Blue Origin successfully launches New Shepard rocket after failed 2022 attempt

Blue Origin’s 24th mission is officially a success. The New Shepard rocket took off as planned this morning and the booster and crew capsule safely separated mid-flight and landed back on this great blue marble we call Earth.

This was an uncrewed mission, but it carried 33 science payloads into low orbit, more than half of them from NASA. The launch allowed for a few minutes of zero gravity in which researchers conducted remote studies on these payloads. For instance, a payload from Honeybee Robotics studied the strength of planetary soils under differing gravity conditions. The manifest also included 38,000 student postcards from the Club for the Future initiative.

To those following this mission, the original launch was scrapped on Monday due to a ground system issue that was, obviously, handled. There were no issues reported regarding today’s flight, though there was a slight holdup of a few minutes added to the countdown.

This mission was basically a do-over of a flight from last year that ended prematurely due to a malfunction of the New Shepard booster’s hydrogen-based rocket engine. This anomaly led to the suspension of Blue Origin launches until an investigation by the Federal Aviation Administration (FAA) was completed.

The FAA’s investigation ended in September, freeing up Blue Origin for more launches once it handled a suite of corrective actions mandated by the agency. This included a redesign of the booster’s engine and nozzle as well as some procedural changes. The company hasn’t announced any official plans for future crewed flights, but recently installed an elevator at the launch tower. This is to make future launches “more accessible to people with disabilities, and more people in general,” launch commentator Erika Wagner said during today’s livestream.

To that end, Blue Origin has begun ramping up promotions to attract customers for crewed flights. You can also apply to add a payload to a future launch.

This article originally appeared on Engadget at https://www.engadget.com/blue-origin-returns-to-form-with-a-successful-rocket-launch-after-being-grounded-for-over-a-year-193948312.html?src=rss

Webb telescope’s new Uranus image looks like a portal to another dimension

The James Webb Space Telescope (JWST) has a treat to celebrate the upcoming second anniversary of its launch. NASA and the European Space Agency (ESA), which operate the craft alongside the Canadian Space Agency (CSA), shared a recent image of the icy planet Uranus. The picture, resembling a glowing blue marble rippling into a black ocean, was funneled through the telescope’s infrared filters to capture wavelengths future space travelers wouldn’t see with the naked eye.

Compared with the generic-looking images of Uranus taken by Voyager 2 in the 1980s, the Webb telescope paints a more vivid picture. Capturing light in the infrared spectrum, the craft’s sensors reveal a “strange and dynamic ice world filled with exciting, atmospheric features,” as the team operating the telescope described it.

The JWST’s image showcases the planet’s rings surrounding the planet, including “the elusive Zeta ring,” Uranus’ faint and scattered innermost one. You can also catch its north polar cloud cap, the white blob near the center.

An image of Uranus taken with the James Webb Space Telescope. It appears as a glowing blue ball with rings surrounding it. Its scattered moons are labeled amid the black space behind it.
NASA / ESA / CSA

The image also captures 14 of Uranus’ 27 moons, labeled in the photo above. Among the (mostly Shakespearean-named) orbiting bodies pictured are Oberon, Titania, Umbriel, Juliet, Perdita, Rosalind, Puck, Belinda, Desdemona, Cressida, Ariel, Miranda, Bianca and Portia.

The JWST’s photo uses four NIRCam filters, revealing detail in the near-infrared spectrum. These include F140M (blue), F210M (cyan), F300M (yellow) and F460M (orange). An image NASA shared earlier this year showed Uranus in only two filters (blue and orange), resulting in a more primitive-looking view of the icy giant.

Speaking of ice, Uranus has loads of it. The planet rotates on its side at about 98 degrees, plunging the opposite side of the planet into extreme cold and darkness for a quarter of a Uranian year. Oh, and since Uranian years last around 84 Earth years, that means, by our calendar, the planet’s dark side enjoys a blustery 21-year winter.

