DROMEDARY US

The DROMEDARY US dataset is a publicly accessible collection that encompasses 3,246 basins throughout the contiguous United States. It includes several datasets: the Gages II dataset (Falcone, 2011), the Cropland Data Layer from the CropScape web platform (Han et al., 2012), meteorological data from the Daymet dataset (Thornton et al., 2021), and streamflow data published by the USGS, accessible via their data retrieval tool (De Cicco et al., 2018). This dataset was created to train Long Short-Term Memory (LSTM) neural networks to predict daily streamflow time series at the outlets of these basins. It aims to provide a comprehensive sample of basins across various hydroclimatological contexts in the US, including those that have undergone significant changes in land use and land cover. The dataset is divided into static attributes and time series. The time series are stored in .nc files, with the 3,246 .nc files compressed into an archive that is split into three parts to facilitate uploading. More details are provided in the article: \"Using Long Short-Term Memory Neural Networks to Assess Streamflow Alteration from Land-Use and Land Cover Changes: Application to Fallowed Land Across the United States\" by Baptiste Francois, Samson Zhilyaev and Casey Brown, which was submitted to Water Resources Research journal. The full reference of the article will be updated once/if it gets accepted for publication. Falcone, J., 2011. GAGES-II: Geospatial Attributes of Gages for Evaluating Streamflow. Reston, VA. https://doi.org/10.3133/70046617 De Cicco, L.A., Hirsch, R.M., Lorenz, D., Watkins, D., Johnson, M., 2024. dataRetrieval: R packages for discovering and retrieving water data available from Federal hydrologic web services, v.2.7.15. https://doi.org/10.5066/P9X4L3GE Thornton, P.E., Shrestha, R., Thornton, M., Kao, S.-C., Wei, Y., Wilson, B.E., 2021. Gridded daily weather data for North America with comprehensive uncertainty quantification. Sci. Data 8, 190. https://doi.org/10.1038/s41597-021-00973-0 Han, W., Yang, Z., Di, L., Mueller, R., 2012. CropScape: A Web service based application for exploring and disseminating US conterminous geospatial cropland data products for decision support. Comput. Electron. Agric. 84, 111–123. https://doi.org/10.1016/j.compag.2012.03.005DROMEDARY US数据集是一套公开可获取的数据集，涵盖美国本土连续区域内的3246个流域。该数据集包含多类子数据集：Gages II数据集（Gages II dataset，Falcone, 2011）、来自CropScape网络平台的农田数据图层（Han等, 2012）、Daymet数据集（Daymet dataset）的气象数据（Thornton等, 2021），以及由美国地质调查局（United States Geological Survey, USGS）发布、可通过其数据检索工具获取的河道流量数据（De Cicco等, 2018）。 本数据集旨在训练长短期记忆（Long Short-Term Memory, LSTM）神经网络，以预测这些流域出口处的逐日河道流量时间序列。其目标是全面采样美国境内不同水文气候背景下的流域，包括那些土地利用与土地覆被发生显著变化的流域。 该数据集分为静态属性与时间序列两类数据。时间序列数据存储于.nc文件中，3246个.nc文件被压缩为一个归档包，并拆分为三个分卷以方便上传。 更多详细信息可参阅已提交至《Water Resources Research》期刊的论文：《利用长短期记忆神经网络评估土地利用与土地覆被变化引发的河道流量改变——美国休耕地应用研究》，作者为Baptiste Francois、Samson Zhilyaev与Casey Brown。该论文的完整参考文献信息将在其被录用发表后更新。 参考文献： 1. Falcone, J., 2011. GAGES-II：用于评估河道流量的测站地理空间属性。弗吉尼亚州雷斯顿：https://doi.org/10.3133/70046617 2. De Cicco, L.A., Hirsch, R.M., Lorenz, D., Watkins, D., Johnson, M., 2024. dataRetrieval：用于发现和检索联邦水文网络服务中水资源数据的R包，v.2.7.15。https://doi.org/10.5066/P9X4L3GE 3. Thornton, P.E., Shrestha, R., Thornton, M., Kao, S.-C., Wei, Y., Wilson, B.E., 2021. 北美网格化逐日气象数据及综合不确定性量化。《科学数据》8卷，190页。https://doi.org/10.1038/s41597-021-00973-0 4. Han, W., Yang, Z., Di, L., Mueller, R., 2012. CropScape：一款基于网络服务的美国本土地理空间农田数据产品探索与传播决策支持应用。《计算机与农业电子学》84卷，111–123页。https://doi.org/10.1016/j.compag.2012.03.005