arXiv AI

WaveHiTS: Wavelet-Enhanced Hierarchical Time Series Modeling for Wind Direction Nowcasting in Eastern Inner Mongolia

arXiv Machine Learning
Aug 27

Frequency-aware forecasting for short-term typhoon gust prediction

The paper introduces WDANet, a frequency‑aware forecasting framework that uses stationary wavelet decomposition, FiLM, and a dual‑branch encoder‑decoder to separately model trend and fluctuation components in typhoon gust prediction. Applied to offshore Western Pacific wind data, WDANet outperforms ECMWF‑HRES for short lead times, achieving higher accuracy within the first 6 hours and better RMSE/MAE during extreme wind events. The study suggests WDANet could improve offshore wind power operations, disaster warnings, and risk mitigation.

By Xuefei Wang, Tingyi Liu, Heng Zhang, Shengjun Zhang
arXiv AI
Jun 18

A Hybrid LSTM--Vision Transformer Architecture for Predicting HRRR Forecast Errors

arXiv:2606. 19026v1 Announce Type: cross Abstract: Forecast errors in high-resolution numerical weather prediction (NWP) systems are often linked to unresolved planetary boundary layer (PBL) processes, convection, terrain-induced circulations, and other vertically structured atmospheric phenomena.

By David Aaron Evans, Jay C. Rothenberger, Kara J. Sulia, Nick P. Bassill, Chris D. Thorncroft
arXiv Machine Learning
Sep 7

WaveletDiff: Multilevel Wavelet Diffusion For Time Series Generation

WaveletDiff is a diffusion-based framework that generates time series by training directly on wavelet coefficients, leveraging multi-resolution structure through level‑specific transformers and cross‑level attention with adaptive gating. The model incorporates Parseval‑theorem‑based energy constraints to preserve time‑frequency properties during diffusion. Experiments on six real‑world datasets from energy, finance, and neuroscience show that WaveletDiff outperforms several diffusion baselines and competes with the VAE/transformer‑based MSDformer, achieving lower discriminative and Context‑FID scores while using fewer parameters and less training time.

By Yu-Hsiang Wang, Olgica Milenkovic