Search Results (1,487)

Industrial tariffs and demand-response (DR) programs pay for two quantities—daily energy and daily peak demand—yet short-term forecasting research addresses mostly the first, and rarely under the constraints of small industrial sites: strongly bimodal operation and only one to two years of records. We propose the Two-Stage Adaptive Framework (TSAF), a metering-only method that detects bimodality, classifies each day as active or inactive from its partial-day consumption, and fits a regression model to active days only; the same 21 features serve both targets. On 15 min data from ten plating factories of the Ansan Plating Industrial Complex (19 months), TSAF reaches 16.2% mean MAPE on daily energy against 58.7% for a day-ahead reference, and no deep-learning model beats the 22-parameter Ridge regressor. On daily peak, evaluated on active days, a joint multi-factory Transformer reaches 8.4% MAPE against a 14.0% constant-predictor floor, and a training-free tabular foundation model (TabPFN) reaches a comparable 7.0% without cross-factory data; intraday peak timing (≈2 h mean error) marks the limit of the meter-only design. External validation on 36 stratified UCI clients delimits the framework’s scope, and a weather ablation, specified in advance of estimation, finds no significant gain (p = 0.23). After adjusting for Stage 1 misclassification and intraday dispatch feasibility, the ten factories gain about 60 million KRW (US$46,000) per year and avoid 15.4 tCO₂ under Korean market conditions. Because TSAF needs only the smart-meter feed, power suppliers and DR aggregators can deploy it without access to customer-facility internals. Full article

The Caspian Sea’s unique environment and intense hydrocarbon extraction make it a high-risk, understudied region for oil spill modelling. This review assesses the physical, chemical, and biological processes governing oil spill transport and fate, and evaluates the principal numerical tools available for the Caspian Sea context. The weathering processes are reviewed from foundational formulations to operational implementations. Key research challenges identified include the absence of photo-oxidation from operational models, limited laboratory data for Caspian crude oil types, and simplified biodegradation parameterizations. Hydrodynamic forcing uncertainty, arising from the lack of a dedicated operational ocean model, remains the dominant source of trajectory forecast error. Seven operational oil spill modelling tools and the ROMS hydrodynamic platform are reviewed. Only OSCAR and MIKE 21 have documented applications to the Caspian Sea, representing a significant regional gap. ROMS is identified as the most suitable hydrodynamic platform for future operational forecasting. Finally, the integration of machine learning and deep learning methods, including neural network trajectory prediction and SAR detection, is discussed as a promising frontier for improving forecast accuracy in this data-sparse environment. Full article

Accurate information on atmospheric temperature profiles is crucial for improving numerical weather prediction (NWP). However, the harsh environment of the Tibetan Plateau (TP) limits the availability of station observations, which thereby fail to meet the high spatial resolution required for NWP. In this study, we present an integrated framework as an engineering refinement combining the variation method with an artificial neural network (Var-ANN) to calibrate temperature profiles obtained from the Vertical Atmosphere Sounding System (VASS) aboard the polar-orbiting satellite FY-3C. The variation method is first applied to construct a spatially consistent reference field from available station observations, and this field is then used as the training target for a back-propagation neural network that learns the empirical relationship between satellite brightness temperatures and corrected atmospheric temperature. The calibrated temperature profiles were evaluated against independent radiosonde observations and further tested through assimilation into the Weather Research and Forecasting (WRF) model for precipitation simulation over the TP. Results indicate that the Var-ANN calibration reduces the root-mean-square error (RMSE) by approximately 60% and the mean bias from approximately −5 °C to −0.7 °C relative to radiosonde observations. In two WRF case studies, the calibrated profiles show potential for improving precipitation forecast skill, although the limited sample size precludes robust conclusions about operational forecast improvements. The Var-ANN framework provides a practical approach for enhancing the utility of FY-3C VASS temperature products for NWP applications over data-sparse complex terrain. Full article

