors capture features such as connected components, cycles, and large-scale structure. The framework combines three components: an observation operator mapping spatial fields to a low-dimensional state, a reduced dynamical model evolving this state in time, and a data assimilation step aimed at improving robustness. This construction maps persistence diagrams to a finite-dimensional Euclidean space. This makes the model tractable but does not preserve the full algebraic structure of the original topological objects. We provide theoretical results supporting the stability of the representation under perturbations of the input field. The method is illustrated on a bow-echo convective system observed over Corsica on 18 August 2022, where the reduced state captures the main structural organization of the system over time. A comparison with standard nowcasting methods shows complementary behavior: pixel-based approaches provide better local accuracy, while the TDT framework better preserves the global spatial structure, as reflected by Wasserstein distances and persistence-based comparisons. Additional tests also indicate that the topological observables remain stable under small perturbations of the input field. The present study is based on a single case and should be understood as a proof of concept, rather than as a definitive validation. Future work will focus on validation on larger datasets and on the use of more advanced dynamical models. Full article

In the period 2 to 4 March 2026, two rainstorms with intense convective weather occurred within and in the vicinity of Hong Kong, China, in the early rain season of the year in southern China. This is rather uncommon because the atmosphere is still generally stable (with very low or even zero value of convective available potential energy), and upper tropospheric divergence does not yet exist in the region climatologically. The rain episode is documented in this paper from both observational and forecasting aspects. On the observational side, a low-level vortex is found on and near the surface based on Doppler velocity measurements from a newly installed C-band solid-state weather radar. Combining the three-dimensional wind field as retrieved from the weather data and the measurements from the other ground-based remote-sensing meteorological equipment, the intense convection is mainly triggered by middle to lower tropospheric waves, and the vertical circulation in the atmospheric boundary layer may be stretched vertically upward to form the low-level vortex. In the second rainstorm, features of elevated thunderstorms are also identified. On the forecasting side, a high-resolution, limited-area atmosphere–ocean–wave coupled model manages to capture the occurrence and the timing of the heavy rain. The sub-seasonal forecast by a global model also provides a useful indication of the occurrence of above-normal rainfall over southern China, with a rather special feature of a deep and stationary westerly trough located to the north of the Indochina Peninsula. The microscale cyclone could be successfully picked up by the real-time run of a high-resolution numerical weather prediction model with data assimilation. This paper also discusses the weather service aspect of this rather unusual rainstorm episode. Full article

In power engineering, various mathematical models are used, for example, to study stability, forecasting, etc., obtained using analytical methods, machine learning, and artificial intelligence. The present authors pursue a novel direction in modeling the development of the power system as an intelligent control system using data from 1990–2024 under conditions including a growing level of renewable energy production and an increased level of electrical energy saving. As a result of the modeling carried out in the MATLAB and Simulink environment, two types of highly accurate development models were obtained: a regression machine learning ARX model and a multilayer perceptron (MLP) neural network. For the neural model, MAPE errors ranged from 0.73% to 3.37%, and the coefficient of determination R² ranged from 0.9478 to 0.9868. The accuracy of the ARX models was close to 100%. Using an ARX model converted into a state-space (SS) model, it was observed that the subsystems of conventional electricity production and renewable energy were observable and controllable. The presented methodology is modern, enabling the study of large development systems using development models in terms of control and systems theory and artificial intelligence methods. Full article

Effective operation and maintenance (O&M) of deep-sea observation networks are challenged by complex environments and energy limitations. While digital twin (DT) technology offers promising solutions, existing frameworks struggle with high-fidelity, multi-platform orchestration and predictions of electrical energy state. This study proposes a DT framework for a deep-sea observation network (DSON-DT), encompassing telemetry acquisition, predictive analytics, and feedback control to realize a closed-loop workflow for monitoring and managing platform states within virtual scenes. Powered by real-time Internet of underwater things (IoUT) data, a high-fidelity virtual environment is constructed in the Unreal Engine 5 game engine, accurately mapping ambient marine environments and reconstructing platform dynamic behaviors via data-driven approaches and geometric constraints. An improved auto-regressive long short-term memory (AR-LSTM) network is proposed to forecast the battery state of charge (SoC). Experimental results show that this algorithm effectively mitigates the impacts of severe deep-sea noise and the flat open-circuit voltage plateau, suppressing state oscillations to provide reliable references for proactive endurance management. The Vue.js-based web prototype, deployed via pixel streaming, offers seamless interfaces for interactive visualization, analysis, and remote operation. This research achieves comprehensive situational awareness for deep-sea platforms, providing validated technical support for the holistic evaluation and intelligent O&M of heterogeneous marine infrastructures. Full article

