This review summarizes recent advances in wind speed forecasting using artificial intelligence. It systematically analyzes multi-scale signal decomposition methods and intelligent model fusion strategies, highlighting their effectiveness in addressing the challenges of nonstationary and multiscale wind data. By identifying key methodological patterns and gaps, the review offers actionable insights for designing more accurate, efficient, and robust AI-based wind forecasting systems.

Critically Endangered female angelsharks (Squatina squatina) are changing normal mating routines in warming oceans as they prioritise staying cool over visiting breeding grounds when things get too hot.

These changes are creating a potential mismatch in the mating behaviours between the sexes of angelshark that could have severe consequences for the future of the species, scientists say.

Reviving floodplain wetlands slashes carbon emissions by 39% and restores critical ecosystem functions in one year – without the methane spike typically seen in restored peatlands, a new study has found.

Layered sodium manganese oxide (NaMnO₂), especially its β-phase, has received considerable attention for use as cathodes in sodium-ion batteries. However, β-NaMnO₂ exhibits stacking faults (SFs), which severely reduce its cycling stability. In a new study, researchers studied how copper-doping can eliminate SFs in β-NaMnO₂, significantly improving cycling stability. This strategy can lead to the development of longer-lasting sodium-ion batteries, leading to more affordable energy-storage solutions.