Numerical Weather Prediction Research Articles

A Model-Chain to Generate Q-/V-Band Attenuation Time Series From Short-Term Numerical Weather Predictions at Continental Scale

A Model-Chain to Generate Q-/V-Band Attenuation Time Series From Short-Term Numerical Weather Predictions at Continental Scale

The Schatten current sheet

Space weather models endeavoring to connect remote observations to in-situ measurements at various locations in the heliosphere invariably require a coronal model to connect the photosphere magnetically to the inner heliosphere. The most famous and popular implementation of this connection is a potential field source surface (PFSS) model out to the source surface, typically located at 2.5 solar radii, combined with a Schatten current sheet (SCS) model. While the PFSS model is mostly understood, the SCS has been utilized in heliospheric physics for nearly 50 years with little understanding of it’s physical and mathematical underpinnings. In this overview article, I lay out the mathematical formalism of the SCS, describe how it differs from the PFSS, and summarize several techniques used to combine the PFSS and SCS to create a global coronal model from the photosphere to the inner heliosphere.

Recommended coupling to global meteorological fields for long-term tracer simulations with WRF-GHG

Abstract. Atmospheric transport models are often used to simulate the distribution of greenhouse gases (GHGs). This can be in the context of forward modeling of tracer transport using surface–atmosphere fluxes or flux estimation through inverse modeling, whereby atmospheric tracer measurements are used in combination with simulated transport. In both of these contexts, transport errors can bias the results and should therefore be minimized. Here, we analyze transport uncertainties in the commonly used Weather Research and Forecasting (WRF) model coupled with the greenhouse gas module (WRF-GHG), enabling passive tracer transport simulation of CO2 and CH4. As a mesoscale numerical weather prediction model, WRF's transport is constrained by global meteorological fields via initialization and at the lateral boundaries of the domain of interest. These global fields were generated by assimilating various meteorological data to increase the accuracy of modeled fields. However, in limited-domain models like WRF, the winds in the center of the domain can deviate considerably from these driving fields. As the accuracy of the wind speed and direction is critical to the prediction of tracer transport, maintaining a close link to the observations across the simulation domain is desired. On the other hand, a link that is too close to the global meteorological fields can degrade performance at smaller spatial scales that are better represented by the mesoscale model. In this work, we evaluated the performance of strategies for keeping WRF's meteorology compatible with meteorological observations. To avoid the complexity of assimilating meteorological observations directly, two main strategies of coupling WRF-GHG with ERA5 meteorological reanalysis data were tested over a 2-month-long simulation over the European domain: (a) restarting the model daily with fresh initial conditions (ICs) from ERA5 and (b) nudging the atmospheric winds, temperatures, and moisture to those of ERA5 continuously throughout the simulation period, using WRF's built-in four-dimensional data assimilation (FDDA) in grid-nudging mode. Meteorological variables and simulated mole fractions of CO2 and CH4 were compared against observations to assess the performance of the different strategies. We also compared planetary boundary layer height (PBLH) with radiosonde-derived estimates. Either nudging or daily restarts similarly improved the meteorology and GHG transport in our simulations, with a small advantage of using both methods in combination. However, notable differences in soil moisture were found that accumulated over the course of the simulation when not using frequent restarts. The soil moisture drift had an impact on the simulated PBLH, presumably via changing the Bowen ratio. This is partially mitigated through nudging without requiring daily restarts, although not entirely alleviated. Soil moisture drift did not have a noticeable impact on GHG performance in our case, likely because it was dominated by other errors. However, since the PBLH is critical for accurately simulating GHG transport, we recommend transport model setups that tie soil moisture to observations. Our method of frequently re-initializing simulations with meteorological reanalysis fields proved suitable for this purpose.

