Latest news with #Graphcast
Coin Geek
19-06-2025
- Climate
- Coin Geek
AI records advanced proficiency in forecasting storms
Getting your Trinity Audio player ready... Two research teams have recorded impressive levels of success with artificial intelligence (AI)-based weather forecasting systems. According to a report, the first research team from Microsoft (NASDAQ: MSFT) leveraged the company's Aurora AI model to create an advanced weather forecasting system. The research, published in the Nature Journal, disclosed that the Aurora AI-based model outperformed traditional computerized weather forecasts. The Microsoft researchers noted that the model can accurately predict a range of weather events, including narrowing down forecasts to specific ocean wave patterns and air quality. Furthermore, the researchers state that the model exceeded expectations in forecasting tropical cyclones with significantly lower computational costs. The team achieved the feat by training the AI weather prediction model on over 1 million hours of 'diverse geophysical data,' providing the system with a deep pool to accurately make forecasts. A U.S.-based team has also recorded significant strides in AI-based weather forecasts, leaning on Google DeepMind's (NASDAQ: GOOGL) Graphcast tool. The National Oceanic and Atmospheric Administration (NOAA) researchers revealed that the new model is 10X faster than traditional systems in storm predictions. The model, trained on data from NOAA's Warn-on-Forecast-System (WOFS), reduces the forecast time for storms from nearly five minutes to seconds. Apart from spotting incoming storms, the Google-based model can predict the storm's pattern and movement for up to two hours with remarkable accuracy. 'The model yielded largely accurate predictions of how storms would evolve for up to two hours,' read the report. 'These predictions matched 70% to 80% of those generated by the Warn-on-Forecast system.' Big Tech is hurtling toward AI-based weather forecasting tools, with Google leading the charge. Microsoft and IBM (NASDAQ: IBM) have also unveiled their AI-based weather prediction models with varying degrees of success. Countries are turning to AI models to stay ahead of the curve Nations at risk of climate and weather disasters embrace AI models to predict incoming events and take proactive measures to mitigate damage. India has integrated AI to track flood patterns, while Chinese researchers are identifying the upsides to AI-based weather forecasting for the country. An Australian charity is leaning on AI to protect the Daintree rainforest from ecological challenges. However, an integration with blockchain and Internet of Things (IoT) technology is tipped to improve the accuracy of AI weather prediction models. DLT can tackle food fraud, but success remains a challenge The scourge of food fraud is on the rise, stealing nearly $50 billion annually from the global food industry while posing significant health risks. However, a report notes that blockchain offers a veritable solution to stifle the activities of bad actors in the food industry. According to a report, while food fraud siphons only a small slice of the food industry's $12 trillion valuation, the figure is equivalent to the GDP of Malta. Cases of food mislabeling and dilution are at an all-time high, with horse meat sold as beef and olive oil diluted with cheaper vegetable oils. The report notes that the absence of transparency in global supply chains is fueling the rise of food fraud. With industry processes built in silos and 'information islands,' participants in the supply chain do not have a bird's eye view of the processes. 'Many companies maintain their own internal tracking systems, but these often lack interoperability with their suppliers or customers,' said Naoris Protocol CEO David Carvalho. To increase transparency and reduce the footprint of bad actors in the space, industry experts are making a case for blockchain. There is a consensus that the transparency and immutability features of publicly distributed ledgers will hold food suppliers to a higher standard. Furthermore, the industry players highlight the perks of 'selective transparency,' which allows supply chain participants to share only relevant data while protecting sensitive commercial data from authorized participants. Experts are turning to the utility of smart contracts and automation functionalities as reasons for blockchain-based supply chains to fight food fraud. Early use cases have yielded a streak of positives with South Korea's KT using the technology to fight food fraud, laying the foundation for new entrants. Vietnamese companies are turning to blockchain to verify halal certifications, preventing unscrupulous suppliers from passing off non-halal food to unsuspecting consumers. Malaysia is also mulling the prospects of on-chain halal certifications, citing a wave of positives for the food industry. Not a walk in the park Incorporating blockchain in food supply chains is not easy, with the report noting steep integration costs and manpower training. Apart from high implementation costs, there is the additional 'garbage in, garbage out' challenge associated with a Web3-based system. The report recommends the integration of oracles and IoT technologies to feed external data into distributed ledgers. Other challenges include privacy and data concerns, as well as the absence of standardized protocols for blockchain adoption across several jurisdictions. In order for artificial intelligence (AI) to work right within the law and thrive in the face of growing challenges, it needs to integrate an enterprise blockchain system that ensures data input quality and ownership—allowing it to keep data safe while also guaranteeing the immutability of data. Check out CoinGeek's coverage on this emerging tech to learn more why Enterprise blockchain will be the backbone of AI. Watch: Artificial intelligence needs blockchain title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen="">
The Star
06-06-2025
- Science
- The Star
AI can make storm warnings faster and more accurate, researchers say
