Search Results (2,474)

Accurate short-term wind power forecasting is essential for the secure and economic operation of power systems with high renewable energy penetration. However, forecasting performance is still affected by meteorological forecast uncertainty and the complex multi-scale fluctuation characteristics of wind power generation. To address these challenges, this paper proposes an Initial-State-Aware Multi-Scale Transformer framework for 12 h-ahead wind power forecasting. The principal methodological contribution is an initial-state-aware meteorological representation and progressive fusion strategy tailored to weather-driven wind power forecasting. The framework explicitly distinguishes the atmospheric state available at forecast initialization from the subsequent forecast meteorological trajectory and uses the former to condition the representation of the latter through cross-attention and gated residual fusion. The resulting meteorological representation is then progressively coupled with coarse- and fine-scale historical power representations, and a horizon-oriented forecasting head generates the future power sequence in parallel. Experiments on three wind farms demonstrate that the proposed method achieves the best overall forecasting performance. Compared with the strongest baseline model, it reduces NMAE and NRMSE by 8.54% and 2.36%, respectively. Full article

Normalized Difference Vegetation Index (NDVI) is an important remote sensing indicator for characterizing vegetation growth status and ecosystem changes. Improving NDVI prediction accuracy is of great significance for regional ecological monitoring and conservation. However, existing prediction methods often rely on single meteorological drivers or numerous explanatory variables that are difficult to obtain for future periods, limiting their applicability to pixel-level NDVI forecasting over spatially distributed areas. In this study, a Dual-Factor-Driven Temporal Network (DfT-Net) was proposed for pixel-level NDVI prediction in the Hulunbuir grassland based on MODIS NDVI data and ERA5-Land temperature and precipitation data from 2013 to 2024. The model was independently applied to valid 1000 m grassland pixels, with the same model parameters shared across pixels. This pixel-wise prediction strategy enables the model to learn common meteorological–vegetation response patterns across different pixels while generating spatially distributed NDVI predictions. For temporal feature modeling, Time Series Decomposition (TSD) was first applied to the temperature and precipitation sequences to decompose them into trend, seasonal, and residual components, thereby characterizing their multi-scale temporal variations and recurrent seasonal patterns. Subsequently, one-dimensional convolutional neural networks (CNNs) and long short-term memory networks (LSTMs) were employed to extract local temporal patterns and long-term temporal dependencies, respectively. Experimental results showed that DfT-Net achieved an RMSE of 0.100, an MAE of 0.074, and an R² of 0.828 on the independent temporal test set (2022–2024). Under the same experimental setting, DfT-Net achieved the lowest RMSE and MAE and the highest R² among the evaluated models, including LSTM, CNN, TSD-CNN, TSD-LSTM, and CNN-LSTM. These results indicate that DfT-Net effectively integrates dual-factor meteorological driving, multi-scale temporal feature representation, and pixel-level prediction, providing a useful framework for spatially distributed grassland NDVI forecasting and ecological monitoring. Full article

Wind direction time series exhibit angular periodic discontinuity, multi-scale non-stationary fluctuations and abrupt wind shifts, which hinder the precision of short-term forecasting for wind turbine yaw control. In this paper, a dual-branch forecasting framework based on Variational Mode Decomposition (VMD) and Transformer is developed to address the above drawbacks, with a hysteresis gating and zoning residual compensation module embedded for targeted error correction. First, sine–cosine encoding is adopted to eliminate the numerical discontinuity between 0° and 360° for wind direction angular data, and valid meteorological input features are screened to discard redundant covariates. Second, the sine–cosine-encoded wind direction sequence is decomposed into multiple band-limited intrinsic mode functions (IMFs) via VMD, extracting frequency-specific features that reduce non-stationarity and facilitate subsequent Transformer modeling. The standard Transformer encoder serves as the normal branch to capture long-range temporal dependencies across the whole time series, while a lightweight multilayer perceptron (MLP) constitutes the compensation branch to learn prediction deviations between baseline predictions and ground-truth values. The hysteresis gating unit activates residual compensation based on historical prediction errors and angular variation, without requiring access to the current ground-truth value, and compensation intensity is adaptively adjusted via the zoning strategy; relevant coefficients are optimized by random search. Verified on a real wind farm dataset consisting of 10,421 15 min sampling points, the proposed model achieves the lowest MAE of 9.64° among six benchmark models. For the improved genuine mutation samples (angle change > 70°), the model achieves a mean improvement of 6.02°. Ablation experiments verify that VMD preprocessing, the MLP compensation branch, and the hysteresis gating mechanism play indispensable roles in forecasting performance. The proposed framework can support accurate yaw control of wind turbines, and the decomposition–compensation workflow can also be generalized to other periodic non-stationary forecasting tasks. Full article