High-Resolution Wind Speed Estimates for the Eastern Mediterranean Basin: A Statistical Comparison Against Coastal Meteorological Observations

Wind speed (and direction) estimated from numerical weather prediction (NWP) models is essential to wind energy applications, especially in the absence of reliable fine scale spatio-temporal wind information. This study evaluates four high-resolution wind speed numerical datasets (UERRA MESCAN-SURFEX, CERRA, COSMO-REA6, and NEWA) against in situ observations from coastal meteorological stations in the eastern Mediterranean basin. The evaluation is based on statistical comparisons of long-term wind speed data from 2009 to 2018 and involves an in-depth statistical comparison as well as a preliminary wind power density assessment at or near the meteorological station locations. The results show that while all datasets provide valuable insights into regional wind variability, there are notable differences in model performance. COSMO-REA6 and UERRA exhibit higher variability in wind speed but tend to underestimate extreme values, particularly in the southern coastal areas, whereas CERRA and NEWA provided closer fits to observed wind speeds, with CERRA showing the highest correlation at most stations. NEWA data, where available, overestimate average wind speeds but capture extreme values well. The comparison reveals that while all datasets provide valuable insights into the spatial and temporal variability of wind resources, their performance varies by location and season, emphasizing the need for the careful selection and potential calibration of these models for accurate wind energy assessments. The study provides essential groundwork for leveraging these datasets in planning and optimizing offshore wind energy projects, contributing to the region’s transition to renewable energy sources.

Assessing rainfall radar errors with an inverse stochastic modelling framework

Abstract. Weather radar is a crucial tool for rainfall observation and forecasting, providing high-resolution estimates in both space and time. Despite this, radar rainfall estimates are subject to many error sources – including attenuation, ground clutter, beam blockage and drop-size distribution – with the true rainfall field unknown. A flexible stochastic model for simulating errors relating to the radar rainfall estimation process is implemented, inverting standard weather radar processing methods and imposing path-integrated attenuation effects, a stochastic drop-size-distribution field, and sampling and random errors. This can provide realistic weather radar images, of which we know the true rainfall field and the corrected “best-guess” rainfall field which would be obtained if they were observed in a real-world case. The structure of these errors is then investigated, with a focus on the frequency and behaviour of “rainfall shadows”. Half of the simulated weather radar images have at least 3 % of their significant rainfall rates shadowed, and 25 % have at least 45 km2 containing rainfall shadows, resulting in underestimation of the potential impacts of flooding. A model framework for investigating the behaviour of errors relating to the radar rainfall estimation process is demonstrated, with the flexible and efficient tool performing well in generating realistic weather radar images visually for a large range of event types.

Long-term exposure to fine particulate matter constituents, genetic susceptibility, and incident heart failure among 411 807 adults.

Long-term fine particulate matter (PM2.5) exposure has been linked to incident heart failure (HF), but the impacts of its constituents remain unknown. We aimed to investigate the associations of PM2.5 constituents with incident HF, and further evaluate the modification effects of genetic susceptibility. PM2.5 and its constituents, including elemental carbon (EC), organic matter (OM), ammonium (NH4 +), nitrate (NO3 -), and sulfate (SO4 2-), were estimated using the European Monitoring and Evaluation Programme model applied to the UK (EMEP4UK) driven by Weather and Research Forecast model meteorology. A polygenic risk score (PRS) was calculated to represent genetic susceptibility to HF. We employed Cox models to evaluate the associations of PM2.5 constituents with incident HF. Quantile-based g-computation model was used to identify the main contributor of PM2.5 constituents. Among 411 807 individuals in the UK Biobank, 7554 participants developed HF during a median follow-up of 12.05 years. The adjusted hazard ratios of HF for each interquartile range increase in PM2.5, EC, OM, NH4 +, NO3 -, and SO4 2- were 1.50 (1.46-1.54), 1.31 (1.27-1.34), 1.12 (1.09-1.15), 1.42 (1.41-1.44), 1.26 (1.23-1.29), and 1.25 (1.24-1.26), respectively. EC (43%) played the most important role, followed by NH4 + and SO4 2-. Moreover, synergistic additive interactions accounted for 9-16% of the HF events in individuals exposed to both PM2.5, NH4 +, NO3 -, and SO4 2- and PRS. Long-term exposure to PM2.5 constituents may elevate HF risk, and EC was the major contributor. Additive effects of PM2.5 constituents and PRS on HF risk were revealed.