Near-surface temperature inversions are prevalent during the cold months in Ulaanbaatar city, Mongolia, and significantly degrade urban air quality by trapping hazardous pollutants within a shallow atmospheric boundary layer. This study investigates spatiotemporal variability, physical mechanisms, and long-term evolution of near-surface temperature inversions over Ulaanbaatar by integrating 25 years (2000–2024) of ground-based meteorological and radiosonde observations, with high-resolution Weather Research and Forecasting (WRF) model simulations for 2012–2023. Our results demonstrate the four-dimensional data assimilation (FDDA) grid nudging effectively captures localized topographic influences in the WRF simulations, showing a strong agreement with radiosonde observations (R² = 0.783, p < 0.000). Near-surface temperature inversions are strongly controlled by the Siberian High, with the highest frequency occurring from December to February, when up to 67% of morning observations exhibit inversion conditions. A pronounced diurnal cycle was identified, with inversion intensity peaking at 5.6–6.8 °C during the early morning hours (02:00–08:00 LST) before reaching a minimum around 14:00 LST. Spatially, the strongest inversions occur along the low-lying Tuul River valley, where the planetary boundary layer is compressed to below 350 m and wind speeds decrease to less than 2.4 m·s⁻¹, creating persistent atmospheric stagnation. Despite these favorable conditions for inversion formation, long-term observations indicate that regional warming (+2.0 °C) and the urban heat island effects have reduced inversion frequency by 31%, inversion thickness by 170 m, and inversion intensity by 0.9 °C over the past 25 years. These findings demonstrate the strong coupling between regional complex terrain, and boundary layer thermodynamics, highlighting the need to incorporate urban ventilation corridors and topography-informed planning into climate adaptation and winter air-quality management strategies. Full article

Predicting vessel motion and environmental dynamics is essential for safe operation of autonomous maritime navigation systems. Transformer-based models have achieved strong results in AIS-trajectory forecasting and in anticipating future sonar observations, however, their use in maritime radar frame prediction has received little attention, despite radar being a key sensing modality in challenging weather and visibility conditions. In an effort to address this gap, this paper introduces a transformer architecture for predicting future maritime radar frames from sequences of past X-band observations and vessel ego-motion derived from GNSS, adapting the EchoPT paradigm originally developed for simulated in-air sonar imagery to the real-world MOANA dataset. We detail the model architecture and evaluate its prediction performance under both single-frame and autoregressive settings on held-out test data, and benchmark the model against persistence and rigid geometric warp references. A complementary failure mode analysis links the observed prediction errors to specific architectural and dataset choices, providing concrete directions for further research. Full article

The geostationary hyperspectral infrared sounder (GeoHIS) provides atmospheric variables at high spatiotemporal resolution. Consequently, GeoHIS can provide valuable information for improving real-time forecasting and enhancing the performance of numerical weather prediction (NWP). GeoHIS provides higher temporal resolution than that of a polar-orbiting platform, observing the same region 2~3 times daily. Therefore, we assess the forecast impact of a next-generation GeoHIS on a numerical model according to observation density using KIM-OSSE (Korean Integrated Model–Observing System Simulation Experiment) in this study. Simulated observations are generated from the nature run dataset (ECO 1280) provided by Cooperative Institute for Research in the Atmosphere at Colorado State University (CIRA/CSU). These simulated observations are then assimilated into KIM, after which KIM generates forecast fields. Using this framework, we evaluated the impact of GeoHIS on a global numerical model. The results showed noticeable improvements in geopotential height, particularly in the mid- and upper troposphere, while wind, temperature, and humidity remain largely unchanged in EXP-1 and EXP-2. An analysis of the sensitivity to GeoHIS temporal resolution, by comparing hourly data and 3-hourly data, revealed that higher temporal resolution leads to greater forecast improvements. Full article

