[HN Gopher] Show HN: Safe Routes. real time turbulence data, ML ...
       ___________________________________________________________________
        
       Show HN: Safe Routes. real time turbulence data, ML predictions
       with an iPad
        
       Author : oron
       Score  : 110 points
       Date   : 2024-06-29 05:56 UTC (17 hours ago)
        
 (HTM) web link (skypath.io)
 (TXT) w3m dump (skypath.io)
        
       | oron wrote:
       | At SkyPath we have a simple solution that doesn't involve
       | installing any HW on the aircraft and uses the airline issued
       | iPad the pilot already uses for other important tasks to help
       | fight Clear Air Turbulence. We use the iPad's accelerometers to
       | measure and report turbulence in real time and collect this data
       | via the internet where it's processed in AWS by our machine
       | learning model to produce customized alerts for each flight that
       | uses our service on incoming CATs in their route.
        
         | tobr wrote:
         | What goes into developing, testing, calibrating something like
         | this?
        
           | oron wrote:
           | Apart from usual SW tests, Lots of testing with airlines and
           | experienced pilots. Processing feedback and improving the
           | model step by step over the course of several years.
        
             | nerdponx wrote:
             | I'm very curious how you "bootstrap" a model like that. Do
             | you start with a physics simulation? Make an educated guess
             | and then get pilots to label when it's wrong in order to
             | incrementally improve? Recruit pilots to manually track CAT
             | events?
             | 
             | I've had to build a few of these kinds of models over the
             | years, and it's consistently the hardest task I've faced in
             | my DS career.
        
               | oron wrote:
               | The second is closer to reality , initially let pilots
               | (lots of them) label flight events and after landing take
               | all data and build the algorithm around their initial
               | labels. The when there are more pilots let them label
               | agree / disagree and relabel etc.
               | 
               | Another aspect is you have usually two iPads in the
               | cockpit for captain and first officer so you can
               | correlate and match what both accelerometers read.
        
               | nerdponx wrote:
               | Thanks! It's nice validation to know that my approach to
               | this kind of problem similar to that of a successful AI
               | startup.
        
           | mayasp wrote:
           | Ipad accelerometers and GPS
        
         | ammmir wrote:
         | amazing! it seems like much of the innovation on the flight
         | deck is happening in iPad apps.
         | 
         | i'm curious, in the beginning, before you had so many users of
         | the app, how did you convince pilots/airlines to install
         | SkyPath before it had enough user-generated turbulence data for
         | its ML model? it almost feels like a chicken-and-the-egg
         | problem: you need enough reports before it's useful around the
         | world at all imaginable air routes, or maybe there's enough
         | air/wind data. interesting stuff!
        
           | mayasp wrote:
           | The effect on the route is immediate. There is no
           | installation or integration so the moment you deploy (with a
           | reasonable fleet size) you have data. Those that where quick
           | to understand the concept embraced technology very fast even
           | without initial data set in the route
        
           | oron wrote:
           | We had to give incentives for the first airline partners and
           | give the product for free for a long trial period at the
           | early years to be able to have initial installs. It was a
           | long ride including Covid which came in the middle and didn't
           | help. In the last years since we have several big airline
           | partners this is less of a problem.
        
         | vivzkestrel wrote:
         | how exactly are you using an accelerometer to determine
         | turbulence
        
           | sigmoid10 wrote:
           | How else would you detect it? Accelerometers seem perfect for
           | this use case.
        
           | oron wrote:
           | By analyzing the acceleration patterns that the iPad the
           | pilot has in the cockpit which is securely attached to the
           | aircraft is measuring. Cleaning out noise such as engine and
           | other non CAT noise and training our model to identify these
           | and also predict future events in the next 3 hours by looking
           | at the current data. It takes millions of events and lots of
           | pilots which help train the initial model and fine tune it.
        
         | tedd4u wrote:
         | Does your app have to run in the foreground on the iPad during
         | the flight? Or can the crew user other apps in flight?
        
           | oron wrote:
           | Can run in the background, pilot can use any other app
           | meanwhile. Or just leave the iPad with screen off. Our app
           | keeps recording and alerting as long as you are in flight.
        
             | hollerith wrote:
             | I'm assuming that the most valuable data for predicting
             | turbulence during a flight is timely data from the
             | accelerometers of the iPads on nearby airliners, which gets
             | me curious as to whether these iPads usually have
             | connectivity (to your AWS servers) during a flight, and how
             | that connectivity is provided. (I'm guessing satellite.)
        
