logo
Passenger jet had to abort takeoff to avoid runway collision at New York's LaGuardia Airport

Passenger jet had to abort takeoff to avoid runway collision at New York's LaGuardia Airport

Federal officials are investigating why two planes got dangerously close on a runway at New York's LaGuardia Airport earlier this month despite the airport being equipped with an advanced surface radar system that's designed to help prevent such close calls.
Both the Federal Aviation Administration and the National Transportation Safety Board said Monday that they are investigating the May 6 incident when a Republic Airways jet had to abort takeoff because a United Airlines plane was still taxiing across the runway.
In audio from the tower that ABC obtained from the website www.LiveATC.net, the air traffic control said to the pilot of the Republic Airways jet: 'Sorry, I thought United had cleared well before that.'
At the time that controller was directing the Republic Airways jet to takeoff, a ground controller on a different radio frequency was directing the United plane to a new taxiway after it missed the first one it was supposed to use to exit the runway.
Neither airline involved responded to questions about the incident and the airport deferred all questions to the FAA.
The number of close calls in recent years has created serious concerns for the FAA, NTSB and other safety experts. The NTSB's investigation of a February 2023 close call in Austin highlighted the concerns, but there have been a number of other high-profile near misses. In one case, a Southwest Airlines jet coming in for a landing in Chicago narrowly avoided smashing into a business jet crossing the runway.
LaGuardia is one of just 35 airports across the country equipped with the FAA's best technology to prevent such runway incursions. The ASDS-X system uses a variety of technology to help controllers track planes and vehicles on the ground. At the other 490 U.S. airports with a control tower, air traffic controllers have to rely on more low-tech tools like a pair of binoculars to keep track of aircraft on the ground because the systems are expensive.
Expanding the systems to more airports is something Transportation Secretary Sean Duffy would like to do if Congress signs off on his multi-billion-dollar plan to overhaul the nation's aging air traffic control system.
But it's clear the technology is not perfect because close calls continue happening. The FAA is taking a number of additional steps to try to reduce the number of close calls, and it plans to install an additional warning system at LaGuardia in the future.
But the rate of runway incursions per 1 million takeoffs and landings has remained around 30 for a decade. The rate got as high as 35 in 2017 and 2018. But generally there are fewer than 20 of the most serious kind of incursions where a collision was narrowly avoided or there was a significant potential for a crash, according to the FAA. That number did hit 22 in 2023 but fell to just 7 last year.
To help, there are efforts to develop a system that will warn pilots directly about traffic on a runway instead of alerting the controller and relying on them to relay the warning. That could save precious seconds. But the FAA has not yet certified a system to warn pilots directly that Honeywell International has been developing for years.
The worst accident in aviation history occurred in 1977 on the Spanish island of Tenerife, when a KLM 747 began its takeoff roll while a Pan Am 747 was still on the runway; 583 people died when the planes collided in thick fog.

Orange background

Try Our AI Features

Explore what Daily8 AI can do for you:

Comments

No comments yet...

Related Articles

HBM And Emerging Memory Technologies Enable AI Training And Inference
HBM And Emerging Memory Technologies Enable AI Training And Inference

Forbes

timean hour ago

  • Forbes

HBM And Emerging Memory Technologies Enable AI Training And Inference

AI During congressional hearing in the House of Representatives' Energy & Commerce Committee Subcommittee of Communication and Technology, Ronnie Vasishta, Senior VP of telecom at Nvidia said that mobile networks will be called upon to support a new kind of traffic—AI traffic. This AI traffic includes the delivery of AI services to the edge, or inferencing at the edge. Such growth in AI data could reverse the general trend towards lower growth in traffic on mobile networks. Many AI-enabled applications will require mobile connectivity including autonomous vehicles, smart glasses, generative AI services and many other applications. He said that the transmission of this massive increase in data needs to be resilient, fit for purpose, and secure. Supporting this creation of data from AI will require large amount of memory, particularly very high bandwidth memory, such as HBM. This will result in great demand for memory that supports AI applications. Micron announced that it is now shipping HBM4 memory to key customers, these are for early qualification efforts. The Micron HBM4 provides up to 2.0TB/s bandwidth and 24GB capacity per 12-high die stack. The company says that their HBM4 uses its 1-beta DRAM node, advanced through silicon via technologies, and has a highly capable built-in self-test. See image below. Micron HBM4 Memory HBM memory consisting of stacks of DRAM die with massively parallel interconnects to provide high bandwidth are combined GPU's such as those from Nvidia. This memory close to the processor allows training and inference of various AI models. The current generation of HBM memory used in current GPUs use HBM3e memory. At the 2025 March GTC in San Jose, Jensen Huang said that Micron HBM memory was being used in some of their GPU platforms. The manufacturers of HBM memories are SK Hynix, Samsung and Micron with SK Hynix and Samsung providing the majority of supply and with Micron coming in third. SK hynix was the first to announce HBM memory in 2013, which was adopted as an industry standard by JEDEC that same year. Samsung followed in 2016 and in 2020 Micron said that it would create its own HBM memory. All of these companies expect to be shipping HBM4 memories in volume by sometime in 2026. Numen, a company involved in magnetic random access memory applications, recently talked about how traditional memories used in AI applications, such as DRAM and SRAM have limitations in power, bandwidth and storage density. They said that processing performance has skyrocketed by 60,000X over the past 20 years but DRAM bandwidth has improved only 100X, creating a 'memory wall.' The company says that its AI Memory Engine is a highly configurable memory subsystem IP that enables significant improvements in power efficiency, performance, intelligence, and endurance. This is not only for Numem's MRAM-based architecture, but also third-party MRAMs, RRAM, PCRAM, and Flash Memory. Numem said that it has developed next-generation MRAM supporting die densities up to 1GB which can deliver SRAM-class performance with up to 2.5X higher memory density in embedded applications and 100X lower standby power consumption. The company says that its solutions are foundry-ready and production-capable today. Coughlin Associates and Objective Analysis in their Deep Look at New Memories report predict that AI and other memory-intensive applications, including the use of AI inference in embedded devices such as smart watches, hearing aids and other applications are already using MRAM, RRAM and other emerging memory technologies will decrease the costs and increase production of these memories. These memories technologies are already available from major semiconductor foundries. They scale to smaller lithographic scaling that DRAM and SRAM and because they are non-volatile, no refreshes are needed and so they consume less power. As a result, these memories allow more memory capacity and lower power consumption in space and power constrained environments. MRAM and RRAM are also being built into industrial, enterprise and data center applications. The figure below shows our projections for replacement of traditional memories, SRAM, DRAM, NOR and NAND Flash memory by these emerging memories. NOR and SRAM, in particular, for embedded memories are projected to be replaced by these new memories within the next decade as part of a future $100B memory market. Projected replacement of conventional memories with new memories AI will generate increased demand for memory to support training and inference. It will also increase the demand for data over mobile networks. This will drive demand for HBM memory but also increase demand for new emerging memory technologies.