Image of Uranus taken with the James Webb Space Telescope. The planet appears as a blue marble-like ball surrounded by light-colored rings of varying clarity and intensity. Moons and distant stars and galaxies appear in the black space surrounding the planet.
NASA / ESA / CSA

Astronomers believe the Webb telescope’s images will help them better understand Uranus, especially its Zeta ring, for future missions. They also view the pictures as a proxy for learning about the nearly 2,000 documented exoplanets in other solar systems that share traits with our ringed and icy neighbor.

This article originally appeared on Engadget at https://www.engadget.com/webb-telescopes-new-uranus-image-looks-like-a-portal-to-another-dimension-181035887.html?src=rss

These tomatoes were lost on the International Space Station for almost a year

In an interview this fall following his return to Earth from the International Space Station, NASA astronaut Frank Rubio shared a little mission anecdote that had us gripped: after he’d harvested one of the first tomatoes grown in space and bagged it up for a presentation, the bag and its contents went missing. With no trace of the fruit, the other astronauts jokingly accused Rubio of eating it. Then, eight months later at the beginning of December, the lost tomato reappeared. A photo shared by NASA now shows there were actually two tomatoes in the rogue sample — and, all things considered, they don’t look half bad.

While a tomato left to rot on Earth isn’t a pleasant thing to come across, Rubio’s tomatoes just look a bit dried out. “Other than some discoloration, it had no visible microbial or fungal growth,” NASA wrote in a blog post.

NASA has for years been experimenting with ways to grow food on the ISS and studying how the space environment affects plant growth. The red dwarf tomatoes were grown as part of a program called the eXposed Root On-Orbit Test System, or XROOTS, which uses a combination of hydroponic and aeroponic techniques instead of soil. Rubio, who was on the ISS for a record-breaking 371 days before his return in September 2023, harvested a batch of the tomatoes in March to be sent back to Earth and examined for the VEG-05 study.

As for the sample Rubio hung onto, which he intended to show to schoolkids in an event a crewmember had planned, the astronaut said the tomatoes simply disappeared. “I was pretty confident that I Velcroed it where I was supposed to Velcro it, and then I came back and it was gone,” he said. Rubio said he spent “eight to 20 hours” looking for it, to no avail. They were eventually found behind the Earth-facing hatch of the ISS's Harmony module, a NASA spokesperson told Engadget. 

Expedition 65 astronaut Megan McArthur inside the Harmony module on the ISS in 2021
NASA

The Harmony module, pictured above in 2021 with astronaut Megan McArthur inside, acts like a crossroads, port and “utility hub” on the orbiting station. Its hatch provides access to the pressurized mating adapter, where spacecraft carrying cargo or crews, like SpaceX's Dragon, dock to the ISS. The months-old tomatoes were discarded after being discovered. 

Update, December 20 2023, 11:28AM ET: This story has been updated to include new information from NASA on where the missing tomatoes were found. 

This article originally appeared on Engadget at https://www.engadget.com/these-tomatoes-were-lost-on-the-international-space-station-for-almost-a-year-182601610.html?src=rss

Amazon boosts its satellite internet network with the help of space lasers

Space lasers, once a mere futuristic joke, have become a real tool in building technology up there and making improvements for all of us down here. There's been NASA's use of space lasers to study plankton, plans to blast space junk and, now, a satellite network courtesy of Amazon. The company has announced that its Project Kuiper has built up its optical inter-satellite links (OISLs) capabilities to create a substantial mesh network of high-speed laser cross-links. This technology could result in faster data transmission to even the most remote places back on earth. 

In October, Amazon launched two prototype satellites and reported successful tests one month later, with the pair dispatching and retrieving data at speeds of up to 100 gigabits per second. "These tests demonstrated our ability to establish a single bi-directional link between two satellites, and initial data indicates that our design will be able to maintain cross-links between multiple satellites at once—the critical feature of a next-generation mesh network in space," the company stated. 

