Accurate wind speed prediction is crucial for the safe and efficient utilization of wind resources. However, current single-value deterministic numerical weather prediction methods employed by wind farms do not adequately meet the actual needs of power grid dispatching. In this study, we propose a new hybrid forecasting method for correcting 10 m wind speed predictions made by the Weather Research and Forecasting (WRF) model. Our approach incorporates variational mode decomposition (VMD), principal component analysis (PCA), and five artificial intelligence algorithms: deep belief network (DBN), multilayer perceptron (MLP), random forest (RF), eXtreme gradient boosting (XGBoost), light gradient boosting machine (lightGBM), and the Bayesian optimization algorithm (BOA). We first predict wind speeds using the WRF model, with initial and lateral boundary conditions from the Global Forecast System (GFS). We then perform two sets of experiments with different input factors and apply BOA optimization to tune the four artificial intelligence models, ultimately building the final models. Furthermore, we compare the aforementioned five optimal artificial intelligence models suitable for five provinces in southern China in the wintertime: VMD-PCA-RF in December 2021 and VMD-PCA-lightGBM in January 2022. We find that the VMD-PCA-RF evaluation indices exhibit relative stability over nearly a year: the correlation coefficient (R) is above 0.6, forecasting accuracy (FA) is above 85 %, mean absolute error (MAE) is below 0.6 m s⁻¹, root mean square error (RMSE) is below 0.8 m s⁻¹, relative mean absolute error (rMAE) is below 60 %, and relative root mean square error (rRMSE) is below 75 %. Thus, for its promising performance and excellent year-round robustness, we recommend adopting the proposed VMD-PCA-RF method for improved wind speed prediction in models.

The planetary boundary layer height (PBLH) is a crucial indicator reflecting the region of the atmosphere characterized by continuous turbulence. Here, we use radiosonde and surface meteorological observations (4–7 times per day, year‐round measurements) during the Multidisciplinary drifting Observatory for the Study of Arctic Climate (MOSAiC) expedition to derive the PBLH (PBLH_MOSAiC), and further evaluate the PBLH from the ERA5 reanalysis (PBLH_ERA5). Comparisons between PBLH_MOSAiC and PBLH_ERA5 from different perspectives reveal that: (a) The overestimation of PBLH_ERA5 when the sea ice concentration is >90% is significant with the centered root mean squared error reaching up to 201 m; (b) The difference between the two products is notably pronounced in cold seasons, while it is comparatively diminished in warm seasons; (c) In neutral boundary layers, differences in PBLH_ERA5 are larger compared with stable and convective boundary layers. In addition, the analysis of error sources indicates that the bias of PBLH_ERA5 is sensitive to the bias of vertical thermal structure and wind speed profiles in ERA5 data sets in all conditions. Finally, we find a Random Forest model effectively reduces the bias of PBLH_ERA5 with the index of agreement reaching up to 0.71 in the test data set, while a multiple linear regression demonstrates comparable performance to the Random Forest model.

The correlations between the planetary boundary layer height (PBLH) and surface meteorological factors, including the surface wind speed (R_WS), temperature (R_TS), specific humidity (R_SH), pressure (R_PS), and lower tropospheric stability (R_LTS), are investigated using hourly profiles from the Aircraft Meteorological Data Reports at 54 major airports over the contiguous United States (CONUS) and surface observations from weather stations. At the diurnal cycle, the R_WS and R_TS are positive and the R_PS and R_LTS are negative across the CONUS, while the R_SH is negative over most areas but tends to be positive in the inland humid region. At the annual cycle, the correlations show significant diurnal variations that cannot be well captured by routine twice‐daily radiosonde data. The R_WS is significantly positive at night but less significant during the daytime over most regions. The R_TS and R_SH are positive and the R_PS and R_LTS are negative at the daytime, which are of the opposite sign at the nighttime, with exceptions in some coastal areas. The diurnal variations of the correlations at the annual cycle also exhibit significant geographic variability, with the diurnal variation generally stronger in central eastern humid areas, weaker in some coastal areas, and moderate in relatively arid or mountain areas. This study highlights that the correlations between the PBLH and meteorological variables depend on the thermal stratification and are affected by the local hydrological and synoptic factors.