               | oron wrote:
               | Yes, satellite internet is now standard on many Western
               | airlines. In addition to this, we utilize weather data
               | and real-time turbulence reports to predict Clear Air
               | Turbulence (CAT) events across the entire sky, even where
               | iPads are currently not on flights.
        
         | btgeekboy wrote:
         | Didn't ForeFlight just come out with something similar
         | recently? https://blog.foreflight.com/2024/05/07/smooth-skies/
         | They don't mention ML specifically, but I imagine their install
         | base is a tad larger and can therefore gather more real data.
         | Is your solution different?
        
           | buildsjets wrote:
           | Note that Foreflight is a Boeing product. Therefore they
           | could potentially have access to actual real-time aircraft
           | data that this product would not.
        
             | oron wrote:
             | Our solution is compatible with Airbus, Boeing, or any
             | other aircraft. It's important to note that connecting to
             | the aircraft systems can be more expensive and add
             | maintenance and complexity costs for the airline.
        
           | oron wrote:
           | We have a partnership with Jeppesen, a Boeing company, for
           | their Flight Deck Pro product. With this collaboration, users
           | can access our data layer and predictions, and also report
           | real-time turbulence within their app. While I'm not
           | extensively familiar with the inner workings of ForeFlight,
           | based on what I've heard, it relies on an external hardware
           | solution, and its coverage and quality are not comparable
        
       | smithcoin wrote:
       | Do you offer turbulence predictions for consumers? I'm scared of
       | flying and would love to know if my ride will be smooth.
        
         | oron wrote:
         | Right now flight predictions and route quality are offered only
         | to pilots who are operating the flight and to dispatchers.
         | There are discussions with the airlines to integrate our
         | technology into their apps but at the moment there is no such
         | solution available.
        
         | Ylpertnodi wrote:
         | Don't be scared of flying, be scared of crashing. Crashing
         | doesn't happen that often.
         | 
         | Try watching/downloading flightradar24 - the sheer number of
         | flights is staggering. Then multiply them by the number of days
         | since you can (without assistance) _actually_ remember hearing
         | about a plane crash.
        
         | havaloc wrote:
         | My site focuses on the consumer side and does just that:
         | https://turbulenceforecast.com
        
           | oron wrote:
           | nice work! where is the data coming from?
        
             | havaloc wrote:
             | We're processing noaa data and making it easy to
             | understand. I'd love to license your data to display in our
             | app behind our paywall.
        
       | scottmcdot wrote:
       | Out of curiosity, was this product a result of a company 'pivot'
       | after the Singapore Airlines flight SQ321 turbulence incident?
        
         | oron wrote:
         | Nope, company was started by commercial / ex-military pilots
         | who scratched their own itch and still today is run by pilots
         | :-)
        
       | VBprogrammer wrote:
       | From the testimonials it seems this is used for tactical rather
       | than strategic planning. Honestly, that would keep me up at
       | night.
       | 
       | It's similar to problems which have been previously caused by a
       | reliance on in cockpit weather data delivered by satellites. At
       | worst it can be 15 minutes out of date and more than one eager
       | light aircraft pilot has flown into the center of a storm cell
       | which wasn't there 15 minutes ago - taking his family with him.
       | 
       | Its only turbulence but worst case scenario with turbulence is
       | still pretty bad - injuries and even deaths are completely
       | possible outcomes.
        
         | oron wrote:
         | Good comment! our algorithms take into account time of report
         | as recorded by the aircraft so latency or offline aircraft is
         | not an issue. Surprisingly most CAT phenomena is pretty stable
         | and can stay in the same area for hours at time.
        
           | VBprogrammer wrote:
           | Thanks for responding. That is interesting. I guess you also
           | have the advantage that current "state of care" is sharing a
           | few radio messages with other aircraft with lots of
           | subjective judgements.
        
           | lawrenceduk wrote:
           | Mostly mountain wave presumably?
        
       | julienreszka wrote:
       | Why not say who this is for?
        
         | oron wrote:
         | This solution is for commercial airlines, pilots and
         | dispatchers and for general and business aviation.
        
       | ed_db wrote:
       | How do you eliminate false positives from pilot usage of the
       | device or knocking into it? I wonder how long it will be before
       | flight insurers start using this data for hedging following the
       | Singapore Airlines flight SQ321 turbulence incident.
        