SpaceX Starlink rivalry grows as next Kuiper deployment nears
SpaceX Starlink rivalry grows as next Kuiper deployment nears

Digital Trends

time2 hours ago

  • Digital Trends

SpaceX Starlink rivalry grows as next Kuiper deployment nears

Amazon is about to send another batch of Project Kuiper internet satellites to orbit as it seeks to take on SpaceX's Starlink service to provide broadband internet to customers around the world. The tech giant has a long way to go before it has any hope of effectively challenging Starlink, but with its second launch set for next week, progress is being made toward its goal. Recommended Videos Project Kuiper is currently targeting Monday, June 16, for the launch of 27 internet satellites aboard a United Launch Alliance (ULA) Atlas V rocket from Cape Canaveral in Florida. The KA-02 mission comes seven weeks after the first Project Kuiper launch, which also deployed 27 internet satellites. Commenting after the inaugural launch, Rajeev Badyal, vice president of Project Kuiper, said: 'We've designed some of the most advanced communications satellites ever built, and every launch is an opportunity to add more capacity and coverage to our network.' SpaceX began deploying its Starlink internet satellites six years ago and now has more than 7,000 of them in low-Earth orbit, bringing broadband connectivity to more than 5 million customers globally. Project Kuiper says its initial constellation will be made up of more than 3,200 satellites, with more than 80 missions needed to reach that goal. To that end, Amazon has put together a busy launch schedule, with six additional satellite deployments planned for ULA's Atlas V rocket, at least 38 on ULA's Vulcan Centaur rocket, and dozens more with Arianespace and Blue Origin. SpaceX's workhorse Falcon 9 rocket may even help out. Amazon is targeting as early as the end of this year for the launch of a high-speed, low-latency satellite-powered internet service, with as few as 1,000 satellites needed for global coverage. Building out the constellation to the targeted 3,200 satellites will help to boost network performance and reliability for paying customers.

Klarna's CEO is now taking your calls — over an AI hotline
Klarna's CEO is now taking your calls — over an AI hotline

The Verge

time2 hours ago

  • The Verge

Klarna's CEO is now taking your calls — over an AI hotline

Klarna CEO Sebastian Siemiatkowski has already used AI to replace himself during earnings reports, and now Klarna is using AI to clone him another way: through an AI-powered phone hotline. The hotline is now open for users to provide feedback to an interactive AI version of Siemiatkowski that's trained on his 'real voice, insights, and experiences,' according to a press release. 'Customers, including consumers and merchants alike, can speak to it about product features, issues and suggestions for improvements,' Klarna says. ''AI Sebastian' can also answer questions about Klarna's vision and mission, and speak about its founding story and journey so far, based on learnings from 'real life Sebastian.'' After the hotline takes a call, a transcript and summary are generated that are 'automatically analyzed by a large language model (LLM), populating an internal live feed and innovation dashboard.' Klarna says its product and engineering teams will then review the 'actionable insights immediately' and assign 'priority tasks.' The company claims that issues raised today could 'translate into tangible product improvements already the following day.' Phone numbers for the hotline are available now in the US, +14246675385, and Sweden, +46852512594. I called the US hotline just to see what the experience was like. After a brief message telling me the call may be recorded, the AI version of Siemiatkowski prompted me to share feedback about using Klarna. No matter what I asked AI Siemiatkowski, even sillier questions, the AI generally tried to push me back to sharing feedback. When I asked if it had talked to Fortnite's AI Darth Vader, for example, here's what it said: That's an interesting question. My focus is entirely on Klarna and gathering feedback to improve our services. I don't have information or conversations with characters from games like Fortnite. I'm here to hear your thoughts on Klarna. Is there anything else about your experience with Klarna that you'd like to share, or any ideas you have for how we could make things even better?

DOWNLOAD THE APP

Get Started Now: Download the App

Ready to dive into the world of global news and events? Download our app today from your preferred app store and start exploring.
app-storeplay-store