Google AI predicts long-term climate trends and weather in minutes

Accurate forecasts help us prepare for extreme weather events like tropical storms. Credit: NOAA/Getty

Computer models that combine traditional weather forecasting techniques with machine learning have outperformed other artificial intelligence (AI)-based tools in predicting weather scenarios and long-term climate trends.

The tool, published in Nature on July 22, is the first machine learning model to generate accurate ensemble weather forecasts covering a range of scenarios. The development of this tool makes it faster and less energy-intensive than existing tools, while providing more detailed forecasts than approaches based solely on AI.

Traditional climate models have to be run on supercomputers; “this model can run in minutes,” says study co-author Stephan Heuer, who studies deep learning at Google Research in Mountain View, California.

How AI is improving climate forecasting

Current forecasting systems typically rely on general circulation models (GCMs) – programs that use the laws of physics to simulate Earth's ocean and atmospheric processes and predict how they affect weather and climate. But GCMs require a lot of computing power, and advances in machine learning are starting to provide more efficient alternatives. “We have terabytes or even petabytes (a million times a gigabyte) of historical weather data,” Heuer says. “We can learn from these patterns to build better models.”

Several machine learning forecasting models are already available, such as Pangu-Weather, developed by Huawei, a technology conglomerate based in Shenzhen, China, and GraphCast, from London-based DeepMind. These models have a level of accuracy comparable to typical GCMs for deterministic forecasts that generate single weather forecasts. However, GCMs are less reliable for ensemble forecasts or long-term climate predictions.

The problem with a pure machine learning approach is that it can only be trained on data it has already seen, says Scott Hosking, who researches AI and environmental data at the Alan Turing Institute in London. Because the climate is constantly changing and we are entering an unknown world, machine learning models need to extrapolate into that unknown future. By bringing physics into the model, we can ensure that the model is physically constrained and cannot do unrealistic things.

Hybrid Model

Heuer and his team developed and trained NeuralGCM, a model that combines aspects of traditional, physically-based atmospheric solvers with some AI components, Heuer says. They used the model to create short-term and long-term weather and climate forecasts. To evaluate the accuracy of NeuralGCM, the researchers compared its predictions to actual data and the output of other models, including GCMs and models based purely on machine learning.

Like current machine learning models, NeuralGCM can produce accurate short-term deterministic weather forecasts one to three days ahead while consuming a fraction of the power required by GCMs. But when producing long-term forecasts beyond seven days, it has much fewer errors than other machine learning models. In fact, NeuralGCM's long-term forecasts are similar to those from the European Centre for Medium-Range Weather Forecasts Ensemble Model (ECMWF-ENS), a GCM widely recognized as the gold standard for weather forecasting.

DeepMind AI accurately predicts weather on desktop computers

The research team also tested how accurately the models could predict various weather phenomena, such as tropical cyclones. They found that many of the pure machine learning models produced inconsistent and inaccurate forecasts compared to both NeuralGCM and ECMWF-ENS. The researchers compared NeuralGCM to an ultra-high-resolution climate model known as the Global Storm-Resolving Model. NeuralGCM was able to generate more realistic numbers and tracks of tropical cyclones in a shorter time frame.

Hosking says being able to predict such events is crucial for improving decision-making capabilities and preparation strategies.

Heuer and his colleagues are keen to further improve and adapt NeuralGCM. “We've been working on the atmospheric component of modeling the Earth's system, which is probably the part that most directly affects our daily weather,” Heuer says. In addition, the team hopes to incorporate more aspects of geoscience into future versions to further improve the accuracy of the model.

What Are The Main Benefits Of Comparing Car Insurance Quotes Online

LOS ANGELES, CA / ACCESSWIRE / June 24, 2020, / Compare-autoinsurance.Org has launched a new blog post that presents the main benefits of comparing multiple car insurance quotes. For more info and free online quotes, please visit https://compare-autoinsurance.Org/the-advantages-of-comparing-prices-with-car-insurance-quotes-online/ The modern society has numerous technological advantages. One important advantage is the speed at which information is sent and received. With the help of the internet, the shopping habits of many persons have drastically changed. The car insurance industry hasn't remained untouched by these changes. On the internet, drivers can compare insurance prices and find out which sellers have the best offers. View photos The advantages of comparing online car insurance quotes are the following: Online quotes can be obtained from anywhere and at any time. Unlike physical insurance agencies, websites don't have a specific schedule and they are available at any time. Drivers that have busy working schedules, can compare quotes from anywhere and at any time, even at midnight. Multiple choices. Almost all insurance providers, no matter if they are well-known brands or just local insurers, have an online presence. Online quotes will allow policyholders the chance to discover multiple insurance companies and check their prices. Drivers are no longer required to get quotes from just a few known insurance companies. Also, local and regional insurers can provide lower insurance rates for the same services. Accurate insurance estimates. Online quotes can only be accurate if the customers provide accurate and real info about their car models and driving history. Lying about past driving incidents can make the price estimates to be lower, but when dealing with an insurance company lying to them is useless. Usually, insurance companies will do research about a potential customer before granting him coverage. Online quotes can be sorted easily. Although drivers are recommended to not choose a policy just based on its price, drivers can easily sort quotes by insurance price. Using brokerage websites will allow drivers to get quotes from multiple insurers, thus making the comparison faster and easier. For additional info, money-saving tips, and free car insurance quotes, visit https://compare-autoinsurance.Org/ Compare-autoinsurance.Org is an online provider of life, home, health, and auto insurance quotes. This website is unique because it does not simply stick to one kind of insurance provider, but brings the clients the best deals from many different online insurance carriers. In this way, clients have access to offers from multiple carriers all in one place: this website. On this site, customers have access to quotes for insurance plans from various agencies, such as local or nationwide agencies, brand names insurance companies, etc. "Online quotes can easily help drivers obtain better car insurance deals. All they have to do is to complete an online form with accurate and real info, then compare prices", said Russell Rabichev, Marketing Director of Internet Marketing Company. CONTACT: Company Name: Internet Marketing CompanyPerson for contact Name: Gurgu CPhone Number: (818) 359-3898Email: [email protected]: https://compare-autoinsurance.Org/ SOURCE: Compare-autoinsurance.Org View source version on accesswire.Com:https://www.Accesswire.Com/595055/What-Are-The-Main-Benefits-Of-Comparing-Car-Insurance-Quotes-Online View photos