Subvolts take AI tackles environmental data gaps, using Google tools for global forest and species monitoring. Jun 19, 2025 - Developers
- Learn about open-source AI tools like Jeo and GeeFlow for deep learning-based remote sensing.
- Business
- Understand how AI and tools like Google Earth Engine can monitor environmental assets and track ecological changes.
This episode features a solid interview on applying AI to significant environmental research challenges.
The Nature of AI: Solving the Planet's Data Gap with Drew Purves
Audio streams from Hannah Fry. Your place is remembered on this device.
From Subvolts
Summary and analysis by Subvolts editorial, AI-assisted.
This Google DeepMind podcast episode features Drew Purves discussing how AI can address the planet's data gap, particularly concerning natural forests and species mapping. Host Hannah Fry explores how AI tools, like those developed at Google, can analyze vast amounts of remote sensing data to monitor environmental changes and biodiversity. The conversation highlights AI's role in ecological research and conservation efforts.
This episode explains how computers can learn from satellite images to understand forests and animals worldwide. It shows how this helps scientists track environmental changes and protect nature, which is important for everyone.
This episode offers insight into how AI, especially deep learning and remote sensing, tackles environmental data challenges. It's for researchers, conservationists, and anyone interested in AI's real-world applications beyond generative models. Listeners learn how Google's tools, like Earth Engine, are used for ecological monitoring, connecting to current efforts by Google Gemini and other labs to apply AI to scientific discovery and planetary health.
- HostHannah Fry
- GuestDrew Purves
- Guest: Drew Purves
- Episode Title: The Nature of AI: Solving the Planet's Data Gap
- Show: Google DeepMind: The Podcast
- Length: 40 minutes
- Mentioned Tools: Google Earth Engine, Perch, DolphinGemma
Further reading:
- Natural forests of the world: paper, data and benchmarks
- Forest loss drivers: paper, summary from WRI, and blog from GFW
- Forest loss drivers code: Google Earth Engine; at WRI; at GFW; or Zenodo.
- Deep learning based remote sensing (open source): Jeo, GeeFlow
- Species mapping paper: Arxiv
- Google resources: Google Earth Engine. Agri with Google, wildlife cameras
- Perch: code, paper
- Perch x coral reefs: Blog
- Agile Modelling: paper, code
- DolphinGemma: blog
P
- remote sensing
- Drew Purves
- gathering information about something from a distance, like using satellites to view Earth
- deep learning
- Drew Purves
- a type of AI that uses complex computer systems to learn from large amounts of data
44 minCan AI help us better predict the weather?
WithPeter Battaglia
45 minThe mathematics of AI uncertainty
WithZoubin Ghahramani
53 min
1 hBuilding Gemini's Coding Capabilities
WithConnie Fan, Danny Tarlow
27 minSergey Brin on the Future of AI & Gemini
WithSergey Brin
Questions people ask
- What is the main challenge discussed regarding environmental data?
- The episode addresses the planet's data gap, particularly in monitoring natural forests and species, and how AI can help solve this.
- What Google tools are mentioned for environmental analysis?
- Google resources like Google Earth Engine, Agri with Google, and wildlife cameras like Perch are highlighted for their use in remote sensing and ecological monitoring.
Page generated Oct 19, 2026. Summaries are Subvolts' own; the audio, artwork and notes belong to Hannah Fry.