This course presents data science techniques for analyzing and deriving insights about biodiversity conservation. With 10-50% of species threatened by human activities, novel computational techniques can unlock new understanding of environmental challenges from digital data, encompassing websites, satellite data, or time series data. In this course, students will learn techniques such as geospatial analysis, natural language processing, and machine learning.
Students will learn how to effectively collect, clean, and extract meaning from unstructured data. Prior programming and statistical analysis experience is strongly encouraged but not required. Through coding assignments and a capstone project, students will build proficiency using open source libraries to wrangle, analyze, visualize, and interpret conservation-related datasets. By the end of the course, a successful learner will have hands-on experience with data science methods, and will have insight on how to connect these with biodiversity and sustainability research, policy, planning, and advocacy.
By the end of the course, a successful learner will be able to:
Location: Seaver South Computer Lab (Room 227)
Schedule: Mondays and Wednesdays, 2:45-4pm
Office Hours: My regularly scheduled office hours will be Tuesdays, 12:30-2pm in my office (Seaver South 108). Times outside of my standard office hours can be scheduled on a first-come-first-served basis here.
Prerequisites: Bio 41E (Intro Ecol & Evolutionary Bio w/Lab) or instructor permission
Readings: This course will use weekly notebook tutorials and will ask students to navigate to readings which will apply what we are learning in a “real world” context.
AI policy: I expect that students will present their own original work in every assignment in this class. However, students may find generative AI to be helpful in deepening their understanding of some of the methods we will be exploring. I expect that if students use generative AI, they will always:
In the longer term, generative AI is extremely expensive for these companies to run and has a substantial environmental and power demand footprint. It is also unclear if companies providing these services will be able to procure enough electricity to be able to meet all consumer demand for this service. Therefore, relying on generative AI puts you at the mercy of large companies that have no accountability to the public, and can harm your growth for near-term convenience that becomes a long-term liability when access to these tools disappears (e.g. companies decide they are a money pit and cut them as a service–see Google Graveyard for some examples) or is only accessible behind prohibitive paywalls (e.g. your organization must subscribe and pay 5-6 figures USD for some recurring subscription).
Digital ethics: One of the tools we will use from time to time in this course is Zoom. To facilitate access, I will typically record Zoom meetings. I will inform students when recordings are in progress. I expect that students in my class will respect one another and my privacy. To that end, students will not record any other member of the class–including the instructor–without obtaining their consent in advance. Students will also not share information about other members of this course in any type of public fora, such as social media. As the instructor, I own the copyright to my instructional materials. These materials cannot be distributed in whole or in part to any person or entity other than other members of the current class without my prior written consent.
Participation is highly important for student success in this course. To that end, I reserve the option to assign a failing grade if students have three or more unexcused absences. Students can have two absences excused with no questions.
I welcome individuals of all ages, backgrounds, beliefs, ethnicities, genders, gender identities, gender expressions, national origins, religious affiliations, sexual orientations, ability - and other visible and non-visible differences. As an instructor, I strongly emphasize student agency; this class is your learning journey, and as such, I expect students to take leadership in their own learning and to keep track of assignments and examination dates. I expect we will respectfully consider differing opinions and engage in constructive discourse. As such, I expect that everyone will help create a collegial environment where all students feel welcome and their rights to learn are respected. Please refer to the Pomona College Student Code for official policy.
I will strive to provide an equitable and inclusive learning environment. My overarching goal is to help you succeed in your exploration of conservation. To that end, you can expect me to be responsive to your concerns about course content, delivery style, and suggestions on how I can improve this course.
A key component of my role as an instructor is office hours. During office hours, I am available to help you work through any problems, questions, or thoughts you have about the course. I am also more than happy to chat about broader questions such as career paths in conservation, next steps after Pomona College/the Claremont Colleges, or other topics of interest to you.
Office hours, email, and class Slack channel: During office hours, I am available to help you work through any problems, questions, or thoughts you have about the course.
