• sphericalcube@lemmy.dbzer0.com
    link
    fedilink
    English
    arrow-up
    0
    ·
    8 days ago

    Interesting article, but only surprising part is that this hasnt been done before (mass analysing the Lidar Data). This seems like something that could have been done with much less compute and more specialized machen Learning algorithms already years ago. I mean most shapes that point to old buildings under the foilage are not exactly suddle in the Lidar Data.

    • glimse@lemmy.world
      link
      fedilink
      English
      arrow-up
      0
      ·
      8 days ago

      Mass lidar scanning IS being done! They’ve found tons of previously unknown settlements and learned a lot more about the ones we did know about.

      There’s just a LOT to scan and you’re limited on distance. IIRC these lidar drones do multiple passes over an area so you’d have to be pretty close to deploy/recharge them.

      In pretty sure they were using deep learning as part of it, before everything was called AI.

  • ChicoSuave@lemmy.world
    link
    fedilink
    English
    arrow-up
    0
    ·
    8 days ago

    Update (11 November): it turns out the site had already been mapped in Estrada-Belli et al. 2025. The agents missed it while going through the literature, so they rediscovered it rather than discovered it (it just wasn’t in INAH’s register yet). Still work to do then!

    Not undiscovered. Bad AI output. This is, ultimately, an article about slop.