Nav: Home

Deep neural networks speed up weather and climate models

November 12, 2019

When you check the weather forecast in the morning, the results you see are more than likely determined by the Weather Research and Forecasting (WRF) model, a comprehensive model that simulates the evolution of many aspects of the physical world around us. 

"It describes everything you see outside of your window," said Jiali Wang, an environmental scientist at the U.S. Department of Energy's (DOE) Argonne National Laboratory, "from the clouds, to the sun's radiation, to snow to vegetation -- even the way skyscrapers disrupt the wind."

The myriad characteristics and causes of weather and climate are coupled together, communicating with one another. Scientists have yet to fully describe these complex relationships with simple, unified equations. Instead, they approximate the equations using a method called parameterization in which they model the relationships at a scale greater than that of the actual phenomena. 

"Collaboration between the climate scientists and the computer scientists was crucial for the results we achieved. Incorporating our domain knowledge makes the algorithm much more predictive." -- Rao Kotamarthi, chief scientist and department head of atmospheric science and climate research, Environmental Science division

Although parameterizations simplify the physics in a way that allows the models to produce relatively accurate results in a reasonable time, they are still computationally expensive. Environmental scientists and computational scientists from Argonne are collaborating to use deep neural networks, a type of machine learning, to replace the parameterizations of certain physical schemes in the WRF model, significantly reducing simulation time.

"With less-expensive models, we can achieve higher-resolution simulations to predict how short-term and long-term changes in weather patterns affect the local scale," said Wang, "even down to neighborhoods or specific critical infrastructure."

In a recent study, the scientists focused on the planetary boundary layer (PBL), or lowest part of the atmosphere. The PBL is the atmospheric layer that human activity affects the most, and it extends only a few hundred meters above Earth's surface. The dynamics in this layer, such as wind velocity, temperature and humidity profiles, are critical in determining many of the physical processes in the rest of the atmosphere and on Earth.

The PBL is a crucial component in the WRF model, but it is also one of the least computationally expensive. This makes it an excellent testbed for studying how more complicated components might be enhanced by deep learning neural networks in the same way.

"We used 20 years of computer-generated data from the WRF model to train the neural networks and two years of data to evaluate whether they could provide an accurate alternative to the physics-based parameterizations," said Prasanna Balaprakash, a computer scientist and DOE Early Career Award recipient in Argonne's Mathematics and Computer Science division and the Argonne Leadership Computing Facility (ALCF), a DOE Office of Science User Facility. 

Balaprakash developed the neural network and trained it to learn an abstract relationship between the inputs and outputs by feeding it more than 10,000 data points (8 per day) from two locations, one in Kansas and one in Alaska. The result was an algorithm that the scientists are confident could replace the PBL parameterization in the WRF model.

The scientists demonstrated that a deep neural network that considers some of the underlying structure of the relationship between the input and output variables can successfully simulate wind velocities, temperature and water vapor over time. The results also show that a trained neural network from one location can predict behavior across nearby locations with correlations higher than 90 percent compared with the test data.

"Collaboration between the climate scientists and the computer scientists was crucial for the results we achieved," said Rao Kotamarthi, chief scientist and department head of atmospheric science and climate research in Argonne's Environmental Science division. "Incorporating our domain knowledge makes the algorithm much more predictive."

The algorithms -- called domain-aware neural networks -- that consider known relationships not only can predict environmental data more accurately, but they also require training of significantly less data than do algorithms that do not consider domain expertise.

Any machine learning project requires a large amount of high-quality data, and there was no shortage of data for this study. Supercomputing resources at the ALCF and the National Energy Research Scientific Computing Center, a DOE Office of Science User Facility at Lawrence Berkeley National Laboratory, contributed to the production of more than 300 years (700 terabytes) of data describing past, present and future weather and climate in North America.

"This database is unique to climate science at Argonne," said Wang, "and we are using it to conduct further studies in deep learning and determine how it can apply to climate models."

The scientists' ultimate goal is to replace all of the expensive parameterizations in the WRF model with deep learning neural networks to enable faster and higher-resolution simulation.

Currently, the team is working to emulate long-wave and short-wave solar radiation parameterization -- two portions of the WRF model that together take up almost 40% of the calculation time of the physics in the simulations.
-end-
The results of the study were published in a paper titled "Fast domain-aware neural network emulation of a planetary boundary layer parameterization in a numerical weather forecast model" on October 10 in Geoscientific Model Development 12, 4261-4274, 2019.

The work was funded by the DOE Office of Science.

