Scripps Research scientists sent stem-cell-derived brain organoids to the ISS to study the effects of microgravity on brain cells, finding that the organoids matured faster and showed signs of specialization compared to Earth-grown controls. The findings have been published in the journal Stem Cells Translational Medicine. Phys.Org reports: To examine how the space environment impacts cellular functions, the team compared the cells' RNA expression patterns -- a measure of gene activity -- to identical "ground control" organoids that had remained on Earth. Surprisingly, they found that the organoids grown in microgravity had higher levels of genes associated with maturity and lower levels of genes associated with proliferation compared to the ground controls, meaning that the cells exposed to microgravity developed faster and replicated less than those on Earth. "We discovered that in both types of organoids, the gene expression profile was characteristic of an older stage of development than the ones that were on the ground," [says co-senior author Jeanne Loring, Ph.D., professor emeritus in the Department of Molecular Medicine and founding director of the Center for Regenerative Medicine at Scripps Research]. "In microgravity, they developed faster, but it's really important to know these were not adult neurons, so this doesn't tell us anything about aging." The team also noted that contrary to their hypothesis, there was less inflammation and lower expression of stress-related genes in organoids grown in microgravity, but more research is needed to determine why. Loring speculates that microgravity conditions may more closely mirror the conditions experienced by cells within the brain compared to organoids grown under conventional lab conditions and in the presence of gravity. "The characteristics of microgravity are probably also at work in people's brains, because there's no convection in microgravity -- in other words, things don't move," says Loring. "I think that in space, these organoids are more like the brain because they're not getting flushed with a whole bunch of culture medium or oxygen. They're very independent; they form something like a brainlet, a microcosm of the brain." "The next thing we plan to do is to study the part of the brain that's most affected by Alzheimer's disease," says Loring. "We also want to know whether there are differences in the way neurons connect with each other in space. With these kinds of studies, you can't rely on earlier work to predict what the result would be because there is no earlier work. We're on the ground floor, so to speak; in the sky, but on the ground floor."

Read more of this story at Slashdot.

SpaceX has filed a petition to incorporate its Starbase facility in South Texas as a new city, aiming to streamline infrastructure development and support the growing workforce needed for Starship production and testing. Space.com reports: "To continue growing the workforce necessary to rapidly develop and manufacture Starship, we need the ability to grow Starbase as a community," SpaceX said in the petition, which was shared in a post on X (formally Twitter). "That is why we are requesting that Cameron County call an election to enable the incorporation of Starbase as the newest city in the Rio Grande Valley." The petition was addressed to Cameron County Judge Eddie Trevino Jr., the county's top elected official. The next step will be for officials to review the petition to determine if it complies with statutory requirements. Then, an election would be held to incorporate Starbase. [...] With Starship expected to "fundamentally alter humanity's access to space," SpaceX aims to make the area of the Starbase launch site the "Gateway to Mars," the company wrote in the petition. [...] "Incorporating Starbase will streamline the processes required to build the amenities necessary to make the area a world class place to live -- for hundreds already calling it home, as well as for prospective workers eager to help build humanity's future in space," SpaceX officials said in the petition.

Read more of this story at Slashdot.

An anonymous reader quotes a report from The Guardian: The UK's first driverless bus service, originally heralded as a breakthrough of global significance, is being withdrawn from service because too few passengers used it. The autonomous buses, operated by Stagecoach, have been running between Fife and Edinburgh along a 14-mile route over the Forth road bridge since May 2023 to relieve the heavy congestion which can bring traffic to a standstill. The CAVForth service, a collaboration between Fusion Processing, the coach-building company Alexander Dennis, Napier University in Edinburgh and the Bristol Robotics Lab -- a joint venture between the University of Bristol and the University of the West of England -- was touted as the most ambitious and complex in the world. Built at an estimated cost of more than 6 million pounds, partly funded by the UK government, the fleet of five single-decker buses had the capacity to carry 10,000 passengers a week but needed two crew on board for safety reasons. Stagecoach said in a statement: "We are proud to have achieved a world first with our CAVForth autonomous bus service, demonstrating the potential for self-driving technology on a real-world registered timetable in East Scotland. Although passenger adoption did not meet expectations, the trial has significantly advanced the understanding of the operational and regulatory requirements for autonomous services, delivering what was expected from this demonstrator project. The partners remain committed to exploring new opportunities for self-driving technology in other areas across the UK, ensuring that this exciting innovation can play a transformative role in future transport networks."