         | oron wrote:
         | Valid observation: turbulence patterns differ from pilot
         | tapping and can be recognized and disregarded. While complete
         | elimination of false positives isn't always feasible, employing
         | various techniques allows us to significantly minimize such
         | occurrences, thereby mitigating their impact.
        
       | sandworm101 wrote:
       | Forget any app. Just _put on your seatbelt_. If you are wearing a
       | seatbelt, the worst that will happen is spilled coffee.
       | 
       | I cannot stand the sound of a hundred belts unclicking all at
       | once the moment the seatbelt sign turns off. Idiots. The presence
       | of a seatbelt across one's lap is the least of the various
       | tortures associated with modern air travel.
        
         | oron wrote:
         | Some of the most severe injuries occur among crew members
         | because they must rush to secure passengers in their seats,
         | often being the last to fasten their own seat belts.
         | Additionally, when turbulence reaches a certain intensity, the
         | aircraft must undergo costly structural testing on the ground,
         | which disrupts the airline's schedule significantly.
        
         | pavel_lishin wrote:
         | To be absolutely pedantic, the worst that will happen is the
         | unbuckled dingdong sitting next to you becoming a loose item
         | and banging into you.
        
       | qwertyuiop_ wrote:
       | How does the app connect to the aircraft's internet during flight
       | ?
        
         | oron wrote:
         | Cockpit WiFi that's open only for the crew.
        
           | culopatin wrote:
           | Does the crew also lose internet when flying over the arctic
           | circle?
        
             | oron wrote:
             | It depends on the provider that the airline has partnered
             | with, I suppose. We don't manage the satellite
             | connectivity, so I can't provide specifics on that.
             | However, in areas with fewer ground stations, disruptions
             | are more likely. Our app and servers are designed to
             | function effectively on unreliable internet connections. it
             | downloads prediction data for several hours ahead and is
             | capable of uploading turbulence data once the internet
             | connection stabilizes.
        
               | culopatin wrote:
               | In my last flight the disconnection over the arctic
               | circle lasted about 5hs. Is the data still relevant then?
               | Does turbulence happen in cycles and is predictable that
               | way?
        
               | oron wrote:
               | Five hours is a bit long; you can choose in the app how
               | far ahead you would like to see. We typically recommend
               | looking two hours ahead. This way, for the initial two
               | hours, you'll have some data that may be partially
               | outdated but still better than having no information at
               | all.
        
       | turrican wrote:
       | You guys have a great product, I fly for a major airline and
       | really like it. Hurry up and get Delta onboard so we can get
       | their data too: I've used their in-house app at my old job and
       | Sky Vector is much better.
       | 
       | Any plans to change the Jepp integration? Most of my colleagues
       | don't use it, too much data displayed at once. I'm not sure of a
       | solution but would love to hear if you guys have any ideas.
        
         | oron wrote:
         | Thank you. We are actively working to onboard as many airlines
         | as possible, and partnering with Delta would be highly
         | beneficial. The more data we have, the safer and more efficient
         | flights become.
         | 
         | Regarding the integration with Jeppesen, we would greatly
         | appreciate hearing more about any issues you encounter and
         | receiving your feedback
        
       | TheJoeMan wrote:
       | Anecdote: I recently flew from Texas to Florida, and the pilot
       | requested a reroute south around Louisiana to avoid a storm cell.
       | ATC denied reroute due to "staffing shortage" and forced us into
       | an extremely uncomfortable ride.
       | 
       | I've been hearing about statistics for turbulence incidences
       | increasing, and wonder if this type of thing is a contributing
       | factor. With this app you'd get a warning but I wonder if you
       | could do anything about it.
        
         | oron wrote:
         | Good question, turning on the seatbelt sign in this case is a
         | good start.
        
       | e12e wrote:
       | Cool product. If it helps most flights avoid turbulence - how
       | will you continue to record areas with turbulence? :)
       | 
       | Or is the steady state simply clear flight paths with continuous
       | adjustments as the clear paths drift?
        
         | oron wrote:
         | Typically, flights do not deviate from their planned routes for
         | non-severe turbulence levels. It's safer and simpler to have
         | passengers remain seated with the seatbelt sign on. Our model
         | considers weather inputs alongside real-time data,
         | acknowledging that weather is continuously changing and
         | somewhat unpredictable. Therefore, we don't perceive this issue
         | as significant
        
       | therobots927 wrote:
       | This is so cool and all I could think when reading the
       | description is how much I want to work with this data lol.
        
       ___________________________________________________________________
       (page generated 2024-06-29 23:00 UTC)