Machine Learning for Environmental Engineering and Science (Columbia University, EAEE4000E)

• Instructor: Pierre Gentine
• Fall 2025: Wednesdays, 4:10 – 6:40pm (ET)

Aimed at understanding and testing state-of-the-art methods in machine learning applied to environmental sciences and engineering problems. Potential applications include but are not limited to remote sensing, and environmental and geophysical fluid dynamics. Includes testing “vanilla” ML algorithms, feedforward neural networks, random forests, shallow vs deep networks, and the details of machine learning techniques.

Special Topics in Earth and Environmental Engineering (Columbia University, EAEE6000E)

• Instructor: Greg Elsaesser
• Fall 2025: Thursdays, 12:00 – 2:00pm (ET)

This “journal-club” style course will expose geoscience students to cutting-edge data science methods, and data science students to currently-existing climate science problems and Earth system model development needs.

Computing and Research Methods for Climate Data Science (Columbia Climate School, CLMT5045)

• Instructor: Dhruv Balwada
• Summer 2025: Tuesdays + Thursdays, 11am – 12:45pm (EDT)

Computing and data analysis have become an indispensable tool for researchers and industry professionals working in virtually any aspect of the modern world. This course will introduce students to the fundamental concepts and methods that are broadly applicable to any data science project, with a thematic focus on climate and environmental data. This includes an introduction to Unix, programming, common data formats, analysis, and visualization. The primary focus will be to teach students the foundations of Python in a climate data science context, which is of the most widely used and accessible programming languages today. Students will also be introduced to cloud computing, which will be the primary tool for in-class assignments and projects. This course is designed to be accessible for students with an interest in being able to ask and answer questions using data. This course will also be invaluable for those looking to interact with scientists and engineers, manage scientific projects, and develop policies in the realm of climate science and sustainability.

Machine Learning for Climate Science & Environmental Sustainability (Columbia Climate School, CLMT 5043)

• Instructor: Kara Lamb
• Summer 2025: Tuesdays + Thursdays, 11am – 12:45pm (ET)

  The application of Machine Learning (ML) to climate science and environmental sustainability has become increasingly popular in recent years, promising to revolutionize how we analyze and address critical environmental challenges. This course will introduce students to the fundamental concepts and methods of ML, emphasizing their practical applications to climate science and environmental sustainability efforts.

  Students will gain both theoretical knowledge and practical skills through hands-on experience with machine learning methods and coding. The course is designed to provide familiarity with the design, implementation, and evaluation of machine learning models towards addressing specific problems in climate science and sustainability. By working with real-world datasets, students will develop a deeper understanding of both the capabilities and limitations of ML tools in climate research and for evaluating environmental sustainability solutions. This course will cover essential topics such as data preprocessing, model selection, evaluation metrics, and the ethical implications of ML in climate science.

  As ML tools become increasingly important to these application areas, this course will be invaluable for those looking to interact with scientists and engineers, manage scientific projects, and develop policies in the realm of climate science and sustainability. 

Humans + the Carbon Cycle (Columbia University, GU4020)

• Instructor: Galen McKinley
• Fall 2024: Tuesdays + Thursdays, 11:40am – 12:55pm (EDT)

The accelerating climate change of the current day is driven by humanity’s modifications to the global carbon cycle. This course offers an introduction basic science of the carbon cycle, with a focus on large-scale processes occurring on annual to centennial timescales. Students will leave this course with an understanding of the degree to which the global carbon cycle is understood and quantified, as well as the key uncertainties that are the focus of current research. We will build understanding of the potential pathways, and the significant challenges, to limiting global warming to 2o C as intended by the 2015 Paris Climate Agreement. The course will begin with a brief review of climate science basics and the role of CO2 in climate and climate change (weeks 1-2). In weeks 3-4, the natural reservoirs and fluxes that make up the global carbon cycle will be introduced. In week 5-6, anthropogenic emissions and the observed changes in climate associated with increasing atmospheric CO2 will be discussed. In weeks 7-11, we will learn about how the land biosphere and ocean are mitigating the increase in atmospheric CO2 and the feedbacks that may substantially modify these natural sinks. In weeks 12-13, the international policy process and the potential for carbon cycle management will be the focus. In weeks 14, students will present their final projects.

Research Computing in Earth and Environmental Sciences (Columbia University, GR6901)

• Instructor: Yutian Wu
• Fall 2024: Tuesdays + Thursdays, 2:40 – 3:55pm (EDT)

Computing has become an indispensable tool for Earth Scientists. This course will introduce incoming DEES PhD students to modern computing software, programming tools and best practices that are broadly applicable to carrying out research in the Earth Sciences. This includes an introduction to Unix, programming in three commonly used languages (Python, MATLAB and Fortran), version control and data backup, tools for visualizing geoscience data and making maps. Students will learn the basics of high performance computing and big data analysis tools available on cluster computers. Student learning will be facilitated through a combination of lectures, in-class exercises, homework assignments and class projects. All topics will be taught through example datasets or problems from Earth Sciences. The course is designed to be accessible for Earth Science graduate students in any discipline.

Machine Learning for Environmental Engineering and Science (Columbia University, EAEE4000E)

• Instructors: Conrad Albrecht
• Fall 2024: Wednesdays, 4:10 – 6:40pm (EDT)

Aimed at understanding and testing state-of-the-art methods in machine learning applied to environmental sciences and engineering problems. Potential applications include but are not limited to remote sensing, and environmental and geophysical fluid dynamics. Includes testing “vanilla” ML algorithms, feedforward neural networks, random forests, shallow vs deep networks, and the details of machine learning techniques.

Readings in Climate Data Science (Columbia University, EAEE6000E)

• Instructor: Greg Elsaesser
• Fall 2024: Thursdays, 12:00 – 1:30pm (EDT)

In conjunction with LEAP-STC’s Fall 2024 Lectures in Climate Data Science, this “journal-club” style course will expose geoscience students to cutting-edge data science methods, and data science students to currently-existing climate science problems and Earth system model development needs.