← Back to all news
arXiv Machine Learning By Xuefei Wang, Tingyi Liu, Heng Zhang, Shengjun Zhang

Frequency-aware forecasting for short-term typhoon gust prediction

Read the original on arXiv Machine Learning →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Sep 25

Neuralized Multi-Wavelet Decomposition for Time Series Classification and Forecasting

The paper introduces m-WCN, an end‑to‑end deep learning framework that neuralizes multi‑wavelet decomposition to jointly extract temporal patterns and frequency components from time series. Two task‑specific architectures built on m‑WCN—TFBC for classification and FTB for forecasting—are shown to outperform baseline models on 64 UCR datasets and seven forecasting benchmarks, achieving average improvements of nearly 20% in both tasks. The approach leverages trainable convolutional operators and orthogonality constraints to produce interpretable multi‑resolution representations.

By Xiaohan Jiang, Jingyuan Wang, Jiahao Ji, Yongyao Wang, Chen Yang, Junjie Wu
benchmarks
More like this →
Hugging Face Trending Papers
Sep 24

Neuralized Multi-Wavelet Decomposition for Time Series Classification and Forecasting

The paper introduces m-WCN, an end‑to‑end deep learning framework that neuralizes multi‑wavelet decomposition to jointly extract temporal patterns and frequency components from time series. It enforces orthogonality constraints to produce interpretable multi‑resolution representations, and builds two task‑specific architectures—TFBC for classification and FTB for forecasting—on top of this foundation. Experiments on 64 UCR datasets and seven forecasting benchmarks show that TFBC and FTB outperform baseline models, achieving average improvements of about 20% in both classification and forecasting tasks.

benchmarks
More like this →