Microsoft researchers claimed that its Aurora AI model outperforms operational forecasts in predicting air quality, ocean waves and more. — Pixabay BERLIN: Artificial intelligence could soon be used to generate faster predictions and more timely warnings of imminent typhoons and downpours, according to scientists based in the US and the Netherlands. In a paper published by the journal Nature , Microsoft researchers claimed that the company's Aurora AI model "outperforms operational forecasts in predicting air quality, ocean waves, tropical cyclone tracks and high-resolution weather, all at orders of magnitude lower computational cost." Microsoft stated that the system was "trained on more than one million hours of diverse geophysical data" – enough information to enable it "more accurately predict not just the weather, but a wide range of environmental events in a series of retrospective analyses," including, hurricanes, typhoons and ocean waves Meanwhile, a team from the US government's National Oceanic and Atmospheric Administration (NOAA) and the University of Oklahoma said that a prediction model they created using Google DeepMind's Graphcast tool could be 10 times faster at predicting storms than previous computer-based platforms. The researchers "trained" the Google platform on data from NOAA's Warn-on-Forecast-System (WOFS), creating an AI variant called WOFSCast that shortens forecast times from minutes to seconds. "The model yielded largely accurate predictions of how storms would evolve for up to two hours; these predictions matched 70% to 80% of those generated by the Warn-on-Forecast system," according to the American Geophysical Union, which published the NOAA/Oklahoma findings its Geophysical Researh Letters journal. – dpa/Tribune News Service
Yahoo
04-06-2025
- Climate
- Yahoo
AI can make storm warnings faster and more accurate, researchers say
Artificial intelligence could soon be used to generate faster predictions and more timely warnings of imminent typhoons and downpours, according to scientists based in the US and the Netherlands. In a paper published by the journal Nature, Microsoft researchers claimed that the company's Aurora AI model "outperforms operational forecasts in predicting air quality, ocean waves, tropical cyclone tracks and high-resolution weather, all at orders of magnitude lower computational cost." Microsoft stated that the system was "trained on more than one million hours of diverse geophysical data" - enough information to enable it "more accurately predict not just the weather, but a wide range of environmental events in a series of retrospective analyses," including, hurricanes, typhoons and ocean waves Meanwhile, a team from the US government's National Oceanic and Atmospheric Administration (NOAA) and the University of Oklahoma said that a prediction model they created using Google DeepMind's Graphcast tool could be 10 times faster at predicting storms than previous computer-based platforms. The researchers "trained" the Google platform on data from NOAA's Warn-on-Forecast-System (WOFS), creating an AI variant called WOFSCast that shortens forecast times from minutes to seconds. "The model yielded largely accurate predictions of how storms would evolve for up to 2 hours; these predictions matched 70% to 80% of those generated by the Warn-on-Forecast system," according to the American Geophysical Union, which published the NOAA/Oklahoma findings its Geophysical Researh Letters journal.
The National
29-01-2025
- Climate
- The National
'Nowcasting': how AI is reshaping weather forecasts
It is no secret that artificial intelligence is everywhere today. But, now, an AI front is passing over the world of weather forecasting. AI has improved forecasting so much that, in some cases, it can outperform conventional systems, an expert has told The National. Marouane Temimi, associate professor at the Stevens Institute of Technology in the US, said the pattern has emerged over the past few years and could lead to hugely improved short-term forecasting that can pinpoint which areas of a city can expect rain. Speaking on the sidelines of the International Rain Enhancement Forum in Abu Dhabi on Wednesday, Prof Temimi said these forecasts – called nowcasting – could also lead to better emergency responses. They can be used for any extreme weather event from hurricanes to wildfires to storms. But he also said that AI systems might run out of data if there is less of a commitment to conventional physics-based forecasting models. 'AI-based models are doing well, close enough to the physics-based model – the traditional model that we have been using,' said Prof Temimi. 'In some cases they even overperformed them. The European model that was developed by the European Centre for Medium-Range Weather Forecasts has shown that.' Where AI systems may have a crucial role is this ultra short-term 'nowcasting' that can track a storm over several hours. 'They tend to have better accuracy when it comes to the location and the timing of the magnitude of rainfall,' he said, with such a model developed at his university. 'If you have a last-minute decision' to take – like evacuate people or close roads – then you rely on the nowcasting instead of the forecasting.' Many technology companies are developing AI weather forecast models. An example is Graphcast developed by Google's DeepMind that identified the landfall location of Hurricane Beryl last year before regular models. Many countries are now exploring this development, with money pouring into the field and government agencies figuring out how to use such models. But much more research and funds are needed. But there is a much larger issue. Conventional forecasting models are a series of complex equations based on huge amounts of data built up over decades and compiled by experts. 'These are basically complex models that are built out of millions and millions of lines of codes and they try with their structure to mimic every single small process that happens out in nature … to predict weather,' said Prof Temimi, who is based in the New Jersey university's department of civil, environmental and ocean engineering. He said there is an entire atmospheric science community that has been studying the physics of clouds, radiation of the Sun and much more that informs these physics-based models. This has been built up over decades thanks to this painstaking work. But with the advent of AI over the past few years, things have started to change as it does not look at these microprocesses. It simply takes the information from satellite images to radar details and identifies patterns over time. 'Unfortunately, AI does not go into those details,' he said. 'AI can try to predict events without that strong knowledge of physics.' The more data the better, but what happens when the data runs out? Prof Temimi said that data could become scarcer if there is a greater reliance on AI and less of a commitment to the hard task of gathering information without which the AI systems could not work. 'Eventually, we may risk running out of data to feed the AI models. The community will [need] to find a solution or a compromise because we cannot drop the physics-based model, in my opinion, and we cannot all shift to the AI models.' The forum, meanwhile, has drawn experts in weather modification and water security from around the world. Discussion on Wednesday focused on new cloud-seeding materials and the role of drones and aircraft in weather modification. Student and early-career scientists from local and international research institutions also presented studies into the field. The forum continues until Thursday.
