NOAA researcher John Hopkins explores AI to predict environmental impacts of pollution.

A group of researchers at the Johns Hopkins Applied Physics Laboratory (APL) and the National Oceanic and Atmospheric Administration (NOAA) are investigating artificial intelligence (AI) models for intelligent weather prediction in an impressive use case.

In a Phys.org post, AI-based weather prediction models rely on the concept of ensemble modeling, which combines multiple models to make accurate predictions. The system, called APL’s Deep-Learning Network, has shown itself to be adept at running hundreds of models to respond to wide variations in atmospheric conditions.

Running models for weather forecasting requires massive amounts of data and complex mathematical calculations to arrive at predictions. Predicting future weather requires enormous computing power to analyze variables and conduct simulations.

APL’s AI forecasting system can simulate multiple ensembles in less time, saving you time and money. Upon closer observation, we found that this model predicted a 10-day forecast with just 21 hours of input data, unlike traditional models that require months of data.

“The amount of computation we can save with our network is enormous,” said Jennifer Sleeman, senior AI researcher at APL. “We are speeding up the work because we are asking the model to compute shorter time steps, which can be done more easily and quickly, and we are using deep learning emulators to simulate these ensembles and account for changes in weather data,” she said.

Recognizing the system’s potential, NASA jumped into research in an attempt to increase the resolution of the results for enterprise use cases. Using NASA’s GEOS Composition Forecasting (GEOS-CF) system, researchers improved system performance by increasing the level of forecast accuracy.

Although there is little climate research supporting AI, recent research related to emerging technologies has laid the foundation for APL’s machine learning model.

“If we had tried to do the same thing five years ago, we wouldn’t have been as successful as we are today,” said Marisa Hughes, head of climate information at APL. “Because we are building on this accelerating momentum of research.” “We set out to share our results and learn which methods and architectures are effective when applied to different problems around the world,” she said.

AI use cases increase

Starting in 2023, research into AI use cases has surged, with researchers exploring multiple utilities for this technology. In 2023, a group of researchers at ETH Zurich used AI models to synthesize new drugs, and a recent MIT study examined the use cases of computer vision AI in the workplace.

Despite growing use cases, AI companies have come under fire for failing to comply with copyright and privacy regulations. Several major AI developers, including OpenAI, are grappling with legal challenges from disgruntled creators amid increased scrutiny from privacy watchdogs around the world.

For artificial intelligence (AI) to function properly within the law and succeed in the face of growing challenges, it must integrate enterprise blockchain systems that ensure data input quality and ownership. This helps keep your data safe while ensuring immutability. data. Check out CoinGeek’s coverage To learn more about this new technology Why enterprise blockchain will become the backbone of AI.

Example: AI is synthetic, not generative.

Are you new to blockchain? To learn more about blockchain technology, check out CoinGeek’s Blockchain for Beginners section, our ultimate resource guide.