Read more of this story at Slashdot.

The Register's Simon Sharwood reports: Tech distribution behemoth Ingram Micro will stop doing business with Broadcom and its VMware range in many territories next year. In a statement sent to The Register, an Ingram spokesperson told us: "We were unable to reach an agreement with Broadcom that would help our customers deliver the best technology outcomes now and in the future while providing an appropriate shareholder return." That decision means that from "early January 2025, Ingram Micro will no longer be doing business with Broadcom and have limited engagement with VMware in select regions." The distie told us this change is not material to its business, and customers and other vendors have been informed. "For us and the more than 1,500 vendors and 161,000 customers we work with, the future of business is focused on transforming relationships, not just transacting sales," the spokesperson explained. Ingram's decision is a challenge to Broadcom, which after acquiring VMware decided to emphasize services delivered through the channel for many customers. However, The Register has heard from VMware users who felt Ingram struggled to handle the increased responsibilities it assumed under this arrangement. We've been told of slow responses, and that Ingram struggled to replicate the expertise that pre-acquisition VMware's support teams delivered. Banter on social media suggests similar experiences were not uncommon. Ingram's decision means VMware's channel has more change to digest, after a year in which Broadcom cancelled its partner program and created a new one that excluded some existing partners. Some of those partners ran small VMware-powered clouds, and faced being unable to secure licenses â" meaning their customers would have faced unwelcome disruption. Broadcom hastily created a scheme under which small resellers outside its cloud partner program could acquire licenses from bigger players. Another change to Broadcom's plans saw it cordon off 2,000 VMware customers to work with directly, rendering them off limits to its channel. It then diluted that decision by deciding it will work direct with only 500 VMware users. Resellers that don't have relationships with distributors other than Ingram will now need to make friends -- fast.

Read more of this story at Slashdot.

Spain's leftwing government has introduced a bill requiring digital platforms and social media influencers with large followings to publish corrections to false or harmful information. The law intends to "[make] life more difficult for those who dedicate themselves to lies and spreading fake news every day," said justice minister Felix Bolanos. The Guardian reports: The draft law replaces legislation from 1984 and targets internet users who have more than 100,000 followers on a single platform or 200,000 across several, the justice ministry said in a statement. These outlets and the platforms that host them must have a mechanism to facilitate citizens' right to ask that false or inaccurate information that harms them be corrected publicly, the ministry said. The correction request will no longer have to be addressed to the outlet's director because confirming their identity is difficult for many "pseudo media," justice minister Felix Bolanos told a press conference.

Read more of this story at Slashdot.

The European Commission has launched formal proceedings against TikTok over concerns about its failure to limit election interference, particularly in last month's Romanian presidential vote. Reuters reports: The Commission said it will request information and look into TikTok's policy on political advertisements and paid-for political content as well as TikTok's systems to generate recommendations and the risks of them being manipulated. The opening of formal proceedings empowers the Commission to take further enforcement steps and to accept commitments made by TikTok. There is no specific deadline to complete proceedings.

Read more of this story at Slashdot.

An anonymous reader quotes a report from The Register: China's Electronics Video Industry Association last week signed off on a standard for a universal remote control -- a gadget Beijing thinks locals need because they're struggling with multiple remotes, but which is also a little more significant in other ways. The standard requires remote controls to allow voice control, and to use one of three means of wireless comms: Bluetooth, infrared, and Star Flash -- more on that later. It has been hailed as a boon for consumers who apparently struggle to find the right remote control to use as they navigate between televisions and set-top boxes. This standard reportedly detects which device a user wants to control, makes the connection, and eases the chore of directing a stream from a set-top box to a display. Device-makers have been told that televisions and set-top boxes must support the standard, and they've quickly complied: local media report that Chinese consumer electronics outfit Konka has already delivered the first Smart TV capable of handling the universal remote. Building a standard ecosystem for universal remotes has obvious benefits for consumers, who should be able to use one unit across multiple devices and won't be tied to proprietary tech. But this move has other benefits for Beijing, thanks to its requirement to use China's home-grown Bluetooth alternative, Star Flash. Star Flash is one of the projects run by the SparkLink Alliance -- a group that lists hundreds of Chinese developers and manufacturers as members. Huawei contributes tech to the group. Chinese IoT hardware vendor Qogrisys has described it as an upgrade to both Bluetooth and Wi-Fi that incorporates ideas used in 5G networks, is capable of handling multiple simultaneous device connections, sips power sparingly so battery-powered devices go longer between recharges, and can stream lossless stereo audio. Chinese consumer electronic and automotive brands are already keen to use Star Flash, and the Alliance is promoting its use in industrial settings too. China will promote use of universal remotes in 2025 -- meaning the protocol may soon appear in millions of domestic devices, giving manufacturers scale to justify further investment.

