Machine Learning in Environmental Science

Welcome to the EDS 232 Website

Image created using the Midjourney image generation tool

Course Description

Machine learning is a field of inquiry devoted to understanding and building methods that “learn,” that is, methods that leverage data to improve performance on some set of tasks. In this course, we focus on the core concepts of machine learning that beginning ML researchers must know. We cover “classical machine learning” primarily using R and explore applications to environmental science. To understand broader concepts of artificial intelligence or deep learning, a strong fundamental knowledge of machine learning is indispensable.

Teaching Team

Instructor: Mateo Robbins (mjrobbins@ucsb.edu)

Student hours: Tuesdays 10:45am (Bren 1424)

Teaching Assistant: Annie Adams (aradams@ucsb.edu)

Student hours: Thursdays 11:00am (Bren 3022)

Weekly Course Schedule

Lecture: TTh 9:30am - 10:45am (Bren 1424)

Sections: Th 1:00pm - 1:50pm or 2:00 - 2:50pm (Bren 3022)

Learning Objectives

The goal of EDS 232 is to equip students with a strong foundation in the core concepts of machine learning. By the end of the course, students should be able to:

  • Explain key machine learning concepts such as classification, regression, overfitting, and the trade-off in model complexity.

  • Identify and justify appropriate data preprocessing techniques and integrate them into machine learning pipelines.

  • Demonstrate an intuitive understanding of common machine learning algorithms.

  • Build supervised machine learning pipelines using Python and scikit-learn on real-world datasets.

  • Apply best practices for machine learning development so that your models generalize to data and tasks in the real world. Measure and contrast the performance of various models

Course Requirements

Computing

Textbook

Course Topics

Week # Dates Lecture Reading
1 1/7, 1/9

Introduction

Linear Regression and ML Modeling Fundamentals I

 ISL Ch. 1, 2.1
2 1/14, 1/16 Regularized Regression and ML Modeling Fundamentals II ISL Ch. 5.1.1-5.1.4, 6.2
3 1/21, 1/23 Logistic Regression, Classification
4 1/28, 1/30 K-nearest neighbors, Decision Trees
5 2/3, 2/6 Random Forest
6 2/11, 2/13 Gradient Boosting
7 2/18, 2/20 Clustering
8 2/25, 2/27 Support Vector Machines
9 3/4, 3/6 Deep Learning
10 3/11, 3/13 Kaggle