To successfully use OISLs, laser links had to maintain contact at a distance up to 1,616 miles while also contending with spacecrafts moving at a speed of 15,534 miles per hour. Plus, Amazon had to minimize light spreading in order to maintain the signal and account for any additional dynamics of all these moving pieces — something it says has been successfully done.

Amazon also claims the mesh network moves data about 30 percent faster than terrestrial fiber optic cables can. "Amazon's optical mesh network will provide multiple paths to route data through space, creating resiliency and redundancy for customers who need to securely transport information around the world," Ricky Freeman, vice president of Kuiper Government Solutions, explained in a statement. "This is especially important for those looking to avoid communications architectures that can be intercepted or jammed, and we look to forward to making these capabilities available to public sector customers looking to move and land data from remote locations to their desired destination." Basically, anyone from a cruise ship passenger to a multi-day hiker should be able to get a connection if this is successful. 

Project Kuiper started in 2019 but has seen a real boost in the last few months. With these successful tests completed, Amazon states that Project Kuiper is starting satellite production, with "full-scale deployment" beginning in the first half of 2024. It also predicts that early customer pilots will begin in the second half of the year. Notably, Amazon signed a deal with SpaceX to launch more Project Kuiper satellites at a faster rate. 

This article originally appeared on Engadget at https://www.engadget.com/amazon-boosts-its-satellite-internet-network-with-the-help-of-space-lasers-123535946.html?src=rss

Researchers fuse lab-grown human brain tissue with electronics

In a story ripped from the opening scenes of a sci-fi horror movie, scientists have bridged a critical gap between the biological and electronic. The study, published in Nature Electronics (summarized in Nature), details a “hybrid biocomputer” combining lab-grown human brain tissue with conventional circuits and AI. Dubbed Brainoware, the system learned to identify voices with 78 percent accuracy. It could one day lead to silicon microchips fused with neurons.

Brainoware combines brain organoids — stem-cell-derived clusters of human cells morphed into neuron-filled “mini-brains” — with conventional electronic circuits. To make it, researchers placed “a single organoid onto a plate containing thousands of electrodes to connect the brain to electric circuits.” The circuits, speaking to the brain organoid, “translate the information they want to input into a pattern of electric pulses.”

The brain tissue then learns and communicates with the technology. A sensor in the electronic array detects the mini-brain’s response, which a trained machine-learning algorithm decodes. In other words, with the help of AI, the neurons and electronics merge into a single (extremely basic, for now) problem-solving biomachine.

The researchers taught the computer-brain system to recognize human voices. They trained Brainoware on 240 recordings of eight people speaking, “translating the audio into electric to deliver to the organoid.” The organic part reacted differently to each voice while generating a pattern of neural activity AI learned to understand. Brainoware learned to identify the voices with 78 percent accuracy.

PHILADELPHIA, PA - AUGUST 15: Fadi Jacob, a visiting graduate student from Johns Hopkins University, dissects a a glioblastoma brain tumor at the University of Pennsylvania Clinical Research Building in Philadelphia, Pennsylvania on August 15, 2018.  The tumor, which came straight from post-op will be dissected into hundreds of small pieces that will be used to grow tumor organdies. (Photo by Jessica Kourkounis for The Washington Post via Getty Images)
Human brain organoids
The Washington Post via Getty Images

The team views the work as more proof of concept than something with near-term practical use. Although previous studies showed two-dimensional neuron cell cultures could do similar things, this is the first trial run using a trained three-dimensional lump of human brain cells. It could point to a future of biological computing, where the “speed and efficiency of human brains” spark a superpowered AI. (What could go wrong?)

