paper
2019
Local & station forecasting
Applications & impacts New model or method
RNN / LSTM / ConvLSTMClassical ML (trees, GP, linear, kernels)6 h–3 days Journal
2019-05-30
018
May 2019
Yu‐Xi Wu, Qingbiao Wu, Jia‐Qi Zhu
IET Renewable Power Generation
Stacked denoising autoencoder features with LSTM improve South African wind speed forecasts by 17% over benchmarks, with NWP data cleaned by clustering.
Data‐driven wind speed forecasting using deep feature extraction and LSTM
In one sentence. Stacked denoising autoencoder features with LSTM improve South African wind speed forecasts by 17% over benchmarks, with NWP data cleaned by clustering.
Labels
- Topic
- Local & station forecasting, Applications & impacts
- Type
- New model or method
- Method
- RNN / LSTM / ConvLSTM, Classical ML (trees, GP, linear, kernels)
- Time scale
- 6 h–3 days
- Domain
- Local / station
- Data
- NWP analysis or forecasts (IFS, GFS, ...), Station / in-situ
- Status
- Research
- Identifiers
- DOI:10.1049/iet-rpg.2018.5917 OpenAlex:W2947870382
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.