URI: 
        _______               __                   _______
       |   |   |.---.-..----.|  |--..-----..----. |    |  |.-----..--.--.--..-----.
       |       ||  _  ||  __||    < |  -__||   _| |       ||  -__||  |  |  ||__ --|
       |___|___||___._||____||__|__||_____||__|   |__|____||_____||________||_____|
                                                             on Gopher (inofficial)
  HTML Visit Hacker News on the Web
       
       
       COMMENT PAGE FOR:
  HTML   New updates and more access to Google Earth AI
       
       
        jasongill wrote 1 day ago:
        Just tested and while it seems interesting, there doesn't seem to (yet)
        be any intelligence about the imagery itself from what I can tell. For
        example, it can give me insights about vegetation data overlayed on a
        map (or try to), but it can't "find the most fertile grassland in this
        radius".
        
        When there is a way to actually "search" satellite images with an LLM,
        it will be a game changer for businesses (and likely not to the
        ultimate benefit of consumers, unfortunately)
       
          Demiurge wrote 1 day ago:
          How would you even define “most fertile grassland”? What does
          “fertile” mean - soil nutrients, water availability, or
          productivity for a specific crop? And what counts as “grassland”?
          Are you talking about a 1 acre parcel, something for sale, or land
          next to a road?
          
          There’s already data for all of this: SSURGO soil maps, vegetation
          indices, climatology datasets, and more — that could help you find
          the “most something” in a given radius. But there are too many
          variables for a single AI to guess your intent. That’s not how
          people who actually farm, conserve, or monitor land tend to search;
          they start from a goal and combine the relevant data layers
          accordingly.
          
          In fact, crop-specific fertility maps have existed for decades, based
          on soil and climate averages, and they’re still good enough for
          most practical uses today.
       
            jasongill wrote 14 hours 14 min ago:
            It was just an example, but you are correct. A more "imagery
            required" example would be "Find all the houses with roofs that
            have been damaged in the last 6 months" or something like that
            which could be used by salespeople or insurers
       
              Demiurge wrote 12 hours 25 min ago:
              That's a good example, yes. I think this one can actually be
              interpreted by multiple AI agents to do search on the algorithms,
              or could even train a model, and then run the model. How amazing
              would it be, if this could actually all happen based on a few
              prompts :)
       
        Reubend wrote 1 day ago:
        Instead of all this stuff, I'd like to see Google use their ML chops to
        "solve" weather forecasting and deliver ultra accurate predictions a
        few days ahead.
       
          NocturnalWaffle wrote 1 day ago:
          They are working on this and have had really good results: [1]
          
  HTML    [1]: https://deepmind.google/science/weathernext/
  HTML    [2]: https://deepmind.google/discover/blog/gencast-predicts-weath...
       
          elpakal wrote 1 day ago:
          But then who’s gonna spend all day Googling stuff when the weather
          changes their plans again?
       
        kittikitti wrote 1 day ago:
        Guess which corporation just announced they're profiting off of the
        government shutdown of vital environmental and climate agencies? I
        wonder why they failed to mention any of that in this press release.
       
        Mashimo wrote 1 day ago:
        Mhh, don't we already have conventional ways of telling where a
        flodding might happen?
       
        polyomino wrote 1 day ago:
        I have found that using LLMs to generate queries for Overpass (Open
        street map query language) works really well. Great alternative if you
        don't care to deal with corporate nonsense.
       
          macNchz wrote 1 day ago:
          I've been able to do really cool stuff that I would never have
          otherwise bothered with by having an LLM generate Overpass queries +
          walk me through complex setup steps with QGIS.
       
            groby_b wrote 1 day ago:
            The flipside is that QGIS and overpass are so complicated that only
            with LLM assistance they're truly usable.
            
            (Applies more to QGIS than to overpass, though both could stand to
            improve a lot in terms of usability)
       
        ecommerceguy wrote 1 day ago:
        In 2001 we used Erdas Imagine to do this type of work. It required
        humans to train the software using heads-up digitizing. Dare I say
        machine learning on Pentium workstations?
        
        edit, looks like they have ai too now. could be neat to play with after
        how long has it been. jeesh.
       
        lacoolj wrote 1 day ago:
        Once Zillow and Redfin start doing this, that will be game-changing
       
        Jordan-117 wrote 1 day ago:
        I have some old screenshots of interesting locations from Google Earth
        circa 2006-2012 that I've never been able to track down. I wonder if
        something like this would be capable of geolocating them somehow --
        like reverse image search for landscapes.
       
          nomel wrote 1 day ago:
          There's a whole community (with world tournaments [1]) around finding
          places from pictures: geoguessers. The top people are absolutely
          incredibly [2]. There are also AI trained for this purpose. Although,
          the perspective they use is usually from street level. [1]
          
  HTML    [1]: https://www.youtube.com/watch?v=u3sVtwexp0o
  HTML    [2]: https://www.youtube.com/@georainbolt
       
            Jordan-117 wrote 1 day ago:
            A few people recommended Geoguessr (and people like Rainbolt are
            definitely amazing), but yeah I reckon they're hyperspecialized on
            reading clues in actual street view imagery, not natural satellite
            footage like this.
       