Arti Ahluwalia, a biomedical engineer at Italy’s University of Pisa, sees the technology shedding more light on the human brain. Since brain organoids can duplicate the nervous system’s control center in ways simple cell cultures can’t, the researcher views Brainoware (and the further advances it could spawn) as helping model and study neurological disorders like Alzheimer’s. “That’s where the promise is; using these to one day hopefully replace animal models of the brain,” Ahluwalia told Nature.

Challenges for the bizarre proto-cyborg tech include keeping the organoids alive, especially when moving to the more complex areas where scientists eventually want to deploy them. The brain cells must grow in an incubator, which could become more challenging with bigger organoids. The next steps include working to learn how brain organoids adapt to more complex tasks and engineering them for greater stability and reliability.

This article originally appeared on Engadget at https://www.engadget.com/researchers-fuse-lab-grown-human-brain-tissue-with-electronics-175507932.html?src=rss

Researchers made VR goggles for mice to study how their brains respond to swooping predators

Believe it or not, scientists have been using virtual reality setups to study brain activity in lab mice for years. In the past, this has been done by surrounding the mice with flat displays — a tactic that has obvious limitations for simulating a realistic environment. Now, in an attempt to create a more immersive experience, a team at Northwestern University actually developed tiny VR goggles that fit over a mouse’s face… and most of its body. This has allowed them to simulate overhead threats for the first time, and map the mice’s brain activity all the while.

The system, dubbed Miniature Rodent Stereo Illumination VR (or iMRSIV), isn’t strapped onto the mouse’s head like a VR headset for humans. Instead, the goggles are positioned at the front of a treadmill, surrounding the mouse’s entire field of view as it runs in place. “We designed and built a custom holder for the goggles,” said John Issa, the study’s co-first author. “The whole optical display — the screens and the lenses — go all the way around the mouse.”

What a mouse sees inside the VR goggles
Dom Pinke/ Northwestern University

In their tests, the researchers say the mice appeared to take to the new VR environment more quickly than they did with the past setups. To recreate the presence of overhead threats, like birds swooping in for a meal, the team projected expanding dark spots at the tops of the displays. The way they react to threats like this “is not a learned behavior; it’s an imprinted behavior,” said co-first author Dom Pinke. “It’s wired inside the mouse’s brain.”

With this method, the researchers were able to record both the mice’s outward physical responses, like freezing in place or speeding up, and their neural activity. In the future, they may flip the scenario and let the mice act as predators, to see what goes on as they hunt insects. A paper on the technique was published in the journal Neuron on Friday. 

This article originally appeared on Engadget at https://www.engadget.com/researchers-made-vr-goggles-for-mice-to-study-how-their-brains-respond-to-swooping-predators-215927095.html?src=rss

Researchers made VR goggles for mice to study how their brains respond to swooping predators

Believe it or not, scientists have been using virtual reality setups to study brain activity in lab mice for years. In the past, this has been done by surrounding the mice with flat displays — a tactic that has obvious limitations for simulating a realistic environment. Now, in an attempt to create a more immersive experience, a team at Northwestern University actually developed tiny VR goggles that fit over a mouse’s face… and most of its body. This has allowed them to simulate overhead threats for the first time, and map the mice’s brain activity all the while.

The system, dubbed Miniature Rodent Stereo Illumination VR (or iMRSIV), isn’t strapped onto the mouse’s head like a VR headset for humans. Instead, the goggles are positioned at the front of a treadmill, surrounding the mouse’s entire field of view as it runs in place. “We designed and built a custom holder for the goggles,” said John Issa, the study’s co-first author. “The whole optical display — the screens and the lenses — go all the way around the mouse.”

What a mouse sees inside the VR goggles
Dom Pinke/ Northwestern University

In their tests, the researchers say the mice appeared to take to the new VR environment more quickly than they did with the past setups. To recreate the presence of overhead threats, like birds swooping in for a meal, the team projected expanding dark spots at the tops of the displays. The way they react to threats like this “is not a learned behavior; it’s an imprinted behavior,” said co-first author Dom Pinke. “It’s wired inside the mouse’s brain.”