Read more of this story at Slashdot.

A San Francisco jury convicted tech entrepreneur Nima Momeni of second-degree murder for the April 2023 stabbing death of Cash App's founder Bob Lee. He faces 15 years to life in prison. The BBC reports: Momeni was found not guilty of the more serious charge of first-degree murder, which denotes a pre-meditated killing. [...] The six-week trial featured dramatic testimony, and details of Mr Lee's drug-fueled final night. According to prosecutors, Momeni stabbed Mr Lee with a kitchen paring knife because he was upset that he had introduced his sister, Khazar Momeni, to a man who gave her GHB, a so-called date rape drug. Like the prosecution, Nima Momeni's defense team said he had been partying with his sister and Mr Lee on the night of his murder. But they said Momeni had been acting in self-defense. Mr Lee, Momeni said, had lunged at him with a knife over what Momeni described as a "bad joke" at the expense of Mr Lee's family, according to CBS News, the BBC's US partner. Prosecutors pushed back on this account, asking why Momeni did not report the incident to the police or tell anyone that Mr Lee had allegedly attacked him. Autopsy reports indicated that Mr Lee was under the influence of alcohol, ketamine and cocaine at the time of his death. Defense attorneys argued that a pattern of drug use had made Mr Lee aggressive. "We are victims of drug abuse," Momeni's mother, Mahnaz Tayarani, told reporters outside the courtroom on Tuesday. "I know my son... This is not a fair trial." Ms Tayarani said her son would appeal against the conviction.

Read more of this story at Slashdot.

Japanese automakers Honda and Nissan are reportedly in merger talks to form a holding company, potentially integrating Mitsubishi Motors to compete with industry giants like Toyota and Volkswagen. CNBC reports: The combined Nissan-Honda-Mitsubishi enterprise would equate to more than 8 million vehicle sales annually, according to Nikkei. That would place the company among the world's largest automakers, but still below fellow Japanese automaker Toyota Motor, at 11.2 million in 2023, as well as German automaker Volkswagen, which last year reported sales of 9.2 million vehicles. The merger report follows the two Japanese automakers entering into a strategic partnership earlier this year on shared automotive components and software. Such a tie-up would be the largest automotive industry merger since Fiat Chrysler joined with France-based PSA Groupe to form Stellantis in January 2021. Honda and Nissan said in similar statements: "The reported content was not released by our company," Honda said. "As announced in March of this year, Honda and Nissan are exploring various possibilities for future collaboration, leveraging each other's strengths. We will inform our stakeholders of any updates at an appropriate time."

Read more of this story at Slashdot.

An anonymous reader quotes a report from Ars Technica: Return-to-office (RTO) mandates have caused companies to lose some of their best workers, a study tracking over 3 million workers at 54 "high-tech and financial" firms at the S&P 500 index has found. These companies also have greater challenges finding new talent, the report concluded. The paper, Return-to-Office Mandates and Brain Drain [PDF], comes from researchers from the University of Pittsburgh, as well as Baylor University, The Chinese University of Hong Kong, and Cheung Kong Graduate School of Business. The study, which was published in November, spotted this month by human resources (HR) publication HR Dive, and cites Ars Technica reporting, was conducted by collecting information on RTO announcements and sourcing data from LinkedIn. The researchers said they only examined companies with data available for at least two quarters before and after they issued RTO mandates. The researchers explained: "To collect employee turnover data, we follow prior literature ... and obtain the employment history information of over 3 million employees of the 54 RTO firms from Revelio Labs, a leading data provider that extracts information from employee LinkedIn profiles. We manually identify employees who left a firm during each period, then calculate the firm's turnover rate by dividing the number of departing employees by the total employee headcount at the beginning of the period. We also obtain information about employees' gender, seniority, and the number of skills listed on their individual LinkedIn profiles, which serves as a proxy for employees' skill level." There are limits to the study, however. The researchers noted that the study "cannot draw causal inferences based on our setting." Further, smaller firms and firms outside of the high-tech and financial industries may show different results. Although not mentioned in the report, relying on data from a social media platform could also yield inaccuracies, and the number of skills listed on a LinkedIn profile may not accurately depict a worker's skill level. [...] The researchers concluded that the average turnover rates for firms increased by 14 percent after issuing return-to-office policies. "We expect the effect of RTO mandates on employee turnover to be even higher for other firms" the paper says.