The effects of atmospheric thermal structure on the surface energy flux are poorly understood over the Arctic sea‐ice surface. Here, we explore the mechanism of sensible heat exchange under different types of thermal structures over the Arctic sea‐ice surface by using data collected during the Multidisciplinary drifting Observatory for the Study of Arctic Climate expedition. The quadrant analysis indicates that strong surface temperature inversions below 100 m enhance non‐local effects on the positive (upward) sensible heat flux () through entrainment of large eddies from the convective boundary layer aloft. However, strong surface inversions restrict the contributions of large eddies to the negative (downward) due to intensified surface stability. By inspecting the existing parameterization schemes, we found that the European Center for Medium‐Range Weather Forecasts Integrated Forecasting System scheme fails to predict the impacts of non‐local processes on the positive , and an adjustment term to correct the bias of parameterized is proposed.

Accurate real-time icing grid fields are critical for preventing ice-related disasters during winter and protecting property. These fields are essential for both mapping ice distribution and predicting icing using physical models combined with numerical weather prediction systems. However, developing precise real-time icing grids is challenging due to the uneven distribution of monitoring stations, data confidentiality restrictions, and the limitations of existing interpolation methods. In this study, we propose a new approach for constructing real-time icing grid fields using 1339 online terminal monitoring datasets provided by the China Southern Power Grid Research Institute Co., Ltd. (CSPGRI) during the winter of 2023. Our method integrates static geographic information, dynamic meteorological factors, and ice_kriging values derived from parameter-optimized Empirical Bayesian Kriging Interpolation (EBKI) to create a spatiotemporally matched, multi-source fused icing thickness grid dataset. We applied five machine learning algorithms—Random Forest, XGBoost, LightGBM, Stacking, and Convolutional Neural Network Transformers (CNNT)—and evaluated their performance using six metrics: R, RMSE, CSI, MAR, FAR, and fbias, on both validation and testing sets. The stacking model performed best, achieving an R-value of 0.634 (0.893), RMSE of 3.424 mm (2.834 mm), CSI of 0.514 (0.774), MAR of 0.309 (0.091), FAR of 0.332 (0.161), and fbias of 1.034 (1.084), respectively, when comparing predicted icing values with actual measurements on pylons. Additionally, we employed the SHAP model to provide a physical interpretation of the stacking model, confirming the independence of selected features. Meteorological factors such as relative humidity (RH), 10 m wind speed (WS₁₀), 2 m temperature (T₂), and precipitation (PRE) demonstrated a range of positive and negative contributions consistent with the observed growth of icing. Thus, our multi-source remote-sensing data-fusion approach, combined with the stacking model, offers a highly accurate and interpretable solution for generating real-time icing grid fields.

Accurate real-time icing grid fields are critical for preventing ice-related disasters during winter and protecting property. These fields are essential both for mapping ice distribution and for predicting icing using physical models combined with numerical weather prediction systems. However, developing precise real-time icing grids is challenging due to the uneven distribution of monitoring stations, data confidentiality restrictions, and the limitations of existing interpolation methods. In this study, we propose a new approach for constructing real-time icing grid fields using 1,339 online terminal monitoring datasets provided by the China Southern Power Grid Research Institute Co., Ltd. (CSPGRI) during the winter of 2023. Our method integrates static geographic information, dynamic meteorological factors, and ice_kriging values derived from parameter-optimized Empirical Bayesian Kriging Interpolation (EBKI) to create a spatiotemporally matched, multi-source fused icing thickness grid dataset. We applied five machine learning algorithms—Random Forest, XGBoost, LightGBM, Stacking, and Convolutional Neural Network Transformers (CNNT)—and evaluated their performance using six metrics: R, RMSE, CSI, MAR, FAR, and fbias, on both validation and testing sets. The stacking model performed best, achieving an R value of 0.634 (0.893), RMSE of 3.424 mm (2.834 mm), CSI of 0.514 (0.774), MAR of 0.309 (0.091), FAR of 0.332 (0.161), and fbias of 1.034 (1.084), respectively, when comparing predicted icing values with actual measurements on pylons. Additionally, we employed the SHAP model to provide a physical interpretation of the stacking model, confirming the independence of selected features. Meteorological factors such as relative humidity (RH), 10-meter wind speed (WS10), 2-meter temperature (T2), and precipitation (PRE) demonstrated a range of positive and negative contributions consistent with the observed growth of icing. Thus, our multi-source remote sensing data fusion approach, combined with the stacking model, offers a highly accurate and interpretable solution for generating real-time icing grid fields.