Accurate one-week-ahead building electricity demand forecasting is essential for building energy management, yet representing future building operational characteristics remains challenging because such information is generally unavailable in advance. This study investigates the effectiveness of representing building operational characteristics using cluster labels derived from daily electricity consumption patterns for medium-term electricity demand forecasting. Cluster labels obtained by k-means clustering were incorporated as operational-state features into a Temporal Fusion Transformer (TFT) together with historical electricity consumption, meteorological variables, and calendar information. Forecasting performance was evaluated for a training facility and three university buildings using walk-forward validation under different feature reference periods. Under an idealized information condition in which meteorological variables and cluster labels corresponding to the forecasting period were provided as known future inputs, this forecasting pattern achieved the highest accuracy for all investigated buildings. Under the same idealized condition, variable importance analysis indicated that the cluster label exhibited the highest importance among the known future inputs, exceeding that of calendar variables and most meteorological variables. In addition, the TFT outperformed Long Short-Term Memory (LSTM) and Multi-Layer Perceptron (MLP) models. These findings indicate the potential value of the proposed operational-state representation for improving one-week-ahead building electricity demand forecasting and provide interpretable insights into the contribution of operational-state features. Full article

Global Navigation Satellite Systems (GNSS) signals are delayed by the atmosphere, and the resulting zenith total delay (ZTD) provides valuable information on atmospheric water vapour for numerical weather prediction (NWP). Despite the demonstrated benefits of GNSS ZTD assimilation, the southern part of the Meteorological Cooperation on Operational Numerical Weather Prediction (MetCoOp) domain remains sparsely observed, particularly along the main southwesterly moisture-transport pathway into Fennoscandia. This study investigates the impact of assimilating additional ZTD observations from northern Germany—provided by the Helmholtz Centre for Geosciences (GFZ)—into the MetCoOp system. By extending ZTD coverage upstream of the forecast domain, the study addresses a documented gap in previous MetCoOp assimilation research, which has largely focused on densely observed regions or event-specific cases. Since moisture transport into Fennoscandia is climatologically dominated by southwesterly flow from the North Sea, particularly during summer, strengthening ZTD coverage in the southern MetCoOp domain therefore provides critical upstream constraints on humidity and temperature advection. Using the convection-permitting High-Resolution Limited Area Model—Applications of Research to Operations at Mesoscale (HARMONIE–AROME) model coupled with the Surface Externalisée scheme (SURFEX), two experiments were run for June–August 2025: a baseline configuration and one including GFZ ZTDs. Assimilating GFZ data significantly refines the mid-to-lower-tropospheric moisture field (500–925 hPa). Although domain-averaged differences remain modest—specific humidity variations of ~1.3 g kg⁻¹ and temperature deviations near 1 K—spatial analyses reveal sharper moisture gradients and improved boundary-layer structure over land. These findings demonstrate that enhanced upstream ZTD density provides valuable constraints on moisture advection and latent-heat-related processes, thereby improving short-range humidity analyses in a high-resolution NWP system and complementing earlier studies conducted in Fennoscandia. Full article