Convectively Induced Secondary Circulations and Wind‐Driven Heat Fluxes in the Surface Energy Balance Over Land

AbstractIncreased resolution has enabled kilometer‐scale weather and climate models to partially resolve secondary circulations, including horizontal convective rolls (HCRs) and cold pool gust fronts. Although these circulations are ubiquitous in convective boundary layers over land, their impacts on the surface energy balance are largely unknown. Doppler lidar and surface observations were combined with DOE E3SM land model experiments, revealing increased surface winds (5 m/s) and heat fluxes (50 W/m2) in convergent branches of HCRs. Larger wind‐driven flux responses (up to 150 W/m2) were found along gust fronts. Surface energy balance shifts to accommodate wind‐driven fluxes, reducing ground heat conduction and longwave cooling. Our findings from the US Southern Great Plains are broadly relevant to modeling convective boundary layers. In particular, widely used subgrid wind gust parameterizations were found to be physically inconsistent with resolved secondary circulations and could worsen climate prediction biases at kilometer‐scales.

RUFCO: a deep-learning framework to post-process subseasonal precipitation accumulation forecasts

Abstract Post-processing is a critical step in attaining calibrated and reliable probabilistic forecast output from numerical weather prediction models. A novel deep-learning framework is proposed to post-process 20 years of 7- and 14-day precipitation accumulation reforecasts from the Global Ensemble Forecast System at subseasonal timescales (week 1, week 2, and combined weeks 3-4 forecasts) over the contiguous United States. The network builds upon previous studies and is a combination of three parallel-trained components suitable for subseasonal prediction. The first is a ResUnet architecture which learns non-linear relationships between binned observed precipitation and input images of weather and geographical variables. The second conditions the network to the month-of-year via a Feature-wise Linear Modulation (FiLM) layer. The third helps the network learn when to revert the forecast to that of climatology. The RUFCO (named for its components ResUnet, FiLM, and Climatological-Offramp) forecasts are compared against raw and climatological forecasts as well as those from a state-of-the-art distributional regression post-processing model, “CSGD,” and a simple bias-corrected model. At week 1, every method exhibited a competitive advantage over climatological forecasts. At week 2, RUFCO generated forecasts with statistically significant improvement over climatology at 82-94% of the domain, beating CSGD’s coverage of 76-90% of the grid points. At week 3, RUFCO’s skillful coverage was 65-85% while CSGD’s dropped to only 12-37%. At the longer lead times, RUFCO achieved the highest domain-averaged skill scores across seasons. However, the network tends to “smooth” forecast skill making it less competitive with CSGD in limited areas with strongly spatially-varying biases.

Dynamical downscaling and data assimilation for a cold-air outbreak in the European Alps during the Year Without a Summer of 1816

Abstract. The “Year Without a Summer” in 1816 was characterized by extraordinarily cold and wet periods in central Europe, and it was associated with severe crop failures, famine, and socio-economic disruptions. From a modern perspective, and beyond its tragic consequences, the summer of 1816 represents a rare opportunity to analyze the adverse weather (and its impacts) after a major volcanic eruption. However, given the distant past, obtaining the high-resolution data needed for such studies is a challenge. In our approach, we use dynamical downscaling, in combination with 3D variational data assimilation of early instrumental observations, for assessing a cold-air outbreak in early June 1816. We find that the cold spell is well represented in the coarse-resolution 20th Century Reanalysis product which is used for initializing the regional Weather Research and Forecasting Model. Our downscaling simulations (including a 19th century land use scheme) reproduce and explain meteorological processes well at regional to local scales, such as a foehn wind situation over the Alps with much lower temperatures on its northern side. Simulated weather variables, such as cloud cover or rainy days, are simulated in good agreement with (eye) observations and (independent) measurements, with small differences between the simulations with and without data assimilation. However, validations with partly independent station data show that simulations with assimilated pressure and temperature measurements are closer to the observations, e.g., regarding temperatures during the coldest night, for which snowfall as low as the Swiss Plateau was reported, followed by a rapid pressure increase thereafter. General improvements from data assimilation are also evident in simple quantitative analyses of temperature and pressure. In turn, data assimilation requires careful selection, preprocessing, and bias-adjustment of the underlying observations. Our findings underline the great value of digitizing efforts of early instrumental data and provide novel opportunities to learn from extreme weather and climate events as far back as 200 years or more.