With this method, the researchers were able to record both the mice’s outward physical responses, like freezing in place or speeding up, and their neural activity. In the future, they may flip the scenario and let the mice act as predators, to see what goes on as they hunt insects. A paper on the technique was published in the journal Neuron on Friday. 

This article originally appeared on Engadget at https://www.engadget.com/researchers-made-vr-goggles-for-mice-to-study-how-their-brains-respond-to-swooping-predators-215927095.html?src=rss

Researchers develop under-the-skin implant to treat Type 1 diabetes

Scientists have developed a new implantable device that has the potential to change the way Type 1 diabetics receive insulin. The thread-like implant, or SHEATH (Subcutaneous Host-Enabled Alginate THread), is installed in a two-step process that ultimately leads to the deployment of “islet devices,” which are derived from the cells that produce insulin in our bodies naturally.

First, the scientists figured out a way to insert nylon catheters under the skin, where they remain for up to six weeks. After insertion, blood vessels form around the catheters which structurally support the islet devices that are placed in the space when the catheter gets removed. The newly implanted 10-centimeter-long islet devices secrete insulin via islet cells that form around it, while also receiving nutrients and oxygen from blood vessels to stay alive.

The implantation technique was designed and tested by researchers at Cornell and the University of Alberta. Cornell’s Minglin Ma, a Professor of Biological and Environmental Engineering, created the first implantable polymer in 2017 dubbed TRAFFIC (Thread-Reinforced Alginate Fiber For Islets enCapsulation), which was designed to sit in a patient’s abdomen. In 2021, Ma’s team developed an even more robust implantable device that proved it could control blood sugar levels in mice for six months at a time.

The current problem with SHEATH is its long-term application in patients. “It’s very difficult to keep these islets functional for a long time inside of the body… because the device blocks the blood vessels, but the native islet cells in the body are known to be in direct contact with vessels that provide nutrients and oxygen,” Ma said. Because the islet devices eventually need to be removed, the researchers are still working on ways to maximize the exchange of nutrients and oxygen in large-animal models — and eventually patients. But the implant could one day replace the current standard treatment for Type 1 diabetes, which requires either daily injections or insulin pumps.

This article originally appeared on Engadget at https://www.engadget.com/researchers-develop-under-the-skin-implant-to-treat-type-1-diabetes-191005726.html?src=rss

Looking back at 25 years of the ISS

Wednesday marks the 25th anniversary of the International Space Station’s (ISS) physical assembly in orbit. On December 6, 1998, the crew aboard the space shuttle Endeavor attached the US-built Unity node to the Russian-built Zarya module, kicking off the modular construction of the ISS. A quarter century later, we look back at the milestones and breakthroughs from one of humanity’s most impressive marvels of engineering and international cooperation.

The ISS, which orbits the Earth 16 times every 24 hours at a speed of five miles per second, has been inhabited by researchers for over 23 years. It’s the product of five space agencies from 15 countries. NASA, Roscosmos (Russia’s national space agency), ESA (European Space Agency), JAXA (Japan Aerospace Exploration Agency) and CSA (Canadian Space Agency) have contributed to the station’s assembly and operation.

From ink to orbit

Its official journey began in the early 1990s when the United States’ Freedom (ordered by President Ronald Reagan in 1984) and Russia’s Mir-2 space station projects were in danger of (literally) never getting off the ground. Freedom was in jeopardy primarily due to a lack of Congressional funding amid rising costs, while Mir-2 was on the brink partially because of financial hardships following the collapse of the Soviet Union.

On September 2, 1993, the two nations, each needing an international ally to forge ahead, signed an agreement to combine their programs and collaborate on a joint mission that would have seemed wildly implausible a few years earlier. US Vice President Al Gore and Russian Prime Minister Viktor Chernomyrdin inked the pact, marking the formal conception of the cosmic laboratory we know today as the ISS.

