paper
2023
Nowcasting
New model or method
RNN / LSTM / ConvLSTMCNN / U-NetClassical ML (trees, GP, linear, kernels)0–6 h Journal
2023-01-01
008
Jan 2023
Amirmasoud Amini, Mehri Dolatshahi, Reza Kerachian
Water Resources Research
Ensembles of CNN and LSTM networks with automatic hyperparameter tuning improve multi-step rainfall nowcasting by 10-25% over univariate models in Tehran.
Effects of Automatic Hyperparameter Tuning on the Performance of Multi‐Variate Deep Learning‐Based Rainfall Nowcasting
In one sentence. Ensembles of CNN and LSTM networks with automatic hyperparameter tuning improve multi-step rainfall nowcasting by 10-25% over univariate models in Tehran.
Labels
- Topic
- Nowcasting
- Type
- New model or method
- Method
- RNN / LSTM / ConvLSTM, CNN / U-Net, Classical ML (trees, GP, linear, kernels)
- Time scale
- 0–6 h
- Domain
- Local / station
- Data
- Station / in-situ, NWP analysis or forecasts (IFS, GFS, ...)
- Status
- Research
- Identifiers
- DOI:10.1029/2022wr032789 OpenAlex:W4315490959
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.