Developing a Workflow for Transforming BIM Models into Immersive Virtual Reality Experiences

Abstract. The integration of Extended Reality (XR) and Building Information Modelling (BIM) has emerged as a promising approach for enhancing interaction with spatial data in the built environment. While the potential of BIM for advanced visualization has been recognized, there remains a need for standardized workflows that facilitate the transformation of BIM models into immersive virtual reality (VR) experiences. This research contributes to the ongoing development of BIM-VR integration by presenting a workflow that leverages Revit, Twinmotion, and Datasmith to create visually rich and interactive VR environments. The established process focuses on enhancing textures, incorporating dynamic lighting and weather simulations, and populating the virtual space with realistic elements. The workflow also addresses the integration of interactable objects to elevate user engagement and the use of cutting-edge VR headsets for an immersive experience. By providing a structured approach to bridging complex BIM data with VR, this research aims to support architects, engineers, construction professionals, and clients in design collaboration, project review, and decision-making across the building lifecycle. The workflow's potential for facilities management and training applications is also explored. Through a case study, the research demonstrates the workflow's effectiveness in facilitating a deeper understanding of architectural spaces before construction, highlighting its potential for improving efficiency and reducing rework. The paper also discusses the challenges and opportunities associated with integrating BIM with GIS and sensor data to create comprehensive digital twins. This research contributes to the growing body of knowledge on BIM-VR integration and underscores the importance of continued development in this field to enhance the design, communication, and experience of the built environment.

Simulation of the Neutral Atmospheric Flow Using Multiscale Modeling: Comparative Studies for SimpleFoam and Fluent Solver

The reproduced planetary boundary layer (PBL) wind is commonly applied in downscaled simulations using commercial CFD codes with Reynolds-averaged Navier–Stokes (RANS) turbulence modeling. When using the turbulent inlets calculated by numerical weather prediction models (NWP), adjustments of the turbulence eddy viscosity closures and wall function formulations are concerned with maintaining the fully developed wind profiles specified at the inlet of CFD domains. The impact of these related configurations is worth discussing in engineering applications, especially when commercial codes restrict the internal modifications. This study evaluates the numerical performances of open-source OpenFOAM 2.3.0 and commercial Fluent 17.2 codes as supplementary scientific comparisons. This contribution focuses on the modified turbulence closures to incorporate turbulent profiles produced from mesoscale PBL parameterizations and the modified wall treatments relating to the roughness length. The near-ground flow features are evaluated by selecting the flat terrains and the classical Askervein benchmark case. The improvement in near-ground wind flow under the downscaled framework shows satisfactory performance in the open-source CFD platform. This contributes to engineers realizing the micro-siting of wind turbines and quantifying terrain-induced speed-up phenomena under the scope of wind-resistant design.

Weather Prediction with Machine Learning

Weather forecasting is the technical process of predicting atmospheric conditions at a location. Many scientists have also been trying to predict the weather, both formally and informally, for years. Weather forecasting is done by collecting data from specific locations with different climate attributes. Traditional numerical weather prediction models have made significant progress, but there are still limitations in their accuracy, especially in detecting local weather events. In recent years, machine learning techniques have become a powerful tool for improving weather forecasts by exploiting the large amounts of data and complex patterns inherent in atmospheric systems. We propose a machine- learning model that uses historical data to train the model. The model is then used to predict weather with better accuracy than traditional models.