Photovoltaic (PV) technology is now one of the main options for expanding the power of low-carbon electricity generation. However, in practical operation, PV systems still face several persistent difficulties, including the variability of solar irradiance, gradual performance degradation, fault occurrence, suboptimal control, and the growing complexity of grid-connected operation. These issues explain why artificial intelligence (AI) has become increasingly relevant in PV research, not only as a prediction tool, but also to improve monitoring, control, diagnosis, and decision-making. This review investigates the applications of AI in the major stages of the PV system lifecycle: solar resource assessment, power forecasting, fault detection, condition monitoring, system sizing, maximum power point tracking (MPPT), and grid integration. Rather than treating these applications as separate research topics, the review attempts to connect them through the common factors that determine their practical value: data quality, sensing configuration, model complexity, physical operating conditions, and deployment constraints. The reviewed studies indicate that AI-based MPPT methods can achieve tracking efficiencies close to 99%, while recent forecasting models, particularly LSTM, CNN–LSTM, and transformer-based architectures, can reduce prediction errors under changing weather conditions. At the same time, PV fault detection is moving beyond electroluminescence image classification toward more practical multimodal strategies that combine infrared thermography, RGB and drone imagery, electrical measurements, and SCADA/IoT data. Nevertheless, the progress reported in the literature should be interpreted with caution. Many proposed models are still evaluated on limited or non-standardized datasets, and their performance may decrease when they are transferred to different PV technologies, climates, fault severities, or operating conditions. Other recurring limitations include class imbalance, high computational cost, weak generalization, and the limited interpretability of deep-learning models. For this reason, hybrid neural networks, explainable AI, physics-informed learning, edge-AI, federated learning, and quantum machine learning are discussed as possible directions for making AI-based PV solutions more reliable and deployable. This review aims to critically synthesize recent advances and remaining gaps in order to support the practical integration of AI into efficient, reliable, and sustainable PV systems. Full article

Historic urban districts face growing challenges in balancing visitor activity with the needs of residents, local businesses, accessibility, and mobility. This study investigates whether short-term visitor forecasts can support destination management and planning in these complex environments. Unlike most visitor-forecasting studies, which focus on large cities and major tourist destinations, this study examines forecasting in a small historic urban district where visitor activity is more variable and management resources are limited. Using hourly pedestrian counts, weather data, and temporal data from the historic urban district of Fredrikstad, Norway, this research forecasts pedestrian activity up to 24 h in advance. The sensors record all pedestrians and do not distinguish tourists from residents or other users. Consequently, pedestrian counts are treated as an operational proxy for overall visitor activity at this heritage destination. Forecasting performance was evaluated using statistical, machine-learning, deep-learning, and benchmark forecasting models. Random Forest achieved the strongest overall forecasting performance (MAE = 209.52; RMSE = 357.18), outperforming the seasonal naïve benchmark (MAE = 247.44; RMSE = 421.70). Random Forest and GRU both outperformed the seasonal naïve benchmark on MAE, demonstrating the value of incorporating weather, temporal, and sensor variables into short-term forecasting. The findings suggest that short-term visitor forecasts may support operational planning, mobility management, service coordination, and other day-to-day destination management decisions. By anticipating periods of increased visitor activity, destination managers, local authorities, and government officials will be better able to allocate resources and coordinate services. This study demonstrates the potential of predictive analytics and sensor technology to support visitor management and operational planning in historic urban districts. Full article

Foundation models for time series forecasting have recently been applied to energy prediction tasks, where they can produce accurate forecasts without task-specific training. This study investigates the impact of two types of covariates, meteorological variables and calendar-based day type indicators, on the forecasting performance of Chronos-2, a state-of-the-art foundation model, in building energy consumption prediction. Using real-world monitoring data from two non-residential buildings at the ENEA Research Centre in Portici, Italy, we systematically evaluate seven configurations combining past and future covariates across multiple observation window lengths (7–28 days). Future meteorological covariates are derived from historical weather forecasts rather than observed weather data, ensuring that the evaluation reflects realistic operational forecasting conditions. The results show that incorporating day type indicators as both past and future covariates consistently delivers the highest forecasting accuracy, reducing CV-RMSE from 14.58% for the covariate-free baseline to 10.41% with a 28-day observation window. A day-stratified analysis further reveals that these improvements are concentrated on regime transition days, for which recent load history alone provides limited information about the operating conditions of the day being forecast. By contrast, meteorological variables, whether obtained from weather forecasts or historical observations, yield only marginal performance gains, suggesting that calendar-driven operational schedules are the primary determinants of energy demand in the buildings considered. These findings provide practical guidance for deploying foundation models in real-world energy building management systems and show that covariate selection is a key determinant of forecasting performance. Full article

