EnviroLLM Guidelines

Welcome to the EnviroLLM Guidelines repository. This repository is the central hub for our working group, encompassing our project overview, proposals, team member information, codebase, and more.

Our Project

Environmental challenges are increasingly complex and pressing, requiring rigorous and rapid synthesis of broad bodies of research for evidence-based actions. To address this need, scientists are increasingly relying on artificial intelligence to analyze vast amounts of research and policy documents. However, they lack clear guidelines for how to use these powerful tools effectively and ethically to address pressing environmental concerns. Our working group brings together experts from research institutions, policy think-tanks, conservation organizations, and a primarily undergraduate institution (PUI) to develop best practices for using AI-powered text analysis in environmental evidence synthesis and policy analysis. By combining high-performance computing resources with undergraduate research experiences, we aim to create a model for inclusive environmental data science that bridges the gap between large research universities and PUIs. Working with undergraduate students through course-based research experiences, we will develop and test user-friendly tools for analyzing conservation literature and environmental policies. This approach not only advances environmental science but also creates new pathways for undergraduates to participate in cutting-edge research using NSF’s advanced computing infrastructure and helps train the scientific workforce of the 21st century. The resulting guidelines and tools will help researchers worldwide more easily and thoughtfully use AI for environmental evidence and policy syntheses, while our educational model will show how to involve undergraduate researchers in advanced computational text analysis projects. This work represents a crucial step toward more inclusive, ethical, and effective use of AI in environmental science, while developing materials to train diverse undergraduate students in environmental data science research.

Documentation

• Access detailed documentation on our GitHub Pages site.
• Find comprehensive guides, tutorials, and additional resources.

Project Proposal

Information forthcoming.

Working Group Team

Members

• Charlotte Chang
• Brian Robinson
• J.T. Erbaugh
• Kemen Austin
• Max Callaghan
• Samantha Cheng
• Karletta Chief
• Amrita Gupta
• Lian Pin Koh
• Sara Kuebbing
• Biljana Macura
• Sparkle Malone
• Lucas Meyer
• Michal Nachmany
• Rhita Simorangkir

Board of Advisors

• Caitlin Augustin
• Stephanie Hampton
• Yuta Masuda
• John Poulsen
• William Sutherland
• Niraj Swami

Code Repository

This section of the repository will include all the code developed for the project. You can structure it as follows:

• Analysis Code: Scripts for data analysis, statistical modeling, etc.
• Data Processing: Scripts for cleaning, merging, and managing datasets.
• Visualization: Code for creating figures, charts, and interactive visualizations.

Meeting Notes and Agendas

Meeting notes and agendas will be regularly updated here to keep all group members informed and engaged with the progress and direction of the project.

Contributing to This Repository

We welcome contributions from all group members. To maintain the quality and integrity of the repository, please adhere to the following guidelines:

• Make sure all commits have a clear and concise message.
• Document any major changes or decisions in the meeting notes.
• Review and merge changes through pull requests to ensure oversight.

Getting Help

If you encounter any issues or have questions about how to contribute, please refer to the ESIIL Support Page or contact the repository maintainers directly.

Customize Your Repository

As a new working group, you'll want to make this repository your own. Here's how to get started:

1. Edit This Readme: Replace the placeholder content with information about your specific project. Ensure that the introduction, project overview, and objectives clearly reflect your group's research focus.

2. Update Group Member Bios: Add details about each group member's expertise, role in the project, and professional background. Include links to personal or professional web pages to foster community engagement and collaboration.

3. Organize Your Code: Structure your codebase in a way that is logical and accessible. Use directories and clear naming conventions to make it easy for all members to find and contribute to different parts of the project.

4. Document Your Data: Include a data directory with README files explaining the datasets, sources, and any preprocessing steps. This will help new members understand and work with the project's data effectively.

5. Outline Your Methods: Create a detailed METHODS.md file where you describe the methodologies, software, and tools you will be using in your research. This transparency will support reproducibility and collaborative development.

6. Set Up Project Management: Utilize the 'Issues' and 'Projects' features on GitHub to track tasks, discuss ideas, and manage your workflow. This can help in maintaining a clear view of progress and priorities.

7. Add a License: Choose and include an appropriate open-source license for your project, ensuring that the broader community understands how they can use and contribute to your work.

8. Create Contribution Guidelines: Establish a CONTRIBUTING.md file with instructions for members on how to propose changes, submit issues, and contribute code.

9. Review and Merge Workflow: Decide on a workflow for reviewing and merging changes. Will you use branch protection? Who will have merge privileges? Document this process to avoid confusion.

10. Establish Communication Channels: Beyond GitHub, set up additional communication channels like Slack, Discord, or email lists for quick and informal discussions.

Remember, the goal is to make your repository clear, accessible, and useful for all current and future members of your working group. Happy researching!