How inaccurate offshore wind observations impact the quality of operational numerical weather prediction

AbstractAt Norwegian offshore platforms, wind speed is observed at heights between approx. 35 and approx. 150 m a.s.l. These observations are used to estimate 10‐m wind speed, by a power law with a constant wind shear coefficient. The resulting 10‐m wind speed is then distributed to the Global Telecommunication System (GTS) and used for assimilation and verification purposes by the meteorological community. However, multiple methods with varying results exist for the reduction of wind speed from the original measurement height to 10 m. The resulting estimate of 10‐m wind speed is therefore sensitive to the choice of method. The use of such observations may therefore be suboptimal in forecast analysis and make the forecast verification difficult to interpret. This study investigates how the use of these observations impacts forecasts from the operational regional forecast system used at MET Norway and the Global Integrated Forecast System operated by ECMWF for the period 2017–2023. Both forecast systems assimilated the observations over major parts of the period and the presented results indicate that the use of these observations increased the initial errors in the forecasts. This is confirmed in a data denial experiment over a shorter period of time. The verification results show that both forecast systems underestimate the wind speed at the original measurement heights, while the results for 10‐m verification vary with the interpolation method between original sensor height and 10 m. The forecasts show in general more wind than the GTS‐distributed estimates and are in better agreement with more advanced interpolation methods. The verification results show a strong dependency on the vertical stability of the atmosphere. The major differences between the forecast systems are that the regional system shows less bias, while the standard deviations of the errors are slightly lower in the global system.

Studies on Heavy Precipitation in Portugal: A Systematic Review

This systematic review, based on an adaptation of the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement from 2020, focuses on studies of the atmospheric mechanisms underlying extreme precipitation events in mainland Portugal, as well as observed trends and projections. The 54 selected articles cover the period from 2000 to 2024, in which the most used keywords are “portugal” and “extreme precipitation”. Of the 54, 23 analyse trends and climate projections of precipitation events, confirming a decrease in total annual precipitation, especially in autumn and spring, accompanied by an increase in the frequency and intensity of extreme precipitation events in autumn, spring and winter. Several articles (twelve) analyse the relationship between synoptic-scale circulation and heavy precipitation, using an atmospheric circulation types approach. Others (two) establish the link with teleconnection patterns, namely the North Atlantic Oscillation (NAO), and still others (three) explore the role of atmospheric rivers. Additionally, five articles focus on evaluating databases and Numerical Weather Prediction (NWP) models, and nine articles focus on precipitation-related extreme weather events, such as tornadoes, hail and lightning activity. Despite significant advances in the study of extreme precipitation events in Portugal, there is still a lack of studies on hourly or sub-hourly scales, which is critical to understanding mesoscale, short-lived events. Several studies show NWP models still have limitations in simulating extreme precipitation events, especially in complex orography areas. Therefore, a better understanding of such events is fundamental to promoting continuous improvements in operational weather forecasting and contributing to more reliable forecasts of such events in the future.

Role of midtropospheric heating and surface forcing on monsoon intraseasonal transitions