Argonne National Laboratory seeks solutions to pressing national problems in science and technology. The nation's first national laboratory, Argonne conducts leading-edge basic and applied scientific research in virtually every scientific discipline. Argonne researchers work closely with researchers from hundreds of companies, universities, and federal, state and municipal agencies to help them solve their specific problems, advance America's scientific leadership and prepare the nation for a better future. With employees from more than 60 nations, Argonne is managed by UChicago Argonne, LLC for the U.S. Department of Energy's Office of Science.

The U.S. Department of Energy's Office of Science is the single largest supporter of basic research in the physical sciences in the United States and is working to address some of the most pressing challenges of our time. For more information, visit https://energy.gov/science.

DOE/Argonne National Laboratory

Related Climate Articles:

Climate Insights 2020: Climate opinions unchanged by pandemic, but increasingly entrenched
A new survey provides a snapshot of American opinion on climate change as the nation's public health, economy, and social identity are put to the test.
Climate action goes digital
More transparent and accessible to everyone: information and communication technologies bring opportunities for transforming traditional climate diplomacy.
Sub-national 'climate clubs' could offer key to combating climate change
'Climate clubs' offering membership for sub-national states, in addition to just countries, could speed up progress towards a globally harmonized climate change policy, which in turn offers a way to achieve stronger climate policies in all countries.
Review of Chinese atmospheric science research over the past 70 years: Climate and climate change
Over the past 70 years since the foundation of the People's Republic of China, Chinese scientists have made great contributions to various fields in the research of atmospheric sciences, which attracted worldwide attention.
How aerosols affect our climate
Greenhouse gases may get more attention, but aerosols -- from car exhaust to volcanic eruptions -- also have a major impact on the Earth's climate.
Believing in climate change doesn't mean you are preparing for climate change, study finds
Notre Dame researchers found that although coastal homeowners may perceive a worsening of climate change-related hazards, these attitudes are largely unrelated to a homeowner's expectations of actual home damage.
How trees could save the climate
Around 0.9 billion hectares of land worldwide would be suitable for reforestation, which could ultimately capture two thirds of human-made carbon emissions.
Climate undermined by lobbying
For all the evidence that the benefits of reducing greenhouse gases outweigh the costs of regulation, disturbingly few domestic climate change policies have been enacted around the world so far.
Climate education for kids increases climate concerns for parents
A new study from North Carolina State University finds that educating children about climate change increases their parents' concerns about climate change.
Inclusion of a crop model in a climate model to promote climate modeling
A new crop-climate model provides a good tool to investigate the relationship between crop development and climate change for global change studies.
More Climate News and Climate Current Events

Trending Science News

Current Coronavirus (COVID-19) News

Top Science Podcasts

We have hand picked the top science podcasts of 2020.
Now Playing: TED Radio Hour

Listen Again: The Power Of Spaces
How do spaces shape the human experience? In what ways do our rooms, homes, and buildings give us meaning and purpose? This hour, TED speakers explore the power of the spaces we make and inhabit. Guests include architect Michael Murphy, musician David Byrne, artist Es Devlin, and architect Siamak Hariri.
Now Playing: Science for the People

#576 Science Communication in Creative Places
When you think of science communication, you might think of TED talks or museum talks or video talks, or... people giving lectures. It's a lot of people talking. But there's more to sci comm than that. This week host Bethany Brookshire talks to three people who have looked at science communication in places you might not expect it. We'll speak with Mauna Dasari, a graduate student at Notre Dame, about making mammals into a March Madness match. We'll talk with Sarah Garner, director of the Pathologists Assistant Program at Tulane University School of Medicine, who takes pathology instruction out of...
Now Playing: Radiolab

What If?
There's plenty of speculation about what Donald Trump might do in the wake of the election. Would he dispute the results if he loses? Would he simply refuse to leave office, or even try to use the military to maintain control? Last summer, Rosa Brooks got together a team of experts and political operatives from both sides of the aisle to ask a slightly different question. Rather than arguing about whether he'd do those things, they dug into what exactly would happen if he did. Part war game part choose your own adventure, Rosa's Transition Integrity Project doesn't give us any predictions, and it isn't a referendum on Trump. Instead, it's a deeply illuminating stress test on our laws, our institutions, and on the commitment to democracy written into the constitution. This episode was reported by Bethel Habte, with help from Tracie Hunte, and produced by Bethel Habte. Jeremy Bloom provided original music. Support Radiolab by becoming a member today at Radiolab.org/donate.     You can read The Transition Integrity Project's report here.