Ecosystem Science and Sustainability 330

Quantitative Reasoning for Ecosystem Science

Authors
Affiliations

Mike Johnson, PhD

NOAA Office of Water Prediction

Alan Cai

Colorado State University

Jaque McVey

Colorado State University

Component 1: Open Science & Tools

Understand the essentials of modern data workflows. This module focuses on setting up your computational environment with R, RStudio, Git, and GitHub while introducing best practices for organizing and managing data. Learn how computers process and interface with data, ensuring you’re equipped for transparent and reproducible science.

Learning Outcomes
  • Set up and navigate R, RStudio, Git, and GitHub.
  • Develop effective data organization strategies.
  • Understand data structures and types.

Lecture 01 (w1): Welcome!

Lecture 02 (w2): Your Digital Environment

Lecture 03 (w2): Data Types

CANCELLED: —

Lecture 04 (w3): Your Tools: Interactive Example

Exercise 01: Setup R & RStudio

Exercise 02: Intro to Terminal / Git Install

Exercise 03: Your first Project

CANCELLED: —

Exercise 04: Tools, Forking, Quarto

Component 2: Working with Data

Build confidence in wrangling, visualizing, and analyzing data. This section covers importing and cleaning data sets, working with joins, and creating effective visualizations. You’ll also delve into study design, hypothesis testing, and statistical analyses spanning uni-variate, bivariate, and multivariate techniques.

Learning Outcomes
  • Import, clean, and merge data sets from diverse sources using core tidyverse packages.
  • Conduct hypothesis testing and interpret results.
  • Create impactful visualizations to communicate findings.

Lecture 05 (w4): Data Structures

Lecture 06 (w4): Data Manipulation (dplyr)

Lecture 07 (w5): Data Visualization (ggplot2)

Lecture 08 (w5): Data Relations & Forms (tidyr)

Lecture 09 (w6): Linear Models (lm)

Lecture 10 (w6): Nests & maps (purrr)

Lecture 11 (w7): EDA

Lecture 12 (w7): Normality & Feature Engineering

Lecture 13 (w8): Review + Example

Lecture 14 (w8): Finding Data & Project Introduction

Exercise 05: Building subsets

Exercise 06: Manipulating Data

Exercise 07: Your first plots

Exercise 08: Joins & Pivots

Exercise 09: Build a model

Exercise 10: Build a model

Exercise 11: Extending your model

Exercise 12: Extending your model

Exercise 13: Self Reflection

Exercise 14: Data Safari

Project Information

Spring Break (w9)

Component 3: Modeling

Gain hands-on experience in regression and machine learning. From foundational techniques in base R to more advanced workflows using the tidymodels framework, this module walks you through feature engineering, model setup, and model evaluation. You’ll also explore time series analysis, preparing you to tackle dynamic ecosystem data challenges where time is a consideration.

Learning Outcomes
  • Apply regression techniques to ecological data.
  • Build and evaluate machine learning models using tidymodels
  • Understand time-series data and methods.

Lecture 15 (w10): Data budgeting

Lecture 16 (w10): Model Workflows

Lecture 17 (w11): Model Specifications

Lecture 18 (w11): Live Demo

Lecture 19 (w12): Evaluating & Tuning a model

Lecture 20 (w12): Full Workflow Demo

Exercise 15: Data Splitting

Exercise 16: Building a workflow

Exercise 17: Reading

Exercise 18: Demo summary

Exercise 19: Whole Process Narative

Exercise 20: Tune a model

Component 4: Spatial and Temporal Data

Harness the power of R as a GIS. Learn to process, analyze, and visualize vector and raster data to address spatial questions in ecosystem science. This component equips you to integrate geospatial techniques into broader data science workflows you’ve already established. Further we will explore applications in timseries analysis, including forecasting and anomaly detection.

Learning Outcomes
  • Use R for vector (sf) and raster (terra) spatial data analysis.
  • Create maps and spatial visualizations.
  • Integrate location with you data science workflows
  • Understand time-series data and methods.

Lecture 21 (w13): Timeseries Basics

Lecture 22 (w13): Timeseries Forecasting

Lecture 23 (w14): Feature Geometries

Lecture 24 (w14): CRS and Measures

Lecture 25 (w15): Predicates

Lecture 26 (w15): Raster Data Introduction

Lecture 27 (w16): Raster Data Manipulation

Lecture 28 (w16): Local, Focal, Zonal Operations

Exercise 21: Decompse the Poudre River Timeseries

Exercise 22: Predicting the Poudre

Exercise 23: Install your GIS

Exercise 24: Larimer County Cities

Exercise 25: Mississippi River

Exercise 26: Fort Collins Elevation PRofile

Exercise 27: Poudre River Profile

Exercise 28: Poudre River Profile