Aurora 1.5: Extending open foundation models for weather and Earth-system applications
Microsoft Research released Aurora 1.5, an upgraded version of its open foundation model for weather and climate prediction. The update introduces hourly forecasting and probabilistic ensemble methods to improve real-world accuracy.
- Aurora 1.5 introduces hourly forecasting and probabilistic ensemble methods, improving real-world weather and climate predictions.
- The model now supports 22 additional variables, expanding its utility for energy grid management and disaster response.
- Aurora 1.5 remains open-source, reinforcing Microsoft’s push for transparent and accessible AI in environmental science.
- The update addresses a critical gap in high-resolution, uncertainty-aware weather forecasting for decision-makers.
Microsoft Research has unveiled Aurora 1.5, a significant upgrade to its open foundation model designed for weather and Earth-system forecasting. The new version expands the model’s capabilities by adding 22 additional variables, enabling hourly temporal resolution instead of daily or sub-daily intervals. This change allows for more granular and timely predictions, which are critical for applications in energy grid management, disaster preparedness, and climate monitoring.
The update also incorporates probabilistic ensemble forecasting, a technique that generates multiple prediction scenarios to quantify uncertainty. This feature is particularly valuable in high-stakes environments where decision-makers need to assess risk and plan for a range of possible outcomes. Aurora 1.5 builds on the original Aurora model, which was already recognized for its open-source approach and broad applicability across weather-related domains.
The release underscores Microsoft’s commitment to advancing AI-driven solutions for environmental challenges. By making the model more accessible and precise, Aurora 1.5 aims to support researchers, policymakers, and industries that rely on accurate weather and climate data.
Provides a powerful open-source tool for building advanced weather and climate applications with higher temporal resolution.
Enables more accurate risk assessment and operational planning in energy, agriculture, and insurance sectors.
Offers a cutting-edge example of AI applied to environmental science and open-source model development.
Improves the reliability of weather forecasts, benefiting public safety and climate adaptation efforts.
- probabilistic ensemble forecasting
- A method that generates multiple prediction scenarios to quantify uncertainty in weather and climate models.
- open foundation model
- An AI model released under an open-source license, allowing public access and modification for broader applications.
Artificial Intelligence: Patient education, or misinformation? - Ophthalmology Times Europe
Artificial Intelligence in Febrile Neutropenia: From Risk Scores to Real-Time Clinical Decision Support - Cureus
Health systems need data discipline for effective AI - Healthcare IT News
China bets on AI to speed up science despite chip limits - Chemical & Engineering News
SU announces launch of artificial intelligence portfolio - Eagle News Online
HardwareMeta’s new AI chips will begin production in September
Meta plans to start manufacturing its latest AI-specific chips in September, aiming to reduce reliance on Nvidia GPUs.
BusinessNvidia is a victim of the compute marketplace it created
Nvidia's stock has dropped 15% from its peak in May, despite projected revenue growth, highlighting vulnerabilities in the AI compute market it helped create.
SecurityMicrosoft goes all in on new AI-powered Windows security strategy - what it means for you
Microsoft’s security team has deployed an AI-driven system to detect and prioritize Windows vulnerabilities, accelerating patch development and deployment.
LLMOpenAI rolls out GPT-5.6 after government green light — and announces ‘ChatGPT Work’
OpenAI has received US government approval to publicly release GPT-5.6, following a limited preview restricted to approved organizations. The company also introduced ChatGPT Work, an AI agent combining ChatGPT and Codex for non-technical users.
BusinessMeta's Muse Spark 1.1 API pricing squeezes OpenAI and Anthropic as the AI price war heats up
Meta launched its Muse Spark 1.1 API at $4.25 per million output tokens, undercutting Grok 4.5 and major competitors like OpenAI and Anthropic.
ProgrammingMCP tool design: Practical approaches and tradeoffs
AWS researchers outline best practices for designing tools within the Model Context Protocol to improve LLM reliability.