Self-contained local forecasting of wind and solar series can improve operational planning of wind farms and photovoltaic (PV) plant day-cycles in addition to numerical models, which are mostly behind time due to high simulation costs. Unstable electricity production requires balancing the availability of renewable energy (RE) with unpredictable user consumption to achieve effective usage. Artificial intelligence (AI) predictive modelling can minimise the intermittent uncertainty in wind and solar resources by trying to eliminate specific problems in RE-detached system reliability and optimal utilisation. The proposed 24 h day-training and prediction scheme comprises the starting detection and the following similarity re-assessment of sampling day-series intervals. Two-point professional weather stations record standard meteorological variables, of which the most relevant are selected as optimal model inputs. Automatic two-layer altitude observation captures key relationships between hill- and lowland-level data, which comply with pattern progress. New biologically inspired differential learning (DfL) is designed and developed to integrate adaptive neurocomputing (evolving node tree components) with customised numerical procedures of operator calculus (OC) based on derivative transforms. DfL enables the representation of uncertain dynamics related to local weather patterns. Angular and frequency data (wind azimuth, temperature, irradiation) are processed together with the amplitudes to solve simple 2-variable partial differential equations (PDEs) in binomial nodes. Differentiated data provide the fruitful information necessary to model upcoming changes in mid-term day horizons. Additional PDE components in periodic form improve the modelling of hidden complex patterns in cycle data. The DfL efficiency was proved in statistical experiments, compared to a variety of elaborated AI techniques, enhanced by selective difference input preprocessing. Successful LSTM-deep and stochastic tree learning shows little inferior model performances, notably in day-ahead estimation of chaotic 24 h wind series, and slightly better approximation of alterative 8 h solar cycles. Free parametric C++ software with the applied archive data is available for additional comparative and reproducible experiments. Full article

Liuchun Lake area, located in the high-elevation and topographically complex western region of Zhejiang Province, exhibits temperature variability strongly influenced by terrain-induced dynamics and local microclimates. The Zhejiang Operational Consensus Forecasts (ZJOCF) model shows pronounced systematic biases in this area, making it difficult to meet the demand for short-term, fine-scale forecasts in cultural-tourism applications. Using observational data from four stations at different elevations, this study analyzes how ZJOCF temperature forecast errors vary with altitude, develops a station-level machine-learning temperature bias-correction model, and evaluates its performance in terms of accuracy, mean absolute error (MAE), error distribution, and control of extreme errors. Results show that the accuracy of the raw forecasts decreases significantly with increasing elevation, with high-altitude sites exhibiting distinct warm biases and strong fluctuations. After correction, the 72 h forecast accuracy at the four stations increases to 69–71% (up to 40.8% at the mountaintop station), MAE is reduced by more than 60% on average, extreme-error cases decrease by 40–60%, and the error distribution shifts from a scattered multi-peak pattern to a concentrated single-peak structure. These findings demonstrate that station-level machine-learning correction can effectively mitigate structural errors in ZJOCF temperature forecasts over complex terrain, providing a reliable technical pathway for refined meteorological services in mountainous regions. Full article

Accurately forecasting the weighted mean temperature (Tm) is critical for converting the zenith wet delay (ZWD) into global navigation satellite system (GNSS)-based precipitable water vapor (PWV) for real-time sensing and forecasting applications. The forecast Vienna Mapping Function 1 (VMF1-FC) is a global forecast product developed by TU Wien based on numerical weather prediction models and can provide grid-wise Tm one day ahead. In this study, we evaluate the accuracy of VMF1-FC-forecasted Tm using observations from 319 global radiosonde (RS) sites during 2019–2021. The results indicate that VMF1-FC-forecasted Tm shows a relatively low RMSE but a relatively large bias (0.75 K) relative to the widely used Global Pressure and Temperature 3 (GPT3) model. To improve the accuracy of VMF1-FC-forecasted Tm, three refined models, XTm, LTm, and CTm, are developed using Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Categorical Boosting (CatBoost), respectively, based on observations from 319 RS sites. The models use longitude, latitude, ellipsoidal height, floating day of year (fdoy), and VMF1-FC Tm as input features, and RS Tm as the target variable. Validation using RS data from 2022 that are not involved in model development shows that the refined models significantly reduce bias, with biases of 0 K, 0 K, and −0.03 K for XTm, LTm, and CTm, respectively. Benefiting from the effective reduction in bias, the root mean square error (RMSE) is correspondingly reduced. The RMSEs of XTm, LTm, and CTm are 1.45 K, 1.45 K, and 1.46 K, respectively, achieving improvements of 18.50%/64.93%, 18.44%/64.91%, and 18.11%/64.76% compared with the VMF1-FC and GPT3 models. In addition, three refined models demonstrate higher accuracy and improve stability across different latitude bands, ellipsoidal height ranges, and temporal scales. The refined models provide more accurate global-scale Tm and offer strong potential for GNSS meteorological applications, particularly real-time GNSS-based PWV sensing and weather forecasting. Full article