Read more of this story at Slashdot.

An anonymous reader quotes a report from the New York Times: TikTokasked the Supreme Court on Monday to temporarily block a law that would effectively ban it in the United States in a matter of weeks. Saying that the law violates both its First Amendment rights and those of its 170 million American users, TikTok, which is controlled by a Chinese parent company, urged the justices to maintain the status quo while they decide whether to hear an appeal. "Congress's unprecedented attempt to single out applicants and bar them from operating one of the most significant speech platforms in this nation presents grave constitutional problems that this court likely will not allow to stand," lawyers for TikTok wrote in their emergency application. President Biden signed the law this spring after it was enacted with wide bipartisan support. Lawmakers said the app's ownership represented a risk because the Chinese government's oversight of private companies would allow it to retrieve sensitive information about Americans or to spread propaganda, though they have not publicly shared evidence that this has occurred. They have also noted that American platforms like Facebook and YouTube are banned in China, and that TikTok itself is not allowed in the country.

Read more of this story at Slashdot.

Waymo will begin testing its autonomous vehicles in Tokyo in early 2025, marking its first deployment outside the U.S. TechCrunch reports: The move to Japan is part of Waymo's "road trips," a development program that involves bringing its technology to a variety of cities and testing it -- with each city having different challenges. In Tokyo, the Waymo robotaxis will face left-hand driving and a dense urban environment. [...] Waymo said it will partner with taxi-hailing app GO and taxi company Nihon Kotsu as part of its Japanese "road trip." Nihon Kotsu will oversee the management and servicing of the Waymo vehicles, according to the company. Initially, Nihon Kotsu drivers will operate the vehicles manually to map key areas of the Japanese capital, including Minato, Shinjuku, Shibuya, Chiyoda, Chuo, Shinagawa, and Koto. Waymo said it is working with Nihon Kotsu's team to train its employees how to operate Waymo's self-driving Jaguar I-Pace vehicles.

Read more of this story at Slashdot.

Ars Technica's Beth Mole reports: Editors of the environmental chemistry journal Chemosphere have posted an eye-catching correction to a study reporting toxic flame retardants from electronics wind up in some household products made of black plastic, including kitchen utensils. The study sparked a flurry of media reports a few weeks ago that urgently implored people to ditch their kitchen spatulas and spoons. Wirecutter even offered a buying guide for what to replace them with. The correction, posted Sunday, will likely take some heat off the beleaguered utensils. The authors made a math error that put the estimated risk from kitchen utensils off by an order of magnitude. Specifically, the authors estimated that if a kitchen utensil contained middling levels of a key toxic flame retardant (BDE-209), the utensil would transfer 34,700 nanograms of the contaminant a day based on regular use while cooking and serving hot food. The authors then compared that estimate to a reference level of BDE-209 considered safe by the Environmental Protection Agency. The EPA's safe level is 7,000 ng -- per kilogram of body weight -- per day, and the authors used 60 kg as the adult weight (about 132 pounds) for their estimate. So, the safe EPA limit would be 7,000 multiplied by 60, yielding 420,000 ng per day. That's 12 times more than the estimated exposure of 34,700 ng per day. However, the authors missed a zero and reported the EPA's safe limit as 42,000 ng per day for a 60 kg adult. The error made it seem like the estimated exposure was nearly at the safe limit, even though it was actually less than a tenth of the limit. "We regret this error and have updated it in our manuscript," the authors said in a correction. "This calculation error does not affect the overall conclusion of the paper," the correction reads. The study maintains that flame retardants "significantly contaminate" the plastic products, which have "high exposure potential."

Read more of this story at Slashdot.