AbstractMonsoon intraseasonal transitions are intrinsically chaotic; hence, their predictability is limited. In the past the majority of studies were conducted solely keeping in account of dynamic prospective like boreal summer intraseasonal oscillation or Madden–Julian oscillation; however its thermodynamic aspect got limited attention. The current study looks at the internal thermodynamic mechanisms pertaining to monsoon intraseasonal transition using two independent sets of reanalysis data (European Centre for Medium‐range Weather Forecasts Reanalysis version 5 and Indian Monsoon Data Assimilation and Analysis), along with the observed cloud type from Met Office Integrated Data Archive System Land and Marine surface station data. A lead–lag composite analysis shows that the midtropospheric warming by diabatic heating is a thermal control to restrict the deepening of convective cloud (cumulonimbus) as the wet spell progresses. This midtroposhperic heating cuts off the formation of deep convective clouds and results in the formation of relatively shallow clouds, such as stratocumulus and stratus. On the other hand, surface forcing during dry spells humidifies the troposphere by detrainment from the shallow convection with the formation of cumulus and cumulus congestus clouds. This facilitates the preconditioning of the atmosphere for deep convection and results in the onset of wet spells by the formation of cumulonimbus clouds. The comprehensive approach used in this work may further help in identifying the limitation of the predictability in monsoon transition period from the numerical weather prediction models.

Improved Orographic Gravity Wave Drag Parameterization Accounting for the Nonhydrostatic Effect in the Weather Research and Forecasting Model: Tests for Short-Range Forecast of Northeast China Cold Vortices

Abstract The parameterization of orographic gravity wave drag (OGWD) is essential for accurate numerical weather prediction in regions of complex terrain. Current OGWD schemes assume hydrostatic OGWs but the parameterized OGWs in fine-resolution models with narrow subgrid-scale orography can be significantly affected by the nonhydrostatic effects (NHE). In our recent work, the OGWD scheme in the Model for Prediction Across Scales (MPAS) was revised by accounting for the NHE on the surface wave momentum flux of upward-propagating OGWs. Herein, the revised OGWD scheme is implemented in the Weather Research and Forecasting (WRF) model to evaluate its performance in short-range weather forecast. Two sets of 36-hr WRF simulations are conducted for nine Northeast China cold vortices (NECVs) that occurred in the warm season of 2011 using the original and revised OGWD schemes. Results show that the WRF model tends to underestimate the intensity of the NECVs, producing too high geopotential height. When accounting for the NHE in the OGWD scheme, the NECV intensity biases are significantly reduced. Analyses reveal that the NHE act to weaken the lower-tropospheric OGWD by decreasing the surface wave momentum flux, which strengthens the NECV in the lower troposphere. Consequently, the strengthened low-level cyclonic circulation increases the post-trough cold advection to the southwest of the NECV which in turn enhances the NECV in the mid-upper troposphere with reduced geopotential height. The NHE are found to increase as the model horizontal resolution increases, suggesting greater importance of the NHE in the OGWD parameterization of high-resolution numerical models.

Weathering words: a virtual reality study of environmental influence on reading dynamics.

Reading is a fundamental cognitive activity that is influenced by both textual and external environmental factors, although the latter has been less thoroughly explored. This study aims to examine the impact of environmental visual conditions on reading performance using Virtual Reality (VR) technology. We conducted two experiments to assess the effects of visual contrast and simulated weather conditions on reading dynamics. In Experiment 1, we measured single-word recognition speed using a lexical decision task under different visual contrasts and weather conditions. In Experiment 2, we assessed reading dynamics during a sentence reading task, analyzing how visual contrast and simulated sunny versus rainy weather conditions affected reading behavior, particularly focusing on reading speed and eye fixations. In Experiment 1, high visual contrast, particularly under sunny conditions, significantly enhanced single-word recognition speed, indicating a notable influence of environmental visual conditions. In Experiment 2, visual contrast had minimal effect on sentence reading; however, sunny weather facilitated faster reading times, while rainy scenarios increased the number of eye fixations. These findings suggest that environmental factors, such as weather conditions, can significantly affect reading behavior. The study contributes to the understanding of key environmental influences on reading in everyday life contexts and has implications for the ergonomic design of reading materials, especially for outdoor settings and VR environments. Additionally, the integration of controlled stimuli within VR increases the ecological validity of reading research, underscoring the potential of VR as a powerful tool for cognitive research.

