paper
2022
Applications & impacts
Post-processing & calibration New model or method
RNN / LSTM / ConvLSTMClassical ML (trees, GP, linear, kernels)6 h–3 days3–15 days Journal
2022-10-27
012
Oct 2022
Yuan‐Kang Wu, Cheng‐Liang Huang, Shenghong Wu et al.
IEEE Transactions on Industry Applications
Combines CWB WRF-based NWP wind speeds with PCA/EMD preprocessing and XGBoost for wind power forecasts, reaching 5.43% NRMSE at one hour ahead.
Deterministic and Probabilistic Wind Power Forecasts by Considering Various Atmospheric Models and Feature Engineering Approaches
In one sentence. Combines CWB WRF-based NWP wind speeds with PCA/EMD preprocessing and XGBoost for wind power forecasts, reaching 5.43% NRMSE at one hour ahead.
Labels
- Topic
- Applications & impacts, Post-processing & calibration
- Type
- New model or method
- Method
- RNN / LSTM / ConvLSTM, Classical ML (trees, GP, linear, kernels)
- Time scale
- 6 h–3 days, 3–15 days
- Domain
- Local / station
- Data
- NWP analysis or forecasts (IFS, GFS, ...)
- Status
- Research
- Identifiers
- DOI:10.1109/tia.2022.3217099 OpenAlex:W4312470194
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.