AI and Sustainability: Transforming Climate Action

AI is transforming weather forecasting from a computational brute-force exercise into a pattern recognition challenge. Traditional numerical weather prediction systems solve complex atmospheric equations across global grids, requiring supercomputers to process terabytes of data for forecasts that often miss localised phenomena critical to business operations.

Machine learning models take a different approach. Instead of solving physics equations in real-time, AI systems analyse decades of historical weather data to identify atmospheric patterns that correlate with specific outcomes. This pattern-based forecasting enables predictions at 200-metre resolution while using a fraction of the computational power required by conventional systems.

The shift matters because climate change is increasing the frequency of extreme weather events that existing forecasting infrastructure struggles to predict. Traditional models operate at kilometre-scale resolution and update every six to twelve hours. AI systems can provide street-level forecasts updated continuously, enabling businesses to respond to weather risks with precision previously unavailable to commercial users.

“AI-powered weather forecasting has the potential to revolutionise high-quality, high-resolution weather and disaster management solutions, particularly in this accelerating phase of climate change,” says H.E. Dr. Abdulla Al Mandous, Director General of the National Center of Meteorology UAE. “By enhancing prediction accuracy and enabling hyper-local, real-time forecasts, this technology empowers better decision-making and strengthens resilience against climate challenges.

“We are excited to see how these innovations will shape the future of sustainability and drive more effective, data-driven solutions. The National Center of Meteorology UAE is rapidly embracing AI technologies for advanced weather forecasting and disaster management, positioning itself at the forefront of global efforts in weather and climate resilience.”

Weather-related disruptions account for 30% of flight delays according to Federal Aviation Administration data, costing airlines billions annually. 

Traditional forecasting provides general airport conditions but cannot predict specific wind shear or visibility affecting individual runways. Ground transportation faces similar challenges where localised fog and precipitation create safety hazards that regional forecasts cannot address.

Behind G42 and Nvidia’s AI and Earth-2 partnership

G42 and Nvidia have developed an AI-powered weather forecasting system through their Earth-2 Climate Tech Lab in Abu Dhabi. The partnership produces 200-metre resolution forecasts using a generative downscaling model that learns small-scale regional physics to predict extreme weather events.

Inception, a G42 company working with Space42, has customised CorrDiff from Nvidia’s Earth-2 platform for detailed urban forecasts. Core42, G42’s digital infrastructure company, hosts the platform using Nvidia hardware. The system demonstrated capabilities through an end-to-end fog simulation over the UAE, addressing localised weather phenomena affecting multiple industries.

Andrew Jackson, Chief Executive Officer of Inception, says: “For AI to be truly transformative, it should be an accessible tool for governments and industries worldwide. Through our collaboration with Nvidia, we are bringing cutting-edge forecasting capabilities within reach of those who need them most. Because CorrDiff is designed to adapt to local weather behaviours, this technology is not only improving forecasting for the UAE but can also be tailored for regions worldwide facing climate volatility.”

AI forecasting systems adapt to local weather patterns across geographical regions. Traditional models use global atmospheric equations that may not capture regional variations. AI systems learn from local historical data to improve predictions for specific areas over time.

Energy companies benefit from hyper-local weather forecasting for renewable energy management. The International Energy Agency reports that improved weather forecasting could increase wind energy efficiency by 15% through better wind pattern prediction. Current renewable energy forecasting operates at kilometre resolutions, making it difficult to predict conditions at individual installations. AI-powered systems provide forecasts for specific turbines or solar arrays.

How Nvidia physics AI models process climate data

Physics AI models process climate data by learning atmospheric patterns through data analysis rather than relying solely on mathematical equations. This approach enables faster forecast generation while reducing computational infrastructure requirements compared to traditional systems.

Dion Harris, Senior Director of HPC and AI Factory Solutions at Nvidia, says: “Hyper-local weather forecasting is becoming crucial to determining patterns and people positioning as climates around the world undergo change. G42 is innovating using the Nvidia Earth-2 platform to drive access to actionable information in areas that need it most.”

The Nvidia Earth-2 platform provides computational frameworks for high-resolution climate modelling. Platform scalability allows organisations to process environmental data from satellite observations, ground-based sensors and atmospheric monitoring systems. Traditional forecasting systems require supercomputing resources previously available only to major meteorological agencies. AI-powered forecasting democratises these capabilities.

Dion continues: “Weather forecasting has always required significant computational power, but AI is redefining what’s possible. With Physics AI models for high-resolution climate modeling, we can now generate faster, more detailed and more adaptive predictions. The scalability of accelerated computing allows us to process vast amounts of data efficiently, helping industries and governments better understand and respond to extreme weather patterns.”

Insurance companies use AI-powered weather forecasting for operational improvements. Weather-related claims account for 60% of property insurance losses globally according to Munich Re data. AI forecasting enables insurers to assess risks at specific locations rather than using broad regional data.

Technology expansion targets climate vulnerable regions

G42 explores expansion of hyper-local forecasting systems to climate-vulnerable regions across Africa, South Asia and Southeast Asia. These regions experience disproportionate climate change impacts despite lower emissions contributions.

Agricultural applications represent opportunities in developing regions. The Food and Agriculture Organization estimates weather-related events cause US$5bn in annual crop losses. Farmers dependent on rain-fed agriculture require accurate precipitation forecasts for planting and harvesting decisions.

Andrew adds: “The ability to generate hyper-local predictions gives decision-makers the confidence to act faster, plan better and build more resilient systems. Beyond its impact on weather forecasting, this breakthrough has far-reaching applications in aviation, urban mobility, energy grid optimisation and environmental planning. Hyper-local insights can reduce flight delays, improve road safety, optimise renewable energy distribution and support climate-adaptive urban development.”

Water resource management benefits from accurate precipitation predictions that enable utilities to manage reservoirs effectively. Early warning systems for extreme weather events can save lives where populations face climate impacts.

Dion concludes: “The scalability of accelerated computing allows us to process vast amounts of data efficiently, helping industries and governments better understand and respond to extreme weather patterns.”