Towards a 2DEnVar surface data assimilation approach within the convective scale numerical weather prediction model AROME‐France

AbstractSurface data assimilation (DA) plays a key role in the initialisation of soil variables in coupled surface–atmosphere numerical weather prediction (NWP) models. Météo‐France, as many other NWP centres, uses an operational surface DA method based on an optimal interpolation (OI), implemented more than 30 years ago. The current surface DA system implemented at Météo‐France in the operational limited‐area AROME‐France model operates in two steps. First, a two‐dimensional OI method analyses the diagnostic screen‐level parameters, which are then used to initialise the prognostic soil variables according to a one‐dimensional OI method. This article presents the implementation and the results of a new two‐dimensional ensemble‐based variational (2DEnVar) system, using the object‐oriented prediction system framework, for the diagnostic screen‐level variable analyses (2‐m temperature and 2‐m relative humidity) within the AROME‐France model. These analysed variables are then used to initialise the soil temperature and soil moisture of the first and second soil layers. A two‐dimensional variational system is initially implemented and compared with an equivalent system that uses an OI surface analysis. The comparison of 2‐m temperature increments shows that the two systems behave in a similar way. From this two‐dimensional variational approach, a 2DEnVar scheme is developed and compared with the OI screen‐level analysis used operationally (reference system). The results are encouraging even though a degradation in forecast quality is noticed at short ranges for 2‐m temperature and 2‐m relative humidity. This is mainly due to a low spread near the surface in the ensemble‐based data assimilation that is used to compute background‐error covariances in 2DEnVar. Sensitivity tests have been performed to improve the initial version of the 2DEnVar scheme. A positive and significant impact is noticed when a multiplicative inflation is applied to the background perturbations coming from the ensemble‐based data assimilation for the computation of 2‐m temperature and 2‐m relative humidity background‐error covariances. Finally, when comparing the inflated 2DEnVar system with the reference, the two systems behave similarly. This suggests that the 2DEnVar scheme, based on ensemble statistics, is capable of properly reconstructing background‐error structures derived from the empirical correlations described in OI.

An Ultra‐Short‐Term Wind Power Prediction Method Based on Spatiotemporal Characteristics Fusion

ABSTRACTAiming at the problem that the existing ultra‐short‐term wind power prediction methods lack consideration of the spatial correlation characteristics of wind farms, resulting in insufficient prediction accuracy, an ultra‐short‐term wind power prediction method based on spatiotemporal characteristics fusion is proposed in this article. First, the fluctuation difference of the time window of wind power is input into the K‐means clustering algorithm to cluster wind farms into several clusters based on power fluctuation similarity. Then, the principal component analysis algorithm is used to reduce the dimensionality of numerical weather prediction data combinations in different regions to reduce the impact of redundant information on modeling accuracy. Finally, a convolutional long‐short‐term memory neural network is designed to extract spatiotemporal features of wind power data and output prediction results. The experimental verification on 18 wind farms in a province in China shows that the proposed wind power prediction method has an average root mean square error of only 0.1257 and has certain applicability.

Numerical Weather Prediction of Sea Surface Temperature in South China Sea Using Attention-Based Context Fusion Network

Numerical weather prediction of sea surface temperature (SST) is crucial for regional operational forecasts. Deep learning offers an alternative approach to traditional numerical general circulation models for numerical weather prediction. In our previous work, we developed a sophisticated deep learning model known as the Attention-based Context Fusion Network (ACFN). This model integrates an attention mechanism with a convolutional neural network framework. In this study, we applied the ACFN model to the South China Sea to evaluate its performance in predicting SST. The results indicate that for a 1-day lead time, the ACFN model achieves a Mean Absolute Error of 0.215 °C and a coefficient of determination (R2) of 0.972. In addition, in situ buoy data were utilized to validate the forecast results. The Mean Absolute Error for forecasts using these data increased to 0.500 °C for a 1-day lead time, with a corresponding R2 of 0.590. Comparative analyses show that the ACFN model surpasses traditional models such as ConvLSTM and PredRNN in terms of accuracy and reliability.