News
Google’s latest AI weather model gives you no excuse to forget your umbrella
Scientists at Google Deepmind and Google Research released a new artificial intelligence model for weather forecasting today that sees our changing atmosphere more clearly and predicts its behavior more often.
WeatherNext 3 is the latest wave of a sea change in meteorology brought out by deep learning techniques, and Google says it will start feeding into weather information users see in search, Google Maps, and Gemini, as well as being available to users and researchers on Google’s cloud platforms.
“This is going to be the first time that some of the core variables feed and power a lot of the Google products,” Samier Merchant, a Google senior staff engineer, told TechCrunch.
The new model has already proven to be the most accurate among leading contenders tested on Operational WeatherBench, a utility for comparing AI forecasts built by the startup Brightband. It looks at metrics like temperature, windspeed, and humidity.
As well as beating out other deep-learning models built by Google, Microsoft, Nvidia, and the European Center for Medium-Range Weather Forecasting, it also beats traditional forecasts from the US National Weather service and the ECMWF.
Most weather forecasts come from government-owned supercomputers laboriously churning through mathematical equations written to describe the physics of weather; while these systems have become remarkably accurate, they are expensive and comparatively slow. After the ECMWF released more than half a century of weather data produced by these systems in 2018, deep learning researchers began training models that could make predictions far more quickly and with comparable accuracy to government tools.
“Weather is chaotic, and so small differences really start to perturb massively…Machine learning targets the problem we are really solving, which is approximate noisy physics from incomplete information and finite compute, and so it learns patterns from a lot of data,” Ferran Alet, a staff research scientist manager at DeepMind.
Since then, model-makers have pushed on the key weaknesses of AI forecasting models: They tend to forecast over a wider area—15 to 25 square km—than is truly useful, they’re not always great with rain, and they still depend on the formatted data-sets produced by government agencies.
WeatherNext 3 takes on all three challenges. On key variables, researchers told TechCrunch, it can predict down to a resolution of 5km. Its evaluations on rain are 60% improved over WeatherNext 2, and it can now produce hourly forecasts, instead of the standard prediction every six hours.
Those improvements are the result of specific choices made by the designers. WeatherNext 3 is a larger model, with 2.4 times more parameters than its predecessor, and tailoring the targets for the decoder heads to give more useful answers. While most weather forecasts output as metrics averaged across a 3D grid, DeepMind researchers have already won plaudits by tuning their model to also visualize cyclone paths.
This time around, the designers also trained the model to target its forecasts to specific weather data stations. This is important not only for offering more granular predictions, but also for being able to evaluate its work against specific, ground-truth data.
“The idea, with a lot of AI applications, is to try to run tasks as end-to-end as possible,” Daniel Rothenberg, an atmospheric scientist at Brightband, said. “Adding a capability where this model is now also predicting, say, what Denver’s airport’s weather station is going to measure on an hourly basis, just connects that forecasting task closer to the core.”
The model is able to forecast more frequently because it can ingest weather satellite data collected in real-time on an hourly basis. Feeding AI models on raw empirical observations, rather than the analysis produced by weather supercomputers, promises a more accurate forecast, but it is still technically challenging to get models to work with unformatted data.
Google says WeatherNext 3 is the “first” AI model to directly incorporate raw observations for a high-resolution global forecast, but the AI weather startup WindBorne says its model, WeatherMesh 6, has been incorporating raw observations from its fleet of weather balloons and other sources since late 2025. Asked about that, Google pointed out that its forecasts are higher resolution across the globe. Regardless, both models still rely on national weather datasets to perform forecasts, so more work will be required for true direct data assimilation.
While LLMs get the bulk of the attention, the transformer revolution in meteorology has been just as important. European and US weather agencies are already using AI models in their forecast products, and their speed and low cost promise to bring economic impact to poorer regions where the expense of high-quality sensors and supercomputers has put accurate forecasts out of reach.
Bill Gates recently cited AI-powered weather forecasting as a crucial benefit of the technology, with better forecasts improving crop yields in developing countries. Alet, the DeepMind researcher, said that higher-resolution forecasts of wind, rain, and cloud cover will be useful to make renewable energy projects more dependable.
“At the end of the day, I think Google is about providing useful information to the user, and a lot of what users are looking for has to do with the weather in some way or another,” Alet said.
News
“The Future Has Announced Itself” — SSA Adeboye Hails Ilenikhena, Usor as Debut Goals Lift Super Eagles
The Senior Special Assistant to the President on Grassroots Sports Development, Hon. Adeyinka Anthony Adeboye, has congratulated the Super Eagles on their hard-fought 2-1 victory over Madagascar, describing the match-winning contributions of debutants George Ilenikhena and Moses Usor as a powerful statement about the future of Nigerian football.
READ ALSO: George Ilenikhena, Moses Usor’s Debut Goals Save Super Eagles From Home Defeat By Madagascar
Nigeria were forced to come from behind at the Godswill Akpabio International Stadium in Uyo after Madagascar took a shock first-half lead in the opening match of the 2027 Africa Cup of Nations qualifying campaign.
Ilenikhena restored parity before the break, marking his senior international debut with a crucial goal, while Usor came off the bench in the second half to score the winner and ensure Nigeria began the campaign with maximum points.
Reacting to the victory, Adeboye said seeing two new players take responsibility on their first appearance for the senior national team was particularly encouraging.
