Skip to content

Welcome to the Course!

Experiential Introduction to AI & Ecology Course Icon, hightlights interdisciplinary collaboration (biology, computer science, etc.), field work experience, AI/ML applied to ecology and biology, scientific impact

Summary

This is a year-long interdisciplinary, project-driven course that brings together biologists, computer scientists, and those from related disciplines to learn, collaborate, and answer questions in ecology/biology/biodiversity science using computational machine learning (ML) approaches. The course begins with foundational concepts in science and analytic areas while formulating group-project ideas, includes a field experience for collecting data, and ends with completing group projects asynchronously and receiving professional development synchronously. The goal of the course is to conduct interdisciplinary scientific inquiry and research at the intersection of AI and ecology, collaborate with scientists across disciplines, become immersed in the research methods of different fields, and explore how the collaboration between those disciplines results in the emergence of new ideas, approaches, and discoveries. More details are provided in the syllabus.

Course Structure

The year-long course has three parts. Part I offers a synchronous, lecture/flipped-classroom introduction to the necessary analytical and biological foundational skills to conduct research at the intersection of AI and ecology. Part II is a three-week field experience under the mentorship of a faculty member, collecting data at a biologically diverse location within the U.S. In Part III, students collaborate in teams to analyze data gathered during the field experience, addressing research questions pertinent to their project.

Part I

Part I offers a synchronous, lecture/flipped-classroom introduction to the necessary analytical and biological foundational skills to conduct research at the intersection of AI and ecology.

Objectives: At the end of part I, students will be able to:

  • Explain why AI can help solve ecology problems.
  • Apply and evaluate relevant AI models for different data types.
  • Develop ecology research questions that can be answered using both unstructured and structured data.
  • Complete field work using data collection methods taught in the course.
  • Open, compile, and execute Python code.
  • Use common language to communicate across the disciplines of Computer Science and Ecology.
  • Adhere to codes of conduct and community principles when conducting research across diverse cultures.

Mode: Virtual, (mostly) synchronous course:

  • This is a hybrid-instruction class. Most course work will occur asynchronously with one 1-hour synchronous class meeting per week
  • Weekly office hours
  • Seven modules with 2-3 sessions (weeks) each

Part II

Part II is a three-week field experience under the mentorship of a course instructor, collecting data at a biologically diverse location.

Objectives: At the end of part II, students will be able to:

  • Collaborate with others on field research data collection
  • Follow data collection protocols
  • Articulate analytic consequences when protocols are not followed
  • Adapt and document changes when protocols must change
  • Implement best practices for data storage, management, and documentation

Mode: In-person at field site location:

  • Students collect data in Hawaii or Kenya for projects
  • Approximate dates are Jan 5-26, 2027 (Hawaii) and January 8-26, 2027 (Kenya)

Part III

Part III provides students an opportunity to collaborate in teams to analyze data gathered during the field experience, addressing research questions pertinent to their project.

Objectives: At the end of part III, students will be able to:

  • Work in teams to analyze data
  • Develop and execute analytic methods to learn from data
  • Answer intended research question(s) defined in Part I & II
  • Create a scientific poster
  • Write a scientific paper
  • Present scientific findings over zoom
  • Articulate responsible data findings, regardless of format (written, oral, visual)

Mode: Virtual, (mostly) asynchronous course:

  • Part III is project-based with each group meeting on their own with their faculty advisor weekly.
  • Every three to four weeks, the entire class will convene in a synchronous meeting to share current project updates and reinforce best practices in professional skills.

Enrollment Requirements

Students who enroll in the Fall semester are expected to complete all three-parts of the course, including the field experience in Hawaii or Kenya, unless prior written approval is granted by the main course instructors (Leanna House and Tanya Berger-Wolf).