Models and Predictions for "The Proper Care and Feeding of CAMELS: How Limited Training Data Affects Streamflow Prediction"

Name: Models and Predictions for "The Proper Care and Feeding of CAMELS: How Limited Training Data Affects Streamflow Prediction"
Creator: Zenodo
Published: 2019-11-17T15:14:19+08:00

Zenodo2020-07-30 更新2026-05-25 收录

数据链接：

https://zenodo.org/record/3543548 数据链接链接失效反馈

官方服务：

资源简介：

Models and Predictions This dataset contains the trained XGBoost and EA-LSTM models and the models' predictions for the paper The Proper Care and Feeding of CAMELS: How Limited Training Data Affects Streamflow Prediction. For each input sequence length (10, 30, 100, 270*, 365*) and each combination of model (XGBoost, EA-LSTM), training years (3, 6, 9), number of basins (13, 26, 53, 265, 531), and seed (111-888), there are five folders. Each corresponds to a random basin sample (for 531 basins there's only one folder, since it's all basins). In each folder, there are three files: \(\texttt{model.pkl}\) (XGBoost) or \(\texttt{model_epoch30.pt}\) (EA-LSTM), which stores the pickled trained model \(\texttt{xgboost_seedNNN.p}\) or \(\texttt{ealstm_seedNNN.p}\), which stores a pickled dictionary that maps each basin to the DataFrame of predicted and actual daily streamflow. \(\texttt{attributes.db}\), which stores static catchment attributes needed for inference. In addition to each folder, there is a SLURM submission script called \(\texttt{<foldername>.sbatch}\) that was used to create and evaluate the model in the folder. * sequence lengths 270 and 365 only contain data for EA-LSTM.

「模型与预测结果」本数据集包含为论文《CAMELS的合理养护与投喂：有限训练数据如何影响径流预测》（The Proper Care and Feeding of CAMELS: How Limited Training Data Affects Streamflow Prediction）训练得到的极端梯度提升树（XGBoost）与进化长短期记忆网络（EA-LSTM）模型，以及这些模型的预测结果。针对每一种输入序列长度（10、30、100、270*、365*）、每一组模型（XGBoost、EA-LSTM）、训练年限（3、6、9）、流域数量（13、26、53、265、531）以及随机种子（111-888）的组合，均对应5个文件夹。每个文件夹对应一组随机抽取的流域样本（当流域数量为531时仅存在1个文件夹，因为此时包含全部流域）。每个文件夹内包含三个文件：`model.pkl`（适用于XGBoost）或`model_epoch30.pt`（适用于EA-LSTM），用于存储序列化后的训练模型；`xgboost_seedNNN.p`（XGBoost场景下）或`ealstm_seedNNN.p`（EA-LSTM场景下），用于存储序列化字典，该字典将每个流域映射至包含预测与实测日径流的数据框（DataFrame）；以及`attributes.db`，用于存储推理所需的静态集水区属性。除上述文件夹外，还附带一个名为`<foldername>.sbatch`的SLURM提交脚本，用于创建并评估对应文件夹内的模型。 *注：序列长度270与365仅包含EA-LSTM的相关数据。

提供机构：

Zenodo

创建时间：

2019-11-17

Models and Predictions for "The Proper Care and Feeding of CAMELS: How Limited Training Data Affects Streamflow Prediction"

资源简介：

相关数据集