Circular data arise in a wide range of scientific fields, including meteorology, medicine, biology, and neuroscience, yet existing regression methods for such data are largely restricted to parametric generalized linear models or tree-based methods that impose distributional assumptions on the circular response. In this paper, we propose a family of Bayesian Additive Regression Tree (BART) methods for regression with circular data, covering three cases: Circular–Circular BART (CCBART), where both the response and the covariates are circular; Circular–Linear BART (CLBART), where the response is circular and the covariates are linear; and Linear–Circular BART (LCBART), where the response is linear and the covariates are circular. The proposed methods adopt a projection approach, decomposing circular variables into their sine and cosine components, fitting separate BART models on these projections, and recovering circular predictions via the two-argument arctangent function. This avoids specifying a von Mises or wrapped normal likelihood directly for the circular response, though it does not avoid all distributional assumptions: BART assumes flexible Euclidean regression models, with Gaussian errors, for the projected sine and cosine components. The approach retains the full inferential power of BART, including posterior uncertainty quantification, automatic variable selection, and the ability to capture nonlinear effects and interactions without pre-specification. An extensive simulation study demonstrates that the proposed methods are highly competitive with random forest benchmarks and consistently outperform linear model benchmarks, with the clearest and most consistent advantage over random forests emerging at high noise levels and in the Linear–Circular case, where LCBART achieves up to 34% lower RMSE than projected random forests. Applications to wind direction forecasting and human motor resonance data further illustrate the practical utility of the proposed methods. Full article

Air quality forecasting supports public-health protection, yet prior Saudi studies have mostly addressed single pollutants or single-city air quality index (AQI) classification. This study evaluates one-hour-ahead AQI forecasting across eight climatically diverse Saudi cities (Makkah, Riyadh, Jubail, Abha, Taif, Madinah, Tabuk, and Yanbu) using attention-based bidirectional recurrent networks, trained with and without meteorological inputs and compared against statistical and machine-learning baselines. Against a stringent persistence baseline that quantifies the predictability ceiling imposed by the strong autocorrelation of hourly AQI, the deep models matched it in RMSE and R² (cross-city mean R² ≈ 0.90) while lowering the mean absolute error by roughly a fifth, an advantage most valuable in the more variable cities where warnings matter most. In an event-based evaluation, the models flagged 84 to 91% of high-AQI threshold exceedances, including in the most volatile city, so the forecasts retain warning value even where the largest peaks are compressed. Surface meteorological inputs contributed little on average and their value was city-specific, and at Riyadh also architecture-dependent. SHAP and LIME confirmed the models rely on physically expected drivers, chiefly particulate matter, with feature rankings stable across cities, methods, and architectures. Evaluating one common framework across climatically diverse cities, we find that forecast skill varies more with local regime and input configuration than with model architecture, which offered no consistent advantage. Per-city input configuration within a common framework accordingly offers a practical basis for deployment. Full article

Lightning poses localized risks to signaling, communication, and traction-power systems along high-speed railways, yet most nowcasting products are generated on regular grids rather than operational line segments. This study developed a grid-to-segment machine-learning framework for next-hour lightning warning along the Jinan West–Tai’an corridor. Ground-based lightning observations, hourly ERA5 fields, temporal variables, and engineered historical lightning features and spatial-neighborhood features were organized on a 0.25° grid. Data from 2014 to 2018 were used for training, 2019 for validation, and 2020 for independent testing. Grid probabilities were converted into warnings for six railway segments using 10 km buffers and maximum-probability aggregation. In 2020, the full extreme gradient-boosting (XGBoost) model, a tree-based ensemble-learning algorithm, achieved grid-level probability of detection (POD), false-alarm ratio (FAR), and critical success index (CSI) values of 0.55, 0.50, and 0.36; segment-level verification yielded 0.60, 0.39, and 0.43. To examine transfer to forecast-driven application, the trained model and threshold were fixed, and ERA5 meteorological inputs were replaced by short-lead ECMWF HRES forecasts for July 2025. POD decreased from 0.85 to 0.80 and CSI from 0.60 to 0.57, while FAR remained nearly unchanged. Under a predefined non-zero rule, HRES litota1 achieved 0.62, 0.71, and 0.25. ML-HRES therefore showed higher CSI and lower FAR than the direct litota1 baseline. Full article

