Automated cartography using AI can identify individual people, invasive plant species, buildings, and more from aerial survey data.
Integrating deep learning into geospatial analysis is feasible by leveraging open-source frameworks and interfaces provided by platforms like SRE.
Deep dives
GIS and AI in Spain's Geospatial Industry
Gabriel Ortiz, principal geospatial information officer at the government of Cantabria in Spain, discusses the exciting developments in the AI industry in Spain. With a strong engineering workforce and a thriving startup ecosystem, Spain provides a great environment for AI professionals. Gabriel highlights the importance of engaging professionals from Spain and shares his positive experience working in AI in the country.
Adopting Deep Learning in Geospatial Analysis
Gabriel Ortiz explains his journey as a geospatial practitioner transitioning into deep learning. With a background in GIS (Geographical Information System), Gabriel shares how he started exploring deep learning techniques and integrating them into geospatial analysis workflows. He emphasizes the importance of gaining hands-on experience and learning the concepts underlying AI to successfully integrate AI into the geospatial industry.
Challenges and Integration of Deep Learning in Geospatial Tools
Gabriel Ortiz discusses the challenges and integration of deep learning in geospatial tools. While at first, it may seem daunting and intimidating, Gabriel emphasizes that with the right tools and resources, integrating deep learning into geospatial analysis is feasible. He highlights the importance of leveraging open-source frameworks and interfaces provided by platforms like SRE, which facilitate the application of deep learning techniques in the geospatial industry.
Automated Cartography with AI in Geospatial Analysis
Gabriel Ortiz shares his experiences with automated cartography using AI in geospatial analysis. By applying deep learning models to aerial surveys and satellite imagery, Gabriel and his team have been able to generate maps and classify various elements such as vegetation, buildings, roads, and more. While there are limitations and mistakes, Gabriel highlights the potential of combining traditional GIS techniques with AI models to improve the accuracy and efficiency of cartography.
Your feed might be dominated by LLMs these days, but there are some amazing things happening in computer vision that you shouldn’t ignore! In this episode, we bring you one of those amazing stories from Gabriel Ortiz, who is working with the government of Cantabria in Spain to automate cartography and apply AI to geospatial analysis. We hear about how AI tooling fits into the GIS workflow, and Gabriel shares some of his recent work (including work that can identify individual people, invasive plant species, building and more from aerial survey data).
Changelog++ members save 3 minutes on this episode because they made the ads disappear. Join today!
Sponsors:
Fastly – Our bandwidth partner. Fastly powers fast, secure, and scalable digital experiences. Move beyond your content delivery network to their powerful edge cloud platform. Learn more at fastly.com
Fly.io – The home of Changelog.com — Deploy your apps and databases close to your users. In minutes you can run your Ruby, Go, Node, Deno, Python, or Elixir app (and databases!) all over the world. No ops required. Learn more at fly.io/changelog and check out the speedrun in their docs.
Typesense – Lightning fast, globally distributed Search-as-a-Service that runs in memory. You literally can’t get any faster!