By Hannah Hickey
Dec 21, 2020
Today’s weather forecasts come from some of the most powerful computers on Earth. The huge machines churn through millions of calculations to solve equations to predict temperature, wind, rainfall, and other weather events. A forecast’s combined need for speed and accuracy taxes even the most modern computers.
The newly developed global weather model bases its predictions on the past 40 years of weather data, rather than on detailed physics calculations.
The simple, data-based AI model can simulate a year’s weather around the globe much more quickly and almost as well as traditional weather models, by taking similar repeated steps from one forecast to the next, according to a paper in the
Artificial intelligence can analyze past weather patterns to predict future events, much more efficiently and potentially someday more accurately than today’s technology, researchers say.
Today’s weather forecasts come from some of the most powerful computers on Earth. The huge machines churn through millions of calculations to solve equations to predict temperature, wind, rainfall, and other weather events. A forecast’s combined need for speed and accuracy taxes even the most modern computers.
The newly developed global weather model bases its predictions on the past 40 years of weather data, rather than on detailed physics calculations.
The simple, data-based AI model can simulate a year’s weather around the globe much more quickly and almost as well as traditional weather models, by taking similar repeated steps from one forecast to the next, according to a paper in the
Stephanie Bailey, CNN • Published 17th December 2020
FacebookTwitterEmail
7 Pictures
(CNN) When a ship sails through the sea, barnacles, mussels, algae, and other organisms stick to the hull of the vessel. This process is called biofouling and it s a big problem for the shipping industry.
Biofouling increases the drag of ships, so more energy is needed to power them, increasing fuel costs and multiplying their carbon emissions.
According to the International Maritime Organization (IMO), maritime transport is responsible for nearly 3% of global greenhouse gas emissions. If shipping were a country, it would be the sixth largest polluter in the world.
The buildup of marine life can also lead to non-indigenous, invasive species being introduced to new environments. This could cause irreversible damage as these species become dominant in their new habitat and disrupt the biodiversity an issue the IMO calls one of the greatest threats to the world s freshwater, coastal and
Cosmographers attend CRA URMD Grad Cohort Workshop
Joseph Kready: 2020 Social Networks and Health Fellow
At COSMOS, we are studying various aspects of social media and online behavior – the good, bad and the ugly. From Autism awareness campaigns to ISIS’ and anti-West/anti-NATO propaganda campaigns, at COSMOS, Dr. Agarwal is directing several projects with funding from the U.S. National Science Foundation (NSF), U.S. Army Research Office (ARO), U.S. Office of Naval Research (ONR), U.S. Air Force Research Lab (AFRL), and U.S. Defense Advanced Research Projects Agency (DARPA).
Research at COSMOS has made contributions to computational social network analysis and advanced the studies in social cyber security, cyber campaign coordination, identifying powerful actors and groups, disinformation dissemination across social media, cyber threat monitoring, social-cyber forensics, health informatics, data mining, and privacy. COSMOS has developed publicly available social media minin
Loading video.
VIDEO: On the left is the new paper s Deep Learning Weather Prediction forecast. The middle is the actual weather for the 2017-18 year, and at right is the average weather for. view more
Credit: Weyn et al./ Journal of Advances in Modeling Earth Systems
Today s weather forecasts come from some of the most powerful computers on Earth. The huge machines churn through millions of calculations to solve equations to predict temperature, wind, rainfall and other weather events. A forecast s combined need for speed and accuracy taxes even the most modern computers.
The future could take a radically different approach. A collaboration between the University of Washington and Microsoft Research shows how artificial intelligence can analyze past weather patterns to predict future events, much more efficiently and potentially someday more accurately than today s technology.