Owing to their geographical dispersion and high deployment costs, distributed photovoltaic (DPV) stations often lack access to high-precision meteorological data, which degrades power forecasting accuracy and threatens grid operational stability. Accordingly, developing a low-cost ultra-short-term power forecasting model is critical for power system dispatching. This study proposes a site-level ultra-short-term power forecasting method incorporating satellite cloud imagery (SCI) for DPV systems. First, three core forecasting challenges are analyzed: cross-modal data correlation establishment, spatial alignment between heterogeneous data structures, and spatiotemporal correlation extraction among dispersed stations. Second, a forecasting model taking satellite imagery and multi-station power outputs as inputs is constructed. It aligns multimodal data via a data embedding layer, and integrates multi-source features through cuboid self-attention modules and an encoder–decoder architecture. Third, a Multi-Scale Correlation Mechanism (MSCM) is proposed to capture spatiotemporal associations across geographically dispersed stations. Experimental results based on a real-world dataset from Hebei Province show strong performance. The full model with satellite cloud imagery achieves a Root Mean Square Error (RMSE) of 0.112 and a Mean Absolute Error (MAE) of 0.059, outperforming baseline models including the backpropagation (BP) neural network, long short-term memory (LSTM) network, and Transformer model. Full article

Hyperlocal meteorological sensing is essential for accurate solar photovoltaic forecasting, yet professional-grade meteorological stations require investments easily exceeding $1000 USD per node, making distributed deployments economically inaccessible. This work presents a modular internet of things (IoT) device based on the ESP32 microcontroller integrating temperature, humidity, luminosity, and solar panel voltage sensing in an IP68-rated enclosure at a total hardware cost of about $65 USD when components are sourced in Germany. The enclosure-mounted temperature sensor is subject to a daytime radiative-heating bias and is not a calibrated ambient-air measurement. A hybrid architecture decouples external model training, performed on a conventional computer using the software Python and the open-source library TensorFlow, from autonomous on-device inference: every 15 min, the embedded feedforward network produces a single one-step-ahead (15 min) prediction of solar panel voltage from the most recent 96 real sensor readings; the resulting sequence of 96 such predictions, logged and assembled over a full day, forms the diurnal forecast profile reported below. This is executed via a three-layer feedforward network with 3011 parameters (11.8 KB). The network is trained offline on site-collected data and deployed on the microcontroller as static weight matrices without cloud connectivity. An on-device incremental gradient descent mechanism enables model adaptation after deployment without external retraining. The system was evaluated through two field deployments: a short period of hardware and firmware validation in Ulm, Germany, and a 115-day deployment in Zapopan, Mexico, comprising 84 days of training and 31 days of autonomous operation with zero missing records (no 15 min interval failed to log a reading); a real-time-clock fault affecting the final three validation days is addressed separately below and excluded from the reported metrics. Over a clean 28-day daytime window, the embedded model attained a coefficient of determination of 0.9165 and a mean absolute error of 0.2975 V (4.65% of the operational range), outperforming a climatology baseline (skill score 0.64) while not surpassing a 24 h persistence baseline. A frozen-weight ablation confirms that the on-device update mechanism yields a small but statistically significant accuracy gain ($p=0.001$), showing that autonomous incremental learning is implementable on low-cost hardware and produces a measurable effect, without cloud connectivity. Full article