“The future has announced itself,” Adeboye said. “Two players were given an opportunity to represent Nigeria at senior level, and both responded with goals. That should excite every Nigerian who believes in the enormous talent we have in this country.”
The Presidential aide commended Super Eagles coach Eric Chelle for providing opportunities for emerging players, stressing that national-team renewal depends on creating room for deserving talents to prove themselves.
According to Adeboye, the performance also strengthens the case for a more deliberate pathway connecting grassroots and youth football with professional clubs and the national teams.
“Nigeria has never lacked talent. The responsibility before us is to build a system that identifies these talents early, develops them properly and ensures they have somewhere to go,” he said.
“Somewhere in our communities today is another young player dreaming of wearing the Super Eagles jersey. Our grassroots development structure must make that journey possible rather than leaving it to chance.”
Adeboye also praised goalkeeper Stanley Nwabali and the rest of the team for showing resilience on a difficult evening when Madagascar threatened to frustrate the three-time African champions.
He said qualification campaigns often produce difficult matches and stressed that the ability to recover from setbacks and secure maximum points would be important as Nigeria progresses.
The SSA also congratulated Moses Simon on reaching his 100th appearance for Nigeria, describing the milestone as an example of commitment and longevity in national service.
“For me, there was something symbolic about the evening,” Adeboye said. “We saw two young players beginning their Super Eagles journeys with goals, and we also celebrated Moses Simon reaching 100 appearances. That is the transition every strong football nation needs — experience alongside emerging talent.”
Adeboye urged the Super Eagles to quickly turn their attention to their next qualifying assignment against Guinea-Bissau, insisting that the victory over Madagascar should provide confidence rather than complacency.
“Three points are important, but the journey has only started. Learn from this game, correct the weaknesses and keep moving forward,” he said.
“To Ilenikhena and Usor, congratulations. You have shown young Nigerian footballers that when opportunity comes, preparation matters. Keep working, remain humble and keep making Nigeria proud.”
The latest operational performance report by the Nigerian Electricity Regulatory Commission (NERC) has shown that Nigeria’s grid-connected power plants operated at an average of 86 per cent of their available capacity in August 2026.
This was one of the major highlights of the NERC’s August 2026 factsheet report published on Thursday. The report showed that Nigeria’s power plants had an average available capacity of 4,758 megawatts (MW) during the month under review, while average hourly generation was pegged at 4,102MW.
According to the report, about 656MW of the available generation capacity was not utilised on average during the period.
Among the major energy producers, Kainji_1 recorded a 98 per cent load factor, generating 345MW out of 352MW available capacity, while Afam_2 recorded 99 per cent, with 262MW generated against 265MW available.
It said Egbin_1 operated at 96 per cent, generating 333MW from 347MW of available capacity, while Ihovbor_2 recorded 92 per cent, generating 418MW from 454MW of available capacity.
Other major plants listed included Delta_1 at 80 per cent load factor, Zungeru_1 at 72 per cent, Odukpani_1 at 74 per cent, Shiroro_1 at 87 per cent, Jebba_1 at 83 per cent, and Okpai_1 at 87 per cent.
Frequency, voltage stability breached limits
Despite the relatively high utilisation rate, NERC reported breaches of prescribed grid frequency and voltage limits during the month.
The commission said the average lower grid frequency was 49.34Hz, while the average upper grid frequency was 50.67Hz, exceeding the prescribed operating range of 49.75Hz to 50.25Hz.
Similarly, it noted that the monthly average lower grid voltage was recorded at 302.29 kilovolts (kV), while the average upper grid voltage stood at 349.68kV.
NERC said both figures exceeded the prescribed voltage range of 313.50kV to 346.50kV.
The data showed significant differences in plant utilisation.
Olorunsogo_1 recorded a 100 per cent load factor, generating 115MW from 115MW of available capacity. Omoku_1 and Igbafо_1 also recorded 100 per cent utilisation.
Omotosho_1 generated 148MW from 149MW available, representing a 99 per cent load factor, while Dadin-Kowa_1 recorded 98 per cent after generating 35MW from 36MW available.
READ ALSO: DisCos bill N250.79bn, collect N205.53bn in July — NERC
However, some plants recorded substantially lower utilisation. Afam_1 operated at 67 per cent, while Ikeja_1 recorded 76 per cent and Ihovbor_1 79 per cent.
Several listed plants recorded zero generation during the month, including Sapele_2, Alaoji_1, Geregu_2 and Ibom Power_1.
The commission’s data also showed that Olorunsogo_2 generated 87MW from 109MW available, while Sapele_1 generated 25MW from 27MW available.
Overall, the August figures indicate a grid operating at relatively high utilisation of available generating capacity, while frequency and voltage excursions remained notable operational issues.
Discover more from Premium Times Nigeria
Subscribe to get the latest posts sent to your email.
-
Featured3 days agoPLATEAU STATE: IS THERE PEACE, OR ONLY THE ABSENCE OF VIOLENCE?
-
News3 days ago
Plateau Killings: Rotjimwa Yilyok Urges Security Agencies to Intensify Action
-
Business3 days ago
Shettima Urges African Leaders to Process Minerals Locally
-
Business3 days ago
General Business to Drive 72% of Mutual Benefits Assurance’s Projected ₦96.82bn GWP