Numerical weather simulations and forecasts are highly sensitive to environmental conditions. This is especially true in Taiwan, an ocean-surrounded island, during its transition season. Atmospheric temperature and moisture profiles retrieved from spaceborne sounders provide essential environmental information in regions lacking in situ observations. However, infrared sounders are sensitive to clouds and may induce uncertainties related to cloud properties. The present study analyzed 1 year of soundings from the National Oceanic and Atmospheric Administration’s Unique Combined Atmospheric Processing System (NUCAPS) to investigate the effects of clouds on the retrievals. The results indicated that the retrieved temperature profiles over land and under clouds had greater uncertainty than over oceans or in clear skies. In addition, the moisture profiles often exhibited a bias against cloud-top pressure. Therefore, this study proposed an objective quality control and bias correction method based on cloud effects. Excluding temperature observations affected by clouds and those over land reduced the root mean square difference from 3.3 K to 1.3 K. The relative cloud-top pressure level was used to conduct water vapor bias correction, which achieved effective correction for dry bias in the retrieved moisture profiles. After appropriate constraint criteria were applied, the bias-corrected profiles demonstrated a reduction in moisture bias from −4% to nearly 0%. That is, we assimilated sounding and radiance data into the regional Weather Research and Forecasting model and evaluated their effects, and we discovered that the retrieved profiles and direct observations positively contributed to the forecast of a spring frontal system. However, experiments using objective-bias-corrected sounding data improved skill scores in precipitation forecasts compared with using original sounding data or radiance data under a standard global operational baseline bias correction. Full article

This study presents a systematic literature-based discovery of the energy management process within household microgrids, combining the methodologies of Systematic Literature Review (SLR) and Literature-Based Discovery (LBD). The objective is to identify and structure key activities that ensure the efficient, scalable, and resilient operation of household microgrids. Drawing on an extensive analysis of the literature, the study proposes a conceptual, process-oriented framework that integrates technological and organizational perspectives into an eight-step roadmap for household energy management. These steps include data acquisition, local weather forecasting, energy production and consumption prediction, demand and supply management, energy generation and storage, power distribution, control of technological and organizational infrastructure, and compliance with safety and regulatory standards. The model supports the integration of predictive, self-learning control systems and highlights the importance of user competence development alongside automation. By mapping out a structured and replicable approach to household microgrid energy management, the study provides a foundation for improved energy independence, operational reliability, and effective integration into decentralized energy markets. The roadmap offers practical insights for both researchers and practitioners aiming to support the sustainable development and governance of household microgrids. Full article

This study investigates the impact of assimilating Advanced Scatterometer (ASCAT) Level-2 surface soil moisture retrievals into the Application of Research to Operations at Mesoscale (AROME) model, the operational numerical weather prediction system of the Hungarian Meteorological Service. The Level-2 retrievals are geophysical soil moisture estimates derived from satellite radar backscatter observations and represent the uppermost soil layer (approximately 0–5 cm). Data assimilation is performed using a Simplified Extended Kalman Filter (SEKF) within the SURFEX surface modeling platform. In the reference configuration (REF), the same SEKF framework is applied, as used operationally for the assimilation of 2 m temperature and relative humidity observations. A second experiment (ASCAT) extends this configuration by additionally assimilating ASCAT surface soil moisture retrievals. The experimental period covers May–October 2023. The objective of the study is to quantify the added value of ASCAT soil moisture assimilation relative to the REF experiment, which does not assimilate ASCAT retrievals. Results indicate a systematic improvement in root-zone soil moisture and soil temperature, suggesting that the assimilation of surface soil moisture observations propagates beneficially to deeper soil layers. Verification against in situ and model-derived diagnostics shows a positive impact on near-surface atmospheric variables, particularly for 2 m temperature and humidity during nighttime conditions. Furthermore, precipitation verification reveals a measurable improvement, suggesting a beneficial influence of improved land–atmosphere coupling on short-range forecasts. Full article