Existing studies still have limitations in characterizing the complex temporal patterns of photovoltaic time series. In particular, current forecasting models often struggle to capture local abrupt fluctuations and nonlinear relationships among variables, while hyperparameter optimization remains challenging. To overcome these limitations, this paper proposes a CNN-iTransformer short-term photovoltaic power forecasting method based on multiscale decomposition and adaptive optimization. First, the original photovoltaic power time series is decomposed into trend, seasonal, and residual components using seasonal-trend decomposition based on Loess (STL). The residual component is then further decomposed through variational mode decomposition (VMD) to fully extract the latent multiscale temporal information embedded in the sequence. Second, a convolutional neural network (CNN) is employed to extract local fluctuation features, while the iTransformer is utilized to model the nonlinear relationships and long-term temporal dependencies between multiple meteorological variables and photovoltaic power. Finally, the Phototropic Growth Algorithm (PGA) is introduced to optimize key hyperparameters of the forecasting model, thereby improving its generalization capability and forecasting accuracy under multi-seasonal scenarios. Simulation experiments are conducted using real-world data from a photovoltaic power station in Alice Springs, Australia. The experimental results show that, under the same PGA optimization conditions, the proposed model reduces the root mean square error (RMSE) and mean absolute error (MAE) by approximately 19.12% and 17.43%, respectively, compared with the baseline iTransformer. Meanwhile, its performance is better than that of several mainstream deep learning models, which verifies the generalization ability and forecasting accuracy of the proposed method under complex seasonal variations. Full article

Renewable-generation forecasting is a probabilistic time-series problem in which point accuracy alone is insufficient for operational decision-making. This study proposes a physics-informed Bayesian framework for multi-horizon forecasting of solar, wind, and total renewable generation. The task is formulated as a 15-dimensional target–horizon problem covering three generation families and five forecast horizons: H1, H3, H6, H12, and H24. A leakage-safe data construction protocol generates causal predictors from meteorological observations, generation history, calendar cycles, lagged and rolling statistics, ramp descriptors, and physics-informed transformations. PI-BHTF partitions the 422-dimensional predictor space into solar, wind, temporal-calendar, and cross-context components, encodes them through parallel nonlinear branches, and combines the representations using cross-energy gated fusion. Its neural core uses a heteroscedastic predictive head and Monte Carlo dropout to distinguish input-dependent aleatoric uncertainty from epistemic variability, whereas the final hybrid forecasts are calibrated using residual quantiles computed from a chronologically held-out validation segment. Across three prespecified random seeds, the full PI-BHTF achieved a mean MAE of 0.0797 ± 0.0007 on the internal chronological test and 0.0686 ± 0.0006 on locked external SCADA validation. Performance and calibration varied substantially across target–horizon tasks, including marked short-horizon external undercoverage for wind generation. Component-wise ablation supported semantic feature partitioning and the heteroscedastic head, whereas the physics-informed features, cross-energy gate, and physics-consistency loss did not independently reduce aggregate MAE. PI-BHTF should therefore be interpreted as a reproducibly competitive framework that balances multi-horizon accuracy, structured representation, uncertainty estimation, and external transferability rather than as a universally dominant model. Full article

Near-surface ozone (O₃) pollution is a growing environmental concern, particularly in the Beijing–Tianjin–Hebei (BTH) region, one of China’s most densely populated megacity clusters experiencing increasingly severe O₃ episodes. Existing data-driven forecasting models systematically underestimate high-concentration events and offer limited lead times. To reveal the meteorological drivers of extreme O₃ episodes, we conducted composite anomaly analysis over 2019–2023 and identified the dominant meteorological mechanism as a coupled pattern of mid-tropospheric anticyclonic circulation with high temperature, low humidity, and deep subsidence inversion, which suppresses vertical diffusion while southerly advection drives rapid near-surface O₃ accumulation. Motivated by meteorological diagnostics, we proposed ARC-Net, a Transformer-encoder-based Adaptive Residual Correction Network that ingests numerical weather prediction data from the European Centre for Medium-Range Weather Forecasts (ECMWF) and air quality observations to produce hourly O₃ forecasts up to 240 h (10 days) ahead. The model features a dual-branch regression-classification architecture enhancing feature discrimination at high concentrations and an Adaptive Residual Correction module that dynamically calibrates outputs through a triple-gating mechanism conditioned on pollution-level priors. In independent forecast tests for the year 2023 across 13 cities in the BTH region, ARC-Net achieved R² = 0.879 and a root mean square error (RMSE) of 17.03 μg/m³ at 0–24 h, retaining R² = 0.749 and RMSE = 24.57 μg/m³ at 0–240 h. For extreme episodes (maximum daily 8 h average ozone (MDA8_O₃) ≥ 215 μg/m³), the Critical Success Index improved by 63.9% over the baseline, and RMSE decreased by 33.15% within the 215–265 μg/m³ range in a representative case. These results indicate that meteorology-guided predictors combined with adaptive residual correction can partially alleviate high-O₃ underestimation and provide practically useful medium-range warning skill. Full article

