Starts: June 16, 2022, at 6 pm ET, and continues weekly [$2500 in gifts for participants]
We will be applying time series and other relevant techniques to Canadian streamflow data in drought-prone areas.
Pre-Requisites - Prior experience using Python is required for this project. We recommend that participants have heard of time series, neural networks, Google Colab, and data cleaning, so they can perform ML-related modelling tasks. Knowledge of environmental science/engineering is not required, but an interest is preferred.
Leads / Advisors
~ Yan Nusinovich | Data Scientist at Slate.AI
~ Dr Andre Erler | Advisor Senior Climate Scientist Aquanty
~ Dr. Karen Smith | Advisor Assistant Professor, U of Toronto
❗ Meeting link: https://meet.jit.si/canadian_prairies
❗ Weekly meeting time: Thursdays, 6pm ET
- “Adequate water resources management is an essential component of socioeconomic security and development. This is made even more critical with the increasing global population and impacts of climate change on water resources” (https://www.nature.com/articles/s41597-020-00583-2).
- “A long-standing problem in the hydrological sciences is about how to use one model, or one set of models, to provide spatially continuous hydrological simulations across large areas (e.g., regional, continental, global)” (https://hess.copernicus.org/articles/23/5089/2019/hess-23-5089-2019.html with accompanying code at https://github.com/kratzert/ealstm_regional_modeling).
- Minimal goal: create a time series model for predicting streamflow using Natural Resources Canada data.
- Stretch goal: create a model that automatically updates streamflow predictions at regular intervals.
Expected time to finish
Discuss the problem + ways to approach
Streamflow Modelling with Time Series https://ai.science/l/9d5a8e1a-e2ab-407c-ada5-371cfa0a3c89 ________________________________________________________ Data for Streamflow Prediction https://ai.science/l/a30e3c41-fb68-4755-9aa1-9986b4dbc564 ________________________________________________________ Learning Multivariate Time Series https://ai.science/l/50144be7-9b81-443a-b67b-ab81ab5516d2 ________________________________________________________ Meeting 2 recording: https://www.dropbox.com/s/fne2dyh78qtzaiz/canadian_prairies on 2022-06-23 23-05.mp4?dl=0
Members present how they will approach + Core Team Distilled
4 - 6 weeks
Meeting 4 recording: https://www.dropbox.com/s/cfd2a09howhtejr/canadian_prairies on 2022-07-07 23-07.mp4?dl=0 ________________________________________________________ Meeting 5 recording: https://www.dropbox.com/s/c93w54raszvr6po/canadian_prairies on 2022-07-14 23-14.mp4?dl=0 ________________________________________________________ Meeting 6 recording: https://www.dropbox.com/s/7ziaqmfev0520z4/canadian_prairies on 2022-07-21 23-02.mp4?dl=0
What will I have to show at the end of this project?
- Contributions to the project’s GitHub repo
- A highlight in the project spotlight page on the Aggregate Intellect community website.
- Bookmark the Working Group’s landing page. All key info centralized there.
- Join our Working Group’s Slack channel by:
- By clicking here.
- If having trouble joining, drop ‘firstname.lastname@example.org’ an email. He’ll add!
- [STRONGLY RECOMMENDED BUT OPT] Virtual environment - Google Colab.
- Google Colab is essentially a Google Cloud hosted Juypter notebook.
- Synchronizes everyone’s environments for easier collaborative bug fixing.
- Gives free GPU access. Google Colab - How to use it
Working Group Journey [more info is being added as we go]
Session #1 + #2:
- Get to know everyone!
- We will introduce the problem & why it matters.
- Discuss how we’re thinking about the solution.
- Review available data.
- Review possible modelling approaches.
- Think about how we can reach (or modify, if needed) our stretch goal.
- Present your approach and ask any clarifying questions.
- End of session → Apply to join the Project Team if it’s your cup of tea.
- Energy & competency are both important, but energy is a little more.
Session #4+ [Tentative length: 1.5 months]:
- Project Team will work towards the core problem.
- Will be recognized by AISC at the conclusion of the project!
- [For your portfolio / blog / Social Media].
- Fill out a form reporting contributions of your colleagues to help divvy up the $2500 in gifts.
Aggregate Intellect hosts one of the most diverse ML communities in the world. Over the course of the working group:
- You’ll get an immersion into that community & walk out with some cool new friends.
- There are $2500 in gifts budgeted for participants based on contribution. (A nice little push to encourage 😉)
- You’ll gain new skills that can make an impact on the world’s most pressing challenges.
To join in, join in the Slack channel by hitting ‘join’, drop a quick intro & mention you’re interested in being a part of the group. Someone will help!