An anonymous reader quotes a report from TechCrunch: Uber has 30 days to require certain drivers to get fingerprinted if the ride-hail giant intends to continue transporting unaccompanied teens in California. The California Public Utilities Commission (CPUC) issued a ruling Thursday that requires taxi and ride-hail drivers who are carrying unaccompanied minors in the state to pass a fingerprint background check. The ruling also requires transport companies to pay for the cost of those background checks. "When an adult is being tasked to provide a service to a minor, the adult is placed in a position of trust, responsibility, and control over California's most vulnerable citizenry -- children," reads the decision. "Not conducting a fingerprint-based background check to identify adults with disqualifying arrests or criminal records would place the unaccompanied minor in a potentially dangerous, if not life-threatening situation." [...] The CPUC's ruling also requires transport companies that intend to transport minors share information with the agency on how they implement live trip tracking for parents, what safety procedures they implement at pickup and drop-off locations, and what sort of driver training the companies implement specifically around transporting unaccompanied minors. The ruling also says that each company is responsible for paying for the checks. Uber has also argued against this stipulation, saying that forcing the company -- which has a market cap of around $150 billion as of December -- to pay for fingerprinting would result in a price hike for the Uber for Teens service.

Read more of this story at Slashdot.

YouTube is introducing an optional feature allowing creators to let third-party companies use their videos to train AI models, with the default setting being opt-out. The Verge reports: "We see this as an important first step in supporting creators and helping them realize new value for their YouTube content in the AI era," a TeamYouTube staffer named Rob says in a support post. "As we gather feedback, we'll continue to explore features that facilitate new forms of collaboration between creators and third-party companies, including options for authorized methods to access content." YouTube will be rolling out the setting in YouTube Studio "over the next few days," and unauthorized scraping "remains prohibited," Rob writes. Another support page says that you'll be able to pick and choose from a list of third-party companies that can train on your videos or you can simply allow all third-party companies to train on them.

Read more of this story at Slashdot.

A cyberattack on Rhode Island's RIBridges system has exposed personal data of individuals involved in programs like Medicaid, SNAP, and others, with hackers demanding a ransom. The breach may include sensitive details like Social Security numbers and banking information. The Associated Press reports: Anyone who has been involved in Medicaid, the Supplemental Nutrition Assistance Program known as SNAP, Temporary Assistance for Needy Families, Childcare Assistance Program, Rhode Island Works, Long-term Services and Supports, the At HOME Cost Share Program and health insurance purchased through HealthSource RI may be impacted, McKee said Saturday. The system known as RIBridges was taken offline on Friday, after the state was informed by its vendor, Deloitte, that there was a major security threat to the system. The vendor confirmed that "there is a high probability that a cybercriminal has obtained files with personally identifiable information from RIBridges," the state said. The state has contracted with Experian to run a toll-free hotline for Rhode Islanders to call to get information about the breach and how they can protect their data.

Read more of this story at Slashdot.

Cloudflare's 2024 internet traffic report highlights a 17.2% global increase in traffic, with Google maintaining its position as the most visited service and the U.S. responsible for 34.6% of bot traffic. The Register reports: One surprise (or perhaps not) is that IPv6 traffic is actually down as a percentage of the packets that passed through Cloudflare's network. It says that 28.5 percent of global traffic was IPv6 during 2024, whereas last year's report put this figure at 33.75 percent. The company also reveals that a fifth of all TCP connections (20.7 percent) are unexpectedly terminated before any useful data can be exchanged. Causes of this could vary from DoS attacks, quirky client behavior, or a network interrupting a connection to filter content. Coudflare says about half of these incidents were connections closed "Post SYN" -- after its server has received a client's SYN packet, but before a subsequent acknowledgement (ACK) or any useful data. These can be attributed to DoS attacks or internet scanning, while Post-ACK or Post-PSH anomalies are more often associated with connection tampering activity such as filtering, especially if they occur at high rates in specific networks. Mobile device traffic accounted for about 41.3 percent of the total, which is roughly the same as last year. This is largely split between the Apple and Android ecosystems, with iOS on almost a third and Android accounting for two-thirds. [...] Google's Chrome appears to be the most popular browser by far, accounting for 65.8 percent of all requests during 2024. Just 15.5 percent came from Apple's Safari browser, which leads the way on iOS devices, naturally. Microsoft's Edge accounted for 6.9 percent of browsing, while Mozilla Firefox stood at 4 percent. For search engines, Google also claimed the top spot, with a greater than 88 percent share of all search traffic that passed through Cloudflare. Yandex and Baidu were next with 3.1 percent and 2.7 percent, respectively, while Bing trailed with 2.6 percent. DuckDuckGo accounted for 0.9 percent of searches. You can read Cloudflare's full Year in Review here.

Read more of this story at Slashdot.

