ESS 523c: Environmental Data Science Applications
Water Resources
Environmental Data Science Applications:
Water Resources
+150 optional final project
About This Course
This course focuses on analyzing and understanding water resources through the lens of modern data science. Building on the foundational R skills from ESS/WR 523a, we examine key innovations in data science, geospatial processing and machine learning for hydrological prediction and model parameterization — with an emphasis using real data.
Every dataset, every example, and every lab draws from systems you will encounter in professional practice. The course is organized around a single professional question: what does it take to turn raw environmental data into a reproducible, publishable result that informs real decisions? Each week answers a piece of that question with a different class of data and methods — from spatial analysis through to machine learning workflows applied directly to hydrological problems.
By the end of the course you will have built a public portfolio of six published analyses spanning data wrangling, vector data, raster data, machine learning, and time series — using the same data infrastructure that federal agencies and consulting firms use operationally.
All course materials — slides, labs, and code — are open source under the Apache 2.0 license and built with Quarto. If you find something that could be improved, please submit an issue on the course GitHub repository.
| Component | Count | Points Each | Total |
|---|---|---|---|
| Labs | 7 | 950 | 950 |
| Final Project (optional) | 1 | 150 EC | +150 |
| Total (required) | 950 |
Grade scale (percentage of 950 required points): A+ ≥ 96.67% · A ≥ 93.33% · A– ≥ 90% · B+ ≥ 86.67% · B ≥ 83.33% · B– ≥ 80% · C+ ≥ 76.67% · C ≥ 70% · D ≥ 60% · F < 60%
Labs - with the exception of Lab 0 - are assigned on Wednesdays and due the following Wednesday before class. All submissions are deployed as GitHub Pages. Collaboration on concepts is encouraged; code, writing, and results must be individually produced.