The AI-powered weather prediction program works by taking in “the two most recent states of Earth’s weather,” which includes the variables from the time of the test and six hours prior. Using that data, GraphCast can predict what the state of the weather will be in six hours.

In practice, AI has already showcased its applicability in the real world. The tool predicted the landfall of Hurricane Lee in Long Island 10 days before it happened, while the traditional weather prediction technologies being used by meteorologists at the time lagged behind. Forecasts made by standard weather simulations can take longer because traditionally, models have to account for complicated physics and fluid dynamics to make accurate predictions.

Not only does the weather prediction algorithm outperform traditional technologies to forecast weather patterns in terms of pace and scale, GraphCast can also predict severe weather events, which includes tropical cyclones and waves of extreme temperatures over regions. And because the algorithm can be re-trained with recent data, scientists believe that the tool will only get better at predicting oscillations in weather patterns that coincide with grander changes that align with climate change.

Soon, GraphCast, or at least the basis of the AI algorithm that powers its predictions, might pop up into more mainstream services. According to Wired, Google might be exploring how to integrate GraphCast into its products. The call for better storm modeling has already paved a path for supercomputers in the space. The NOAA (National Oceanic and Atmospheric Administration) says it has been working to develop models that will provide more accurate readings on when severe weather events might occur and importantly, the intensity forecasts for hurricanes.

The post AI is starting to outperform meteorologists appeared first on Best News.

Current AI models such as GraphCast and Fourcastnet are already generating weather forecasts more quickly than traditional meteorological models. However, IBM notes those are AI emulators rather than foundation models. As the name suggests, foundation models are the base technologies that power generative AI applications. AI emulators can make weather predictions based on sets of training data, but they don’t have applications beyond that. Nor can they encode the physics at the core of weather forecasting, IBM says.

NASA and IBM have several goals for their foundational model. Compared with current models, they hope for it to have expanded accessibility, faster inference times and greater diversity of data. Another key aim is to improve forecasting accuracy for other climate applications. The expected capabilities of the model include predicting meteorological phenomena, inferring high-res information based on low-res data and "identifying conditions conducive to everything from airplane turbulence to wildfires."

This follows another foundational model that NASA and IBM deployed in May. It harnesses data from NASA satellites for geospatial intelligence, and it's the largest geospatial model on open-source AI platform Hugging Face, according to IBM. So far, this model has been used to track and visualize tree planting and growing activities in water tower areas (forest landscapes that retain water) in Kenya. The aim is to plant more trees and tackle water scarcity issues. The model is also being used to analyze urban heat islands in the United Arab Emirates.

The post NASA and IBM are building an AI for weather and climate applications appeared first on Best News.