An anonymous reader quotes a report from 9to5Mac: A new survey suggests that Apple Intelligence matters to iPhone buyers, but the majority say that the initial features add little to no value. It remains to be seen whether Genmoji and ChatGPT integration will change that view. Things are even worse for Samsung smartphones, with an even greater majority of owners saying they can't see much point in the AI features offered A new survey by tech trade-in site SellCell found that AI is an important factor when choosing a new smartphone: "iPhone users showed relatively higher interest in mobile AI than Samsung users as almost half (47.6%) of iPhone users reported AI features as a 'very' or 'somewhat' important deciding factor when buying a new phone vs. 23.7% of Samsung users who said the same." "Smartphone users in general are unsatisfied with the existing AI features as the survey recorded 73% of Apple Intelligence users and 87% of Galaxy AI users stating the new features to be either 'not very valuable' or they 'add little to no value' to their smartphone experience," reports SellCell. According to the survey, these are the most popular Apple Intelligence features: - Writing Tools (72%) - Notification summaries (54%) - Priority Messages (44.5%) - Clean Up in Photos (29.1%) - Smart Reply in Mail and Messages (20.9%)

Read more of this story at Slashdot.

Google DeepMind announced a next-gen video-generating AI tool to rival OpenAI's Sora. Called Veo 2, it can generate AI video clips longer than two minutes with resolutions up to 4K (4096 x 2160). TechCrunch reports: In Google's experimental video creation tool, VideoFX, where Veo 2 is now exclusively available, videos are capped at 720p and eight seconds in length. (Sora can produce up to 1080p, 20-second-long clips.) VideoFX is behind a waitlist, but Google says it's expanding the number of users who can access it this week. Eli Collins, VP of product at DeepMind, also told TechCrunch that Google will make Veo 2 available via its Vertex AI developer platform "as the model becomes ready for use at scale." "Over the coming months, we'll continue to iterate based on feedback from users," Collins said, "and [we'll] look to integrate Veo 2's updated capabilities into compelling use cases across the Google ecosystem ... [W]e expect to share more updates next year."

Read more of this story at Slashdot.

An anonymous reader quotes a report from Ars Technica: The fall of the Berlin Wall in November 1989 was a seminal moment in 20th century history, paving the way for German reunification. Many segments, both large and small, were preserved for posterity -- including portions covered in graffiti or murals. A team of Italian scientists used a combination of spectroscopic analysis and machine learning to study paint chips from wall fragments to learn more about the chemistry of the paints and pigments used, according to a new paper published in the Journal of the American Chemical Society. [...] Nondestructive techniques like Raman spectroscopy are often used to identify the molecular signatures of pigments, dyes, and other chemical compounds, but this usually requires bringing samples to the lab. Handheld Raman devices are used for cases where analysis must be done on-site, but they are far less precise than full-size laboratory equipment. So [Francesco Armetta of the University of Palermo and co-authors of the paper] decided to adopt a machine-learning approach to enhance the precision and sensitivity of spectral data collected by those handheld devices. The team collected 15 pictorial fragments of five different colors from Berlin Wall paintings. They used handheld Raman spectroscopy on the paint chips and compared that spectral data to a commercial library of pigment spectra, confirming those findings with X-ray fluorescence and optical fiber reflectance spectroscopy. Most of the fragments had two top layers that had been painted with a brush rather than spray paint; brushstrokes were clearly visible under a microscope in several cases. The underlying third layer, in contact with the masonry, was white and probably used to prepare the surface for painting. Calcium and titanium were the most abundant elements in all the samples. Chromium and lead were present in a green-colored sample, and the authors think this was mixed with another color to get that particular shade. There were also traces of copper in blue and green samples. Armetta et al. also created their own mock-up samples by mixing commercial German acrylic paints (commonly used since the 1800s) in different ratios to try to match colors and tints from the fragments -- crucial information for restoration. This is where their machine-learning algorithm (dubbed SAPNet) proved useful. They trained it on the Raman spectral data from the Berlin Wall samples and used it to determine the percentage of pigment. The model concluded that the Berlin Wall paint chips contained titanium white and as much as 75 percent pigment. "The identification of most of the components of the fragments was only possible through the comprehensive evaluation of the results provided by all the techniques [combined]," the authors concluded, further augmented by the development of SAPNet. "While SAPNet was specifically tailored for pigment mixture analysis, its robust framework demonstrates the transformative potential of deep learning methodologies for Raman spectral analysis across diverse scientific and industrial applications."

Read more of this story at Slashdot.