Russian Prime Minister Viktor Chernomyrdin (R) and U.S. Vice President Al Gore appear at a press conference, 16 December 1993. The U.S. and Russia signed a series of space and investment agreements, including one making Russia a partner in the international space station project. Vice President also criticized nationalist leader Vladimir Zhirinovsky, saying
US Vice President Al Gore (left) and Russian Prime Minister Viktor Chernomyrdin in 1993
VITALY ARMAND via Getty Images

The following years included a design overhaul to fold Russian technology into America’s existing Freedom plans, a milestone 1995 docking of NASA’s Atlantis to Russia’s Mir station (epitomizing the fruit of the once-far-fetched collaboration), the addition of funding and cooperation from Europe, Canada and Japan in 1996 and Russia’s launch of Zarya a month before the ISS assembly began. That all led to the day 25 years ago when the two nations’ space tech linked together, sounding the death knell for the Cold War-era space race.

The first crewed mission began on November 2, 2000, when NASA astronaut Bill Shepherd and cosmonauts Yuri Gidzenko and Sergei Krikalev stepped onboard. The inaugural crew spent four months in space, laying the groundwork for subsequent crews. (The record for the most time living and working in space was set by Peggy Whitson, who celebrated 665 days aboard the ISS in 2017.)

ISS inaugural crew of Yuri P. Gidzenko (left) William M. Shepherd (center), and Sergei K. Krikalev.
NASA

The US Lab Module linked to the station in February 2001, expanding the station’s onboard living space by 41 percent. Four years later, Congress named the US portion a national laboratory. Far more than a symbolic gesture (although it was also that), the designation opened the door to funding and research from a much more comprehensive array of institutions, including universities, other government agencies and private businesses. In 2008, laboratories from Europe and Japan joined the ISS.

The ISS’s construction and expansion from 1998 to 2010 amassed around 900,000 pounds of modules. The station contains about $100 billion worth of gear spinning around the globe.

Research and breakthroughs

Photo taken aboard the ISS during its initial assembly. A module sits upright at center with the Earth behind it.
NASA

During the ISS’s more than 100,000 orbits of the Earth, it has ushered breakthroughs in areas ranging from disease research to bodily changes from microgravity.

Studying how proteins, cells and biological processes behave in microgravity has boosted research in Alzheimer’s, Parkinson’s, heart disease and asthma. Many of these studies wouldn’t have been possible on Earth. Meanwhile, protein crystal growth experiments have sparked advances in developing treatments for conditions including cancer, gum disease and Duchenne Muscular Dystrophy.

ISS researchers made surprising discoveries about “cool flames,” which can burn at extremely low temperatures. Nearly impossible to study outside of microgravity, the astronauts’ research has challenged our previous understanding of combustion. It may open new frontiers with internal combustion engines (ICE), allowing them to run cleaner and more efficiently.

Studies aboard the space station have contributed significantly to our knowledge of human muscle atrophy and bone loss. (ISS astronauts typically work out at least two hours daily to prevent these conditions.) Studying how prolonged time in microgravity affects muscle deterioration and recovery also applies to Earthbound patients stuck in bed for extended periods. In addition, the research can help us learn more about conditions like osteoporosis, leading to improved preventative measures and treatments. It has also helped scientists better understand broader biological changes in microgravity, which could pay dividends if or when humans colonize Mars.

Water purification systems designed to sustain astronauts over long periods have also borne fruit on Earth. ISS astronauts recycle 98 percent of their pee and sweat using highly efficient and compact systems. This has led to the technology’s use in agriculture, disaster relief and aid provision for less developed areas.

ISS astronauts studied the Bose-Einstein Condensate (BEC), a “fifth state of matter” that deviates significantly from known states like solids, liquids, gases and plasmas. In 2018, the ISS’s Cold Atom Lab produced BEC in orbit for the first time. Space’s colder temperatures and lack of gravity allow for longer observation times, helping researchers learn more about the behaviors of atoms and BECs. Not only is this crucial to quantum physics studies, it could aid in developing more advanced quantum technologies down the road.

