(1) Data science approaches to ecological forecasting and decision making

Applications for Spring 2022 are now closed for this project.

Become familiar with the mathematical, statistical, and computational tools used in the group and learn how to apply these methods to answer questions in ecological research and conservation decision making.

We will work to train and evaluate cutting edge and emerging deep reinforcement learning algorithms on challenging ecological decision making problems. The ideal outcome will be a suite of trained agents on a set of example conservation challenges, similar to existing benchmarks in reinforcement learning that rely on benchmarks based in robotics and arcade games, e.g. https://gym.openai.com

Qualifications: Familiarity with two or more of the following areas will make an applicant both more competitive and more likely to enjoy a successful and productive research experience: Introductory statistics and probability, dynamical systems/differential equations, programming (particularly programming and data analysis in R or python), familiarity with git/GitHub, courses and/or research experience in ecology. Programming experience in python, and particularly experience with popular reinforcement learning frameworks such as OpenAI gym, tensorflow/agents or stable-baselinesv3 would be ideal.

Weekly Hours: to be negotiated

Off-Campus Research Site: All work can be conducted remotely via GitHub. During the COVID-19 pandemic there will be no need to perform any of this work on the Berkeley campus.

Related website: https://boettiger-lab.github.io/conservation-gym/
Related website: https://stable-baselines3.readthedocs.io/

(2) Data Science Software Development with Applications to Ecology and Environmental Science

Applications for Spring 2022 are now closed for this project.

Get involved on the front line of data science research in the R language with rOpenSci (https://ropensci.org).

Students will also be involved in the fundamentals of software development and maintenance, including unit testing and continuous integration. Successful completion of the project will involve peer review of software and a public software release of one or more R packages to the Central R Archive Network (CRAN).

Students will learn essential skills of data science and software development not usually taught in classes while working collaboratively with the rOpenSci team. Through this project, students will learn the following tools and technologies:

- GitHub: git flow, pull requests, GitHub API use
- R: Package development, documentation, testing
- JSON-LD: linked data principles, schema.org descriptions, parsing, serialization and validation
- Managing relational database interfaces with R (Postgres, MonetDB, etc)

Applicants will choose a specific software project in consultation and collaboration with Prof Boettiger. Currently active projects include ecological networks, taxonomic biodiversity tools, phylogenetics tools, structured and semantic data synthesis, global fish data, and ecological trait data.


Qualifications: Candidates should be self-motivated, curious, and able to collaborate effectively and professionally in an online environment. Applicants should have some prior experience with both R and GitHub, and an interest in applications to issues in ecology, environment and biodiversity.

Weekly Hours: to be negotiated

Related website: https://ropensci.org
Related website: https://carlboettiger.info