I have email boundaries and I encourage you to find your own. Mine include not answering emails after 6pm, or on weekends or holidays. Finally, I request that emails only be used for interactions that are truly one-on-one (e.g. requesting extensions to assignments or accommodations); in general, to help create an atmosphere of transparency and group learning, I request that questions about content and assignments be directed to the #bio108 Slack channel in the Pomona College Division-II workspace.
Learning diversity & accommodations: Pomona College welcomes and accommodates students with disabilities. As your instructor, I care about you and your growth as an environmental scholar. If you encounter obstacles to your success, please let me know immediately so that we can work together to identify ways to overcome any limitations of current course design. If you feel you need a reasonable accommodation to participate in this class, complete course requirements, or benefit from the College’s programs or services, you are also welcome to contact the student accessibility resource office at your College to begin this conversation or to establish accommodations for this or other courses.
Below is a list of the relevant accessibility resource offices at each of the Colleges:
Writing center and student support services: I urge all students to make use of your home campus’ Writing Center and other student support services. A list of relevant resources in included below. For example, the Writing Center is a great resource to workshop and improve your writing whether that is for classwork, for public consumption (e.g. op-eds), graduate school or funding applications, or any other domain.
Late assignments: When assignments are handed in late without prior notice, I reserve the right to apply a grade deduction penalty (~1 grade reduction for each day late; 4 or more days late translates to a failing grade).
Academic integrity: Academic honesty is a core value of Pomona College and the Claremont Colleges. Plagiarism undermines academic integrity and is a threat to communal ethics. I will assign plagiarized assignments a failing grade and will report any instance of plagiarism to the College.
Please note that this schedule is subject to change; this syllabus is very much a living document that will change to reflect the unique conditions of this semester. I reserve the right to exercise some flexibility in scheduling, usually in favor of giving more time to students.
| Week | Topic | Resources | Assignments |
|---|---|---|---|
| 1 | Introduction | Week 1 Notebook | Read syllabus, HW1 |
| 2 | Data manipulation and plotting | Week 2-Pandas; Week 2-Plotting. While this Pandas Book (chapters 5-8) is not required reading, you may find it to be a very helpful resource going forward. | HW2 |
| 3 | Time series data | Week3-TS; Week3-TSds. While this Pandas Book (chapter 11) is not required reading, you may find it to be a helpful resource. | HW3 |
| 4 | GIS systems. Note: We will meet in the library on Wednesday 2/13 for a special guest lecture by the data science, GIS, and biology subject librarians about useful resources in the library. | ArcGIS online tutorial - note: you may first need to login at the Claremont Colleges ArcGIS site; Please read this chapter before next week Geocomputation in Python Chapter 1. | HW4 |
| 5 | Spatial data in Python: shapefiles and rasters | Please read Geocomputation in Python Chapter 1 before this week begins! Week5-Vector1, Week5-Vector2 | HW5 |
| 6 | Remotely sensed data in Python (land cover and satellite imagery) | W6-rasterio-1, Guest lecture by Dr. Nikhil Deshmukh | HW6 |
| 7 | Scraping data in Python: OpenAlex and eBird | W7-raster-vector, W7-leafmap, W7-Scraping | HW7 |
| 8 | Guest lecture & tutorial overview | Guest lecture by Dr. Millie Chapman; Async class on Software Carpentry tutorial format | HW8, Begin thinking of a topic for the data workshop |
| 9 | Spring break | ||
| 10 | Machine learning for conservation | W10-ML, W10-RF | HW10 |
| 11 | NLP and guest lecture | W11-NLP, Dr. Amrita Gupta (4/2) | HW11 |
| 12 | Drafting workshops | Potential tutorial depending on HWs 10 and 11 | Selecting a topic and method, drafting workshop |
| 13 | Drafting workshops | Peer review | |
| 14 | Student workshops | Submit workshop draft (W13 or W14) | |
| 15 | Student workshops | Seniors must complete by this week | |
| 16 | Student workshops |