MC-LSTM papers, model runs

Runs from two papers exploring the use of mass conserving LSTM. Model results used in the papers are 1) model_outputs_for_analysis_extreme_events_paper.tar.gz, and 2) model_outputs_for_analysis_mass_balance_paper.tar.gz.

The models here are trained/calibrated on three different time periods. Standard Time Split (time split 1): test period(1989-1999) is the same period used by previous studies which allows us to confirm that the deep learning models (LSTM andMC-LSTM) trained for this project perform as expected relative to prior work. NWM Time Split (time split 2): The second test period (1995-2014) allows us to benchmark against the NWM-Rv2, which does not provide data prior to 1995. Return period split: The third test period (based on return periods) allows us to benchmark only on water years that contain streamflow events that are larger (per basin) than anything seen in the training data (<= 5-year return periods in training and > 5-year return periods in testing).

Also included are an ensemble of model runs for LSTM, MC-LSTM for the "standard" training period and two forcing products. These files are provided in the format "<model_type>_<forcing_product>_standard_training.tar.gz". Note that these individual ensemble member runs we used to produce the runs in the files "model_outputs_for_analysis_<*>_paper.tar.gz".

IMPORTANT NOTE: This python environment should be used to extract and load the data: https://github.com/jmframe/mclstm_2021_extrapolate/blob/main/python_environment.yml, as the pickle files serialized the data with specific versions of python libraries. Specifically, the pickle serialization was done with xarray=0.16.1.

Code to interpret these runs can be found here:
https://github.com/jmframe/mclstm_2021_extrapolate
https://github.com/jmframe/mclstm_2021_mass_balance

Papers are available here:
https://hess.copernicus.org/preprints/hess-2021-423/

本数据集源于两篇研究，探讨了质量守恒长短期记忆网络（LSTM）的运用。文中使用的模型结果包括：1) model_outputs_for_analysis_extreme_events_paper.tar.gz，2) model_outputs_for_analysis_mass_balance_paper.tar.gz。所涉模型在三个不同的时间区间内进行了训练/校准。标准时间分割（时间分割1）：测试期（1989-1999）与先前研究使用的时期相同，这使得我们得以验证，为该项目训练的深度学习模型（LSTM和MC-LSTM）在相对先前工作的情况下表现符合预期。NWM时间分割（时间分割2）：第二个测试期（1995-2014）使我们能够与NWM-Rv2进行基准测试，NWM-Rv2在1995年之前不提供数据。回水期分割：第三个测试期（基于回水期）仅对包含超过训练数据中任何记录的径流事件（训练数据中为5年一遇，测试数据中为大于5年一遇）的水年进行基准测试。此外，还包括了针对“标准”训练期的LSTM和MC-LSTM的模型运行集合，以及两种强迫产品。这些文件以“<模型类型>_<强迫产品>_standard_training.tar.gz”的格式提供。请注意，这些独立的集合成员运行被用于生成“model_outputs_for_analysis_<*>_paper.tar.gz”文件中的运行。重要提示：应使用以下Python环境提取和加载数据：https://github.com/jmframe/mclstm_2021_extrapolate/blob/main/python_environment.yml，因为pickle文件使用特定版本的Python库序列化了数据。具体而言，pickle序列化使用了xarray=0.16.1。解释这些运行的代码可在此处找到：https://github.com/jmframe/mclstm_2021_extrapolate和https://github.com/jmframe/mclstm_2021_mass_balance。相关论文可在以下链接获取：https://hess.copernicus.org/preprints/hess-2021-423/