Kondylatos, S., Prapas, I., Ronco, M., Papoutsis, I., Camps-Valls, G., Piles, M., et al. (2022). Wildfire Danger Prediction and Understanding with Deep Learning. Geophysical Research Letters, 49, e2022GL099368.
https://doi.org/10.1029/2022GL099368
数据使用声明:
The datacube is in Zenodo (Prapas et al., 2022) (https://doi.org/10.5281/zenodo .6475592). The datasets are also in Zenodo (Prapas et al., 2022) (doi.org/10.5281/ zenodo.6528394). Both are under Creative Commons Attribution 4.0 International Public License.
代码和模型使用声明:
The code and instructions for training the models are in Zenodo (Prapas & Kondylatos, 2022) (https://doi.org/10.5281/zenodo.6524771), under MIT license.
运行代码:
The code is GPU-ready, and it is recommended to have a cuda-enabled NVIDIA GPU to run the experiments. They can also be run in a CPU, but expect slow training times
The code has been tested in a server with 128GB RAM and an NVIDIA RTX 3080 (10GB).
Running the Random Forest model
See notebook notebooks/RF.ipynb.
Training the LSTM model
Training the LSTM with the hyperparameters that were used in the paper:
python run.py experiment=lstm_temporal_cls
Training the convLSTM model
Training the convLSTM with the hyperparameters that were used in the paper: