By: Nathan Smith
Date: March 22, 2020
This project was completed as a component of the Part Time Data Science Course through BrainStation.
The purpose of this study is to assess the ability to use machine learning to estimate daily streamflow in British Columbia, Canada using streamflow and climate data in proximity to the stream of interest. This study looks at estimating the Stave River streamflow using data available within a 100 km radius. This should be considered an initial step in determining if an automated or semi-automated procedure could be applied to generate machine learning models for any streamflow location in British Columbia.
The work was completed in Jupyter Notebook and the environment.yml file can be used to create the python environment. Details on creating an environment in conda can be found here: https://docs.conda.io/projects/conda/en/latest/user-guide/tasks/manage-environments.html
Note that the notebook uses interactive plots using plotly which can only be viewed in Jupyter Notebook (currently not in Jupyter Lab).
An html file of the notebook is also available at the following link: https://wraysmith.github.io/StreamflowPyML/