Short‐term wind speed prediction is essential for economical wind power utilization. The real‐world wind speed data are typically intermittent and fluctuating, presenting great challenges to existing shallow models. In this paper, we present a novel deep hybrid model for multistep wind speed prediction, namely, LR‐FFT‐RP‐MLP/LSTM (linear fast Fourier transform rank pooling multiple‐layer perceptron/long short‐term memory). Our hybrid model processes the local and global input features simultaneously. We leverage RP for the local feature extraction to capture the temporal structure while maintaining the temporal order. Besides, to understand the wind periodic patterns, we exploit FFT to extract global features and relevant frequency components in the wind speed data. The resulting local and global features are, respectively, integrated with the original data and are fed into an MLP/LSTM layer for the initial wind speed predictions. Finally, we leverage a linear regression layer to collaborate these initial predictions to produce the final wind speed prediction. The proposed hybrid model is evaluated using real wind speed data collected from 2010 to 2020, demonstrating superior forecasting capabilities when compared with state‐of‐the‐art single and hybrid models. Overall, this study presents a promising approach for improving the accuracy of wind speed forecasting.

Hazardous gas emissions, including volatile organic compounds (VOCs), nitrogen oxides (NO _x ), sulfur dioxide (SO₂), elemental mercury (Hg⁰), carbon dioxide (CO₂), and chemical warfare agents (CWAs), pose severe threats to human health and the environment, driving the need for efficient, cost-effective removal technologies. Activated carbon (AC), renowned for its high surface area, tunable porosity, and economic viability, serves as an ideal support for transition metal modification (e.g., Mn, Fe, Co, Ni, Cu, Zn), which imparts enhanced catalytic activity and selectivity through redox and acid–base functionalities. This review systematically summarizes recent advances in transition metal-modified ACs for hazardous gas elimination, covering preparation methodologies (impregnation, doping, sol–gel, and composites), adsorption mechanisms (physisorption vs chemisorption, and diffusion processes), key influencing factors (pore structure, surface chemistry, metal dispersion, gas properties, and operational conditions), and practical applications across diverse pollutants. Key insights highlight the synergistic roles of metal loading in bridging physical adsorption and catalytic conversion, while addressing challenges such as pore blockage, humidity interference, and multipollutant competition. Future perspectives prioritize operando mechanistic studies, scalable engineering processes, and precision synthesis to bridge the gap between fundamental research and industrial application, achieving scalable, high-performance solutions for real-world environmental remediation.

Wind direction forecasting plays a crucial role in optimizing wind energy production, but faces significant challenges due to the circular nature of directional data, error accumulation in multi-step forecasting, and complex meteorological interactions. This paper presents a novel model, WaveHiTS, which integrates wavelet transform with Neural Hierarchical Interpolation for Time Series to address these challenges. Our approach decomposes wind direction into U-V components, applies wavelet transform to capture multi-scale frequency patterns, and utilizes a hierarchical structure to model temporal dependencies at multiple scales, effectively mitigating error propagation. Experiments conducted on real-world meteorological data from Inner Mongolia, China demonstrate that WaveHiTS significantly outperforms deep learning models (RNN, LSTM, GRU), transformer-based approaches (TFT, Informer, iTransformer), and hybrid models (EMD-LSTM). The proposed model achieves RMSE values of approximately 19.2°-19.4° compared to 56°-64° for deep learning recurrent models, maintaining consistent accuracy across all forecasting steps up to 60 minutes ahead. Moreover, WaveHiTS demonstrates superior robustness with vector correlation coefficients (VCC) of 0.985-0.987 and hit rates of 88.5\%-90.1\%, substantially outperforming baseline models. Ablation studies confirm that each component—wavelet transform, hierarchical structure, and U-V decomposition—contributes meaningfully to overall performance. These improvements in wind direction nowcasting have significant implications for enhancing wind turbine yaw control efficiency.

The stable boundary layer (SBL) over land exhibits pronounced vertical decoupling and structural heterogeneity that remain challenging to diagnose using routine operational monitoring. Here, we utilize a three-year continuous multi-level tower dataset ($N=\mathrm{40,630}$ quality-controlled 15-min records at 2, 10, 20, and 50 m) over the Horqin Grassland to characterize stability-dependent modifications of surface-layer wind structure and near-surface kinetic energy. Using the bulk Richardson number ($R{i}_b$) and raw thermal gradients ($\Delta T_v/\Delta z$), we identify a stability-driven reduction in vertical wind coupling, with a statistical change-point cluster centered near $R{i}_b\approx 0.30$ (95% CI: 0.09–0.52). Cross-level correlation analysis empirically localizes a structural transition zone to the 10–20 m interval, separating a faster, shear-driven upper layer from a dynamically suppressed near-surface flow under strong stability. Concurrently, near-surface horizontal kinetic energy ($HK{E}_{02}$) undergoes a 47% (nighttime) to 55% (full-record) median reduction, while horizontal wind-direction variability (${\sigma }_{\theta \_02}$) broadens due to low-wind meandering, and sub-hourly vertical velocity variance (${\sigma }_{w,\mathrm{LF}}^2$) is suppressed by 57–72% across all heights. Multidimensional scaling (MDS) reveals a statistically significant phase-space compaction under high stability (${\tilde{d}}_{\mathrm{high}}=2.13$ vs. ${\tilde{d}}_{\mathrm{low}}=2.67$, $p<0.001$), with adjusted odds ratios highlighting thermal gradient ($\mathrm{OR}=5.80$), wind shear ($\mathrm{OR}=1.52$), and directional variability ($\mathrm{OR}=1.34$) as dominant positive predictors. These empirical patterns remain robust under temporal-holdout validation (Year-1 calibration vs. Years 2–3 validation; consensus breakpoint $R{i}_b=0.161$ vs. $0.156$) and seasonal/wind-speed stratifications. The results demonstrate that routine 15-min multi-level tower networks provide valuable observational constraints on surface-layer structural transitions, informing boundary-layer parameterizations in numerical weather prediction models and near-surface dispersion assessments.