Accurate prediction of PV output is critical for optimizing its absorption potential and ensuring the safe, stable, and cost-effective operation of the power grid. Yet, due to the intermittent and stochastic nature of photovoltaic power generation, establishing a highly precise prediction model presents significant difficulties. In this study, a hybrid forecasting framework integrating WCSD, CEEMDAN-FE, IPOA, and Transformer-LSTM is developed to improve PV power forecasting accuracy. Firstly, a new training data sample generation method based on WCSD is developed for determining the historical days having similar meteorological conditions to the predicted day. Secondly, CEEMDAN is employed to decompose original output sequence into an ensemble of components with different amplitudes and frequencies, where they were recombined as new set including a handful of components with low-frequency variation characteristics based on FE index. Thirdly, the IPOA is proposed for the first time, which couples Gaussian mutation and enhanced circle chaotic mapping. Next, the prediction model for each component is formulated by aid of Transformer-LSTM algorithm, the optimal hyperparameter combination of which is determined by IPOA method. Finally, the predicted results are obtained as the sum of individual component predictions. The prediction performance of the designed model is tested and verified via experimental analysis located in Yunnan Province, China and the publicly available Australian DKASC dataset. The empirical findings demonstrate that, in contrast to alternative benchmark models, our developed hybrid prediction model consistently attains superior prediction accuracy. Full article

The case of common ragweed (Ambrosia artemisiifolia) stands as a prime example of an invasive plant that links global change, biological invasion, aeroallergen exposure, and allergic airway disease. However, evidence remains fragmented across invasion biology, aerobiology, molecular allergology, and respiratory medicine. By separating plant occurrence, pollen abundance, molecular allergen dose, sensitisation, and airway disease, this review develops an integrated invasion–exposure–disease logic for interpreting ragweed-related health risk. We examine how climate change, land-use disturbance, repeated introductions, rapid adaptation, and air pollution influence plant distribution, flowering phenology, pollen production, airborne allergen load, and respiratory outcomes. Attention is given to Amb a 1 as the principal marker of genuine ragweed sensitisation, cross-reactivity with Artemisia and other weed pollens, allergen-bearing respirable particles, and the diagnostic limitations of extract-based immunoglobulin E (IgE) testing. The literature indicates that ragweed sensitisation follows a pronounced hotspot–gradient pattern in Europe, whereas patterns in other invaded regions remain more heterogeneous and incompletely characterised. Clinically relevant exposure depends not only on pollen concentration but also on airborne allergen load, pollen allergen potency, atmospheric transport, respirable particle fractions, meteorological conditions, and pollution. Ragweed-related airway disease is mediated by IgE-dependent type 2 immunity and amplified by epithelial danger signals, oxidative stress, protease activity, and innate immune pathways. Based on current evidence, we propose that an integrated surveillance framework linking plant distribution, pollen and airborne-allergen exposure, molecular sensitisation, symptoms, lung function, and asthma outcomes could strengthen risk forecasting, source attribution, prevention, and invasion control of the common ragweed. Full article