Tropical cyclones (TCs) and the Madden–Julian Oscillation (MJO) are two of the most impactful weather systems in the tropics. For example, it is not uncommon for a strong TC to kill hundreds of people and cause tens of billions of dollars in damage. The MJO modulates not only TCs but also monsoons around the world, which contribute essential rainfall for agriculture that supports billions of people, but which also can cause deadly floods. Because of the close coupling between the MJO and TCs, as well as the several week predictability of the MJO, models that can accurately simulate both kinds of weather systems have the potential to be useful for both mid-range weather forecasting and studies of impacts of climate change. This paper describes the further development of one such model, the Lagrangian Atmospheric Model (LAM), which simulates atmospheric motions by predicting motions of individual air parcels, and which has been shown to accurately simulate the MJO in previous studies. In this study, a new parameterization of cloud albedo is included in the LAM, and the model is tuned to improve simulations of TC distributions while still maintaining a robust and realistic MJO. Objective metrics of the model basic state, MJO quality, and TC distributions are used to optimize parameter selections for the cloud albedo parameterization and convective mixing. After tuning the LAM using dozens of 3-year simulations, we conduct two longer simulations forced with observed sea surface temperatures to verify that the new version of LAM has a substantially improved representation of TCs while still maintaining a realistic MJO. Full article

We introduce the Normalising Flow GARCH (NF-GARCH), a two-stage hybrid framework that enhances traditional GARCH models by replacing restrictive parametric innovation distributions with learned densities via normalising flows. Our approach preserves the interpretability of standard variance dynamics while addressing the common issue of innovation misspecification. In the first stage, we estimate standard GARCH variants (sGARCH, TGARCH, and gjrGARCH) to extract standardised residuals. In the second stage, a Masked Autoregressive Flow learns the underlying residual distribution, with samples from the flow subsequently driving the GARCH recursion for out-of-sample forecasting. Evaluated on 13 daily financial series (six FX pairs and seven equities), NF-GARCH demonstrates systematic, statistically significant improvements in forecast accuracy for skewed-t baselines. Wilcoxon signed-rank tests confirm superior performance specifically for gjrGARCH-sstd and sGARCH-sstd specifications. While the framework offers enhanced flexibility and generative realism, we observe that computational overhead is increased, and the log-variance specification of eGARCH exhibits instability when paired with flow-based innovations. These results suggest that while NF-GARCH effectively captures empirical tail behaviour in univariate settings, future research should explore conditional flow architectures and multivariate extensions to account for time-varying innovation shapes. For risk management, gains are most relevant where skewed-t baselines are used and where closer residual realism supports scenario analysis; effect sizes remain modest relative to model risk and implementation cost. Full article

Accurate forecasting of near-surface PM_2.5 concentrations remains challenging due to the complex coupling between atmospheric vertical structure, thermodynamic stability, and pollutant accumulation processes. Most existing surface-based statistical and deep learning approaches struggle to represent the three-dimensional state of the atmosphere, which limits their robustness under complex meteorological conditions. In this study, we propose a multi-source spatiotemporal learning framework(MST-Net) to enhance PM_2.5 forecasting accuracy by integrating vertically resolved atmospheric information from lidar and radiosonde observations. The proposed approach incorporates vertical profile features together with surface measurements to provide complementary information on atmospheric vertical structure and its temporal evolution. Experimental results demonstrate that MST-Net consistently outperforms conventional time-series models across multiple forecast horizons. Notably, at extended lead times (12–24 h), the proposed framework exhibits enhanced stability and slower error growth. For 24 h forecasts, MST-Net reduces RMSE by approximately 13% and MAE by about 19%. These results indicate that leveraging multi-source vertical atmospheric information can effectively improve the reliability of urban air quality forecasting. Full article