For more detail on the ISS’s breakthroughs, NASA has a dedicated writeup from 2020.

Decommissioning

Expanded cross-section of the ISS, showing its various parts and labels.
NASA

The ISS is currently scheduled for decommissioning in January 2031. (Russia currently plans to leave in 2028.) Its late 90s infrastructure is aging quickly, and the space station would grow increasingly and prohibitively expensive to maintain over the long haul. Government and commercial orbital labs will likely pick up the slack in the following years.

When its time comes, the ISS will undergo a controlled deorbit. As for what that might involve, Kirk Shireman, deputy manager of NASA’s space station program, broached the subject with Space.com in 2011. “We’ve done a lot of studies,” he said. “We have found an orbit and a change in velocity that we believe is achievable, and it creates a debris footprint that’s all in water in an unpopulated area.”

As Engadget’s Andrew Tarantola wrote about the ISS’s pending demise:

Beginning about a year before the planned decommissioning date, NASA will allow the ISS to begin degrading from its normal 240-mile high orbit and send up an uncrewed space vehicle (USV) to dock with the station and help propel it back Earthward. The ultimate crew from the ISS will evacuate just before the station hits an altitude of 115 miles, at which point the attached USV will fire its rockets in a series of deorbital burns to set the station into a capture trajectory over the Pacific Ocean.

NASA plans to guide any remaining bits into a remote area of the South Pacific Ocean. “We’ve been working on plans and update the plans periodically,” Shireman said. “We don’t want to ever be in a position where we couldn’t safely deorbit the station. It’s been a part of the program from the very beginning.”

NASA 25th-anniversary event

NASA held a live-streamed event on Wednesday to mark the quarter-century anniversary of the Zarya and Unity modules linking up. All seven STS-88 Space Shuttle Mission crew members joined NASA Associate Administrator Bob Cabana (mission commander) and ISS Program Manager Joel Montalbano to discuss the milestone.

You can watch it here:

This article originally appeared on Engadget at https://www.engadget.com/looking-back-at-25-years-of-the-iss-173155049.html?src=rss

NASA and IBM are building an AI for weather and climate applications

NASA and IBM have teamed up to build an AI foundation model for weather and climate applications. They’re combining their respective knowledge and skills in the Earth science and AI fields, respectively, for the model, which they say should offer “significant advantages over existing technology.”

Current AI models such as GraphCast and Fourcastnet are already generating weather forecasts more quickly than traditional meteorological models. However, IBM notes those are AI emulators rather than foundation models. As the name suggests, foundation models are the base technologies that power generative AI applications. AI emulators can make weather predictions based on sets of training data, but they don’t have applications beyond that. Nor can they encode the physics at the core of weather forecasting, IBM says.

NASA and IBM have several goals for their foundational model. Compared with current models, they hope for it to have expanded accessibility, faster inference times and greater diversity of data. Another key aim is to improve forecasting accuracy for other climate applications. The expected capabilities of the model include predicting meteorological phenomena, inferring high-res information based on low-res data and "identifying conditions conducive to everything from airplane turbulence to wildfires."

This follows another foundational model that NASA and IBM deployed in May. It harnesses data from NASA satellites for geospatial intelligence, and it's the largest geospatial model on open-source AI platform Hugging Face, according to IBM. So far, this model has been used to track and visualize tree planting and growing activities in water tower areas (forest landscapes that retain water) in Kenya. The aim is to plant more trees and tackle water scarcity issues. The model is also being used to analyze urban heat islands in the United Arab Emirates.

This article originally appeared on Engadget at https://www.engadget.com/nasa-and-ibm-are-building-an-ai-for-weather-and-climate-applications-050141545.html?src=rss