              1d22a wrote 1 day ago:
              Rainbolt often finds locations for people who have old photos of
              friends/family who have passed away etc., so the skills
              definitely seem to extend past just street view.
       
          tom1337 wrote 1 day ago:
          Out of interest: have you already tried using GPT 5 (reasoning /
          thinking) for that? I've had quite some success in the past using
          them to track down such places.
       
            Jordan-117 wrote 1 day ago:
            Yeah, that and Gemini 2.5. They actually were able to help identify
            a handful based on context clues, or at least narrow it down enough
            that I could find it myself. But there were three I couldn't crack
            -- even a forum dedicated to solving GE puzzles came up empty:
            
  HTML      [1]: https://googleearthcommunity.proboards.com/thread/10731/ul...
       
              theletterf wrote 1 day ago:
              First photo could be Namibia? 29°40'04"S 18°11'12"E
       
                Jordan-117 wrote 1 day ago:
                Hmm, plausible... though I'll have to go back in time and kick
                myself if it turns out I captioned it with the wrong continent!
       
                  theletterf wrote 1 day ago:
                  Gemini says:
                  
                  "This looks almost certainly like a satellite view of a
                  region in Western Australia, such as the Pilbara or the
                  Hamersley Range. The dark areas are likely ancient, iron-rich
                  rock formations (ironstone), and the surrounding soil is
                  iconic of what's known as Australia's "Red Centre."
       
              howenterprisey wrote 1 day ago:
              Maybe Geoguessr players would be good at identifying them as
              well?
       
        chrisshroba wrote 1 day ago:
        > Bellwether, a moonshot at Alphabet's X, is using Earth AI to provide
        hurricane predictions insights for global insurance broker McGill and
        Partners. This enables McGill's clients to pay claims faster so
        homeowners can start rebuilding sooner.
        
        Hm, I'm quite skeptical about this claim.
       
          citizenpaul wrote 22 hours 17 min ago:
          Sorry but our AI said your home destroyed in the hurricane was not in
          fact destroyed by a hurricane.    Claim denied.  We accept no further
          inquiries on the matter.
          
          100% of claims paid out instantly, so its kinda true.
          
          I suspect you don't have an MBA /s
       
          notatoad wrote 1 day ago:
          quicker approvals probably also means quicker denials, if you want to
          look at the negative side of it.
       
            giobox wrote 1 day ago:
            A quicker denial is still better than a long drawn out one, even if
            it isn't the outcome you might want.
       
          Legend2440 wrote 1 day ago:
          Seems plausible to me. It would allow them to start contracting CAT
          adjusters as soon as a hurricane is expected, before other insurers
          start bidding for them.
          
          Will this actually pay off for them? Who knows. But insurers are
          quite into ML for claims/underwriting these days, so I'd believe
          they're giving it a try.
       
            KRAKRISMOTT wrote 1 day ago:
            Wdym by 'bid for them'? Won't the MGA want to get rid of their
            contracts in an area that's about to be hit by a hurricane ASAP?
       
              olq wrote 1 day ago:
              More like booking them for the availability and likely a fixed
              non-hurricane-panic price.
       
              Legend2440 wrote 1 day ago:
              You need a large workforce of adjusters to handle big events like
              a hurricane, but you don’t need them all the time. So
              catastrophe adjusters are often independent contractors.
              
              Pay is good but hours are long, and you are often deployed far
              away from home.
       
              piperswe wrote 1 day ago:
              They want to pay adjusters and contractors the least amount
              possible - that's what they're bidding on
       
          moffkalast wrote 1 day ago:
          > McGill and Partners
          
          Hi, I'm Saul Goodman. Did you know that you have hurricanes? The
          constitution says you do! And so do AI.
       
          apples_oranges wrote 1 day ago:
          Haha yeah. Perhaps a marketing gimmick with an asterisk..
       
          tencentshill wrote 1 day ago:
          Could be a nice expensive contractor option for replacing the NOAA's
          public data that we lost. But it probably wont be picked up because
          it has to study the climate, which is a bad word now.
       
            CobrastanJorji wrote 1 day ago:
            You can totally create a private version of NOAA so long as you
            keep the messaging about insurance intelligence and never, ever
            speculate out loud about the causes of hurricanes. And if that's
            not enough, just do what Meta did and hire some shmuck like Robby
            Starbuck to signal that you're on the right team.
       
              mrtesthah wrote 1 day ago:
              I see the humor in this but you'd still need to operate your own
              satellites.
       
                vineyardmike wrote 1 day ago:
                Google (with partner companies) launched a climate-monitoring
                satellite last year. Thanks to SpaceX, it’s cheaper than ever
                for private organizations to launch satellites.
       
                wlesieutre wrote 1 day ago:
                What they want is for the government to run the satellites and
                provide the data on the taxpayers' dime, but only let private
                companies interpret that data so they can sell their
                forecasting [1] (note: old news)
                
  HTML          [1]: https://www.cnn.com/2017/10/14/politics/noaa-nominee-a...
       
        diogenico wrote 1 day ago:
        It shifts from map layers to answer “what/where/why now?” rather
        than just “show me X.”
        
        And the Gemini-in-Google Earth bit could lower the barrier for non-GIS
        folks.
       
       
   DIR <- back to front page