There is a lot of concern today about adopting new AI tools, and there are certainly important questions in ethical use and best practices. However, there are also a number of AI-driven applications in Data for Good that deserve notice. This month, Stats4Good’s annual Earth Day column presents some of the ways AI-driven tools are being used in citizen science projects to preserve and protect the living world around us.
One area in which AI is having a growing effect is deforestation. This critical area for environmental advocacy was named a 2026 Data for Good Top Challenge. The Forest Foresight project from the World Wildlife Fund is an AI tool leveraging satellite images and other data to track and forecast deforestation at a local level. Researchers at the University of Eindhoven in the Netherlands led a collaboration to develop the AI further, including a new R package and GitHub repository. The group is now able to forecast deforestation across the global tropical zone within 30 degrees of the equator. The WWF is looking for new partners to extend the Forest Foresight project.
AI for the environment also drives a number of phone apps, making the technology easily accessible to almost everyone. The Merlin bird ID app from the Cornell lab of ornithology is popular for identifying birds using images or by their song. It’s free to download and works on both iOS and Android. One of Merlin’s greatest strengths is its range, covering thousands of bird species throughout most of world. I have used it in both North America and Europe and can attest to its accuracy and ease of use. (The app works in the rain but your phone might not. If it’s raining or you are hiding in a lake or swamp to see birds, you will want a clear plastic cover for the phone.)
AI is also at the heart of many programs that leverage crowd-sourced data captured and uploaded by environmental Data for Good activists. A great example of this is CoralNet from the University of California at San Diego. Registered users can upload benthic (lowest layer of an aquarian environment) images to a website for AI analysis and annotation. You can view your images with the AI-generated annotations, and all the data goes into the CoralNet database to support research on protecting the environment.
Another leading platform in this space is iNaturalist. It has a phone app in which participants can upload images and audio to a crowd-sourced database and receive support for identification from a combination of AI and human participation. But iNaturalist is more than an app; it’s a group of millions of environmental activists in a social media community creating and leveraging crowd-sourced data. Participation is free, and the website has good information about making observations, uploading the data, and networking with other naturalists.
Beyond all the many ways AI is being leveraged in environmental advocacy, these platforms also offer an opportunity to teach AI ethical use and best practices in general. A European team led by Maryam Lotfian wrote an outstanding open-access paper in Nature offering “a vision for responsible AI integration in citizen science.” This important work can contribute to much more than environmental activism; it shows how AI apps can be used as a living laboratory to teach people what AI can do—and what it can’t.
AI phone apps like Merlin can be used to teach the fundamentals of responsible AI. Students, professionals, and government leaders can learn about hallucinations, data privacy and protection, the importance of keeping a human in the loop when using AI, and much more.
The potential of environmental AI tools for engaging with the public about the benefits and potential risks of AI cannot be overstated. This is an Earth Day project in which everyone can participate. ASA chapters can hold an AI for Earth Day town hall in which the public can learn about citizen science and AI best practices and engage with the ASA all at once. The opportunities here are endless, so now is the time to plan an activity for Earth Day and beyond in Data for Good.
Getting Involved
The 2026 Statistical Learning and Data Science conference is accepting submissions for presentations through May 1. The conference will be in New York City from November 1–3. Also, check out the ASA Student and Early Career Travel Fund. It provides support for travel to ASA meetings and conferences. Applications are due three months before the event, so submissions for JSM need to be in by May 1.
David Corliss
With a PhD in statistical astrophysics, David Corliss works as a data scientist in industry. He serves on the ASA Board as a Council of Chapters representative and is the founder of Peace-Work, a data for good nongovernmental organization.
This column is written for those interested in learning about the world of Data for Good, where statistical analysis is dedicated to good causes that benefit our lives, our communities, and our world. If you would like to know more or have ideas for articles, contact David Corliss.
Leave a Reply