Dataset for Global Daily Discharge Estimation Based on Grid-Scale Long Short-Term Memory (LSTM) Model and River Routing

Corresponding peer-reviewed publication Yang, Y., Feng, D., Beck, H.E., Hu, W., Sengupta, A., Delle Monache, L., Hartman, R., Lin, P., Shen, C. and Pan, M. Global Daily Discharge Estimation Based on Grid-Scale Long Short-Term Memory (LSTM) Model and River Routing. Water Resources Research (Under Review). DOI: 10.22541/essoar.169724927.73813721/v1. For updates and revisions to the original manuscript, please refer to the AGU 2024 presentation available on the GRADES-hydroDL website: https://www.reachhydro.org/home/records/grades-hydrodl. When using any of the files in this dataset, please cite both the article as mentioned above and the dataset herein. Summary This dataset contains input files for developing GRADES-hydroDL (global reach level daily discharge based on machine learning and river routing model) dataset and final evaluation metrics. GRADES-hydroDL.pdf: The details of GRADES-hydroDL dataset, including overview, download links, instructions, etc. training_gauge_information.csv: The basic information of the 4215 basins selected for LSTM training. training_gauge_attr.csv: The static attributes of the 4215 training basins used in the LSTM training process. 10fold_training_basin.zip: The training basins and corresponding test basins for the 10-fold cross-validation experiments. global_025d_gridinfo.csv: The basic information of the global 0.25-degree grids used for LSTM application. metrics.zip: All evaluation results of all experiments used in the article.对应同行评议论文 Yang, Y.、Feng, D.、Beck, H.E.、Hu, W.、Sengupta, A.、Delle Monache, L.、Hartman, R.、Lin, P.、Shen, C.及Pan, M. 基于网格尺度长短期记忆（Long Short-Term Memory, LSTM）模型与河道汇流的全球逐日径流量估算. 《Water Resources Research》（审稿中）. DOI: 10.22541/essoar.169724927.73813721/v1. 若需查看原稿的更新与修订版本，请参阅GRADES-hydroDL网站上的2024年美国地球物理联合会（American Geophysical Union, AGU）报告：https://www.reachhydro.org/home/records/grades-hydrodl. 若使用本数据集内的任意文件，请同时引用上述论文与本数据集。 数据集概述 本数据集包含用于构建GRADES-hydroDL（基于机器学习与河道汇流模型的全球河段逐日径流量数据集）的输入文件，以及最终评估指标集。 GRADES-hydroDL.pdf：GRADES-hydroDL数据集的详细说明，涵盖数据集概况、下载链接、使用说明等内容。 training_gauge_information.csv：用于长短期记忆（LSTM）模型训练的4215个流域的基础信息。 training_gauge_attr.csv：LSTM模型训练过程中使用的4215个训练流域的静态属性数据。 10fold_training_basin.zip：用于10折交叉验证实验的训练流域与对应测试流域数据。 global_025d_gridinfo.csv：用于LSTM模型应用的全球0.25°网格的基础信息。 metrics.zip：论文中所有实验的全部评估结果。