Artificial academy 2 lag crash
![artificial academy 2 lag crash artificial academy 2 lag crash](https://images-na.ssl-images-amazon.com/images/I/41ISw3NOBSL._SY279_BO1,204,203,200_.jpg)
![artificial academy 2 lag crash artificial academy 2 lag crash](https://images-na.ssl-images-amazon.com/images/I/41HsCo58c3L._SX323_BO1,204,203,200_.jpg)
The results were striking: The Winds Aloft prediction was off by 56.2 miles, in an easterly direction, while the researchers' prediction was off by only 11.6 miles, in the same direction.Ī small aircraft would spend much less time traveling the same route and climbing through those altitudes, but the NOAA error is "a pretty big cumulative error in terms of winds across altitude profiles," Kapoor says. Equipped with a GPS device, barometric and temperature sensors, and an onboard computer, the balloon was carried by the wind, reaching an altitude of 95,000 feet.īefore launch, they estimated the endpoint of the balloon's journey-when it would reach maximum altitude and rupture-using their own model, as well as the Winds Aloft model from the National Oceanic and Atmospheric Administration (NOAA). To help with testing the accuracy of their model, which they call Windflow, Kapoor and Horvitz-along with two high school researchers, Spencer Laube and Horvitz's son, Zachary, both students at the Seattle Academy of Arts and Sciences-launched a helium-filled high-altitude balloon in eastern Washington state in June 2013. In essence, they came up with a way to solve a puzzle despite many missing pieces. They then figured out a way to exploit this property by taking observations from nearby wind stations, combining it with the FAA data, and then using a probabilistic model to infer the wind velocity. Solving this conundrum involved a creative leap-what Kapoor calls their "biggest intellectual aha moment." They realized that winds exhibit a special property known as spatial regularity-that is, nearby airplanes are likely to encounter similar winds. If you know the groundspeed and the airspeed, along with where the plane is heading and its actual course over the ground, you can calculate the wind speed and direction.īut one key piece of data was unavailable: The data provided by the FAA does not include information about where a plane is headed. That sounds straightforward enough-if no wind is present, the groundspeed will match the airspeed and the plane will fly along its intended course. In other words, could airplanes in flight be employed as a vast sensor network to determine atmospheric conditions? Could data available today be used to infer winds on a large scale without special plane-based wind sensors and new infrastructure to access and combine signals from planes?īecause winds will change an aircraft's flight path and affect the groundspeed, the researchers determined that they could estimate the wind conditions mathematically. "Our research question was: Could we take the information that was already available and use it to predict wind conditions without needing any additional infrastructure?" Kapoor says.
![artificial academy 2 lag crash artificial academy 2 lag crash](https://attachments.f95zone.to/2020/04/648314_2020_0414_0034_54861.png)
That means people can view any commercial aircraft's flight plan-the planned airspeed (fixed cruising speed relative to the air mass), altitude, distance, and route-as well as the observed groundspeed (speed relative to the ground), altitude, longitude, and latitude at any moment during the flight, with only a small time lag.
![artificial academy 2 lag crash artificial academy 2 lag crash](https://images-na.ssl-images-amazon.com/images/I/515s9Vp-QwL._SX339_BO1,204,203,200_.jpg)
It turns out that data about the tens of thousands of flights over the United States each day are publicly available from the Federal Aviation Administration (FAA). They focused on using aircraft in flight as a possible source of data. Kapoor and his colleague Eric Horvitz, a Microsoft distinguished scientist and managing director of Microsoft Research Redmond, began looking for such a solution-specifically, one that would not involve installing new sensors or other equipment. In our data-driven, sensor-filled world, that lack of precision motivated an effort to devise a better solution. Pilots learn to plan for longer flight times and greater fuel consumption, he says, in case the actual wind conditions are not as expected. "They would tell you, 'Winds Aloft is often not accurate, so you have to take that into account when you make your flight plan,'" says Kapoor, a Microsoft researcher who specializes in machine learning and decision-making.