Reliable power systems are essential to modern life, as severe storms continue to disrupt grid stability and cause widespread outages. Predicting storm outages enables utilities and emergency managers to pre-stage resources and improve resilience. However, the several days of forecast lead time typically needed for preparedness significantly affect the accuracy of outage predictions. This study investigates the impact of forecast lead time on the error propagation of a Gradient Boosting Machine (GBM)-based outage prediction model (OPM) driven by Weather Research and Forecasting (WRF) model forecasts and analysis predictions. We evaluate three error-analysis scenarios: FFAP (forecast vs. analysis-based outage predictions), FFAO (forecast vs. actual outages), and LFAO (leave-one-storm-out forecast vs. actual outages). Model performance is compared using Mean Absolute Percentage Error (MAPE) and Centered Root-Mean-Square Error (CRMSE) across short (12 h–1 d), medium (2–3 d), and long (4–5 d) forecast lead-time categories, with the long category representing the upper end of the medium-range forecast window relevant to operational preparedness. The results show that forecast lead time substantially affects outage prediction accuracy, but the magnitude depends on the evaluation setup. In the controlled FFAP scenario, CRMSE increased by approximately 110% as lead time increased, from 259 to 543 outages, isolating the effect of weather forecast degradation. In the more operational LFAO scenario, CRMSE was already high at short lead times, increasing from 847 to 920 outages, indicating that model generalization error dominates once storms are unseen. Across scenarios, LFAO errors were 51% higher than FFAO errors at short lead times, highlighting the importance of testing outage models under unseen-event conditions. These results quantify how forecast degradation and model generalization jointly shape the reliability of outage prediction and provide practical guidance for lead-time-aware storm preparedness. Full article

The output of photovoltaic power generation exhibits significant randomness, volatility, and intermittency, and its uncertainty will have an impact on the planning assessment, dispatch decision-making, and real-time operation of the power system. To systematically understand the development status of modeling methods for the uncertainty of photovoltaic power generation, this paper conducts a review around the generation of annual scenarios and multi-timescale power prediction of photovoltaic power, and analyzes the correlations between photovoltaic output, influencing factors, and system applications from the perspective of statistical relationships and artificial intelligence. For the annual scale, the focus is on the generation methods of meteorological-driven scenarios for long-term sequences, including probability statistical methods, deep generation methods, constraint relations and engineering application evaluation issues; for the day-ahead scale, the historical power, meteorological variables and numerical weather forecasts are used to explore feature extraction, probability prediction and robust modeling methods; for the intraday scale, the signal decomposition, deep learning, regional collaborative modeling and multi-source perception methods for short-term power fluctuations perception are summarized. On this basis, further analysis is conducted on subsequent research directions such as multi-timescale collaborative modeling, multi-source heterogeneous information fusion, controllable generative modeling, extreme scenario characterization, and engineering closed-loop verification. This paper can serve as a reference for scenario generation, power prediction, and power system operation analysis under the condition of a high proportion of photovoltaic power integration. Full article

High-resolution projections of near-surface winds are crucial for ocean circulation and sea level studies in Southeast Asia, a region characterized by complex coastlines and monsoon variability. This study evaluates the added value of dynamical downscaling using the Weather Research and Forecasting (WRF) model at 9 km resolution, driven by two CMIP6 global climate models (EC-Earth3 and MPI-ESM1-2-HR), to simulate 10 m wind climatology over the Southeast Asian seas. Comparisons were made against ERA5 reanalysis and the parent CMIP6 GCMs, focusing on seasonal mean patterns, interannual variability, and the annual cycle. The WRF simulations demonstrate substantial improvement in capturing the spatial structures of monsoonal winds and regional circulation features. Future wind projections under SSP2-4.5 and SSP5-8.5 scenarios reveal seasonally and spatially heterogeneous trends. The downscaled models project strengthening of winter monsoon winds over the Southeast Asian seas and a weakening of summer monsoon flows, with implications for upper ocean dynamics and regional sea level patterns. The leading modes of variability from EOF analysis indicate basin-wide wind anomalies modulated by periodic signals at ~1 year and ~2–7 years, likely driven by ENSO and the Asian monsoon. The power spectra of principal components reveal that internal variability persists across scenarios, though with increased signal-to-noise ratios (SNRs) in the WRF projections toward the end of the 21st century. Full article