Can Deep Learning Replace Numerical Weather Prediction?

By Oliver Peckham

March 3, 2021

Numerical weather prediction (NWP) is a mainstay of supercomputing. Some of the first applications of the first supercomputers dealt with climate modeling, and even to this day, the largest climate models are heavily constrained by the scale of the supercomputers that run them. While some wait for the exascale era – and beyond – to brute force punishingly accurate and complex climate models into existence, others are looking for a deep learning-powered shortcut to the same results. In a paper for Philosophical Transactions of the Royal Society, eight researchers from the Jülich Supercomputing Center explored whether deep learning could ever actually beat numerical weather prediction at its own game – and if so, how and when that might happen.

Status quo

The weather and climate supercomputing community is no stranger to deep learning, but it has hitherto mostly been used to augment NWP approaches (e.g. in resolving post-processing issues). These modelers, however, are reticent to incorporate deep learning in more meaningful capacities.

“[There] are still reservations about DL in this community,” the authors write. “Two core arguments in this regard are the lack of explainability of deep [neural networks] and the lack of physical constraints. Furthermore, some scepticism prevails due to the fact that researchers have experimented with rather simple [neural networks] which were clearly unsuited to capture the complexity of meteorological data and feedback processes, but then extrapolate these results to discredit any [neural network] application including the much more powerful [deep learning] systems.”

While the  paper explores whether deep learning could eventually replace significant elements of a major NWP model, it’s perhaps more interested in whether deep learning could replace the whole thing.

That bar, of course, is extraordinarily high.

“Over the past decades, the ability of NWP models to predict the future atmospheric state has continuously improved,” the paper reads. “Contemporary global NWP models are not only able to predict the synoptic-scale weather pattern for several days, but they have also reached remarkable accuracy in forecasting end-user relevant meteorological quantities such as the 2m temperature and regional-scale precipitation events.”

But deep learning hasn’t been standing still, either – far from it. Steep increases in available computational power also benefit deep learning applications, which are also boosted by increased data availability and a rapidly expanding library of neural network architectures. 

Comparison of NWP, deep learning, and hybrid workflows for NWP. Image courtesy of the authors.

In fact, some researchers have already carried out NWP-mimicking deep learning tests – but, the authors note, these studies have been extremely limited in scope, focusing on forecasting by up to a day. 

Learning curves

The authors suggest that any eventual deep learning replacement for an NWP would likely consist of several neural networks trained on subsets of forecast products, allowing deep learning techniques to excel by focusing on specific tasks. Key to this approach, they say, is understanding the distributions of meteorological and climatological variables, which can be both complex and crucial: by way of example, they discuss sea ice, which might change very little over the course of a typical forecast, but which produces profound effects in the medium- to long-term.

Challenges facing deep learning as it tackles weather prediction. Image courtesy of the authors.

A number of challenges face deep learning as it climbs toward NWP. For instance, rare extreme weather events are difficult in terms of training and testing, though the authors report some success across various studies in accounting for this gap. Data availability is another problem: NWP typically uses satellite data where missing values are interpolated, but using such filled-in data with deep learning models poses a serious risk of concept drift, where an assumption made early on leads to cascading built-in biases.

Indeed, the authors say that with respect to data preparation generally, “best practices differ between the meteorological and ML communities.” Machine learning development, they explain, typically involves three datasets: a training dataset, a validation dataset and a test dataset, all of which should be independent from one another. But there’s a problem here, at least for weather prediction: the data is auto-correlated, meaning the datasets aren’t truly independent. 

Furthermore, neural networks, the authors say, may need to be directly taught the relationships between certain variables, as short- to medium-term datasets are unlikely to teach a model to understand longer-term variations like El Nino or climate change. This need for intervention extends to limiting factors, as well: deep learning models might be inspired to produce physically impossible forecasts or establish scientifically unsound correlation-causation links. The authors say that some studies have introduced such physical restraints to general success.

“It may be useful to reflect on the potential and necessity of physically constraining [deep learning] models from an abstract point of view,” they add. “In spite of their complexity and dimensionality, [deep learning] models still adhere to the fundamental principles of (data-driven) statistical modelling. This implies that there must be some rules in place to constrain the future, because otherwise extrapolation will be unbound.”

Finally, the authors touch on uncertainty estimation. Ensemble models, which use a series of runs to estimate the relative likelihood of various outcomes, have become more or less the norm in top-of-the-line NWP. However, ensemble approaches introduce exorbitant computational costs for deep learning models. The authors discuss Bayesian deep learning as a reasonable alternative, noting that it has already been tested for weather forecasting applications.

Prognostication

So: where is deep learning-powered weather prediction heading?

“We expect that the field of ML in weather and climate science will grow rapidly in the coming years as more and more sophisticated ML architectures are becoming available and can easily be deployed on modern computer systems,” the authors write. “We [also] expect that the success of [deep learning] weather forecast applications will hinge on the consideration of physical constraints in the [neural network] design. Taken to the extreme, portions or variants of current numerical models could eventually end up as regulators in the latent space of deep neural weather forecasting networks.”

“So, to answer the question posed in the title of this article,” they conclude, “we can only say that there might be potential for end-to-end [deep learning] weather forecast applications to produce equal or better quality forecasts for specific end-user demands, especially if these systems can exploit small-scale patterns in the observational data which are not resolved in the traditional NWP model chain.”

“Whether [deep learning] will evolve enough to replace most or all of the current NWP systems cannot be answered at this point.”

About the research

The paper discussed in this article, “Can deep learning beat numerical weather prediction?“, was published in the February 2021 issue of Philosophical Transactions of the Royal Society. The paper was written by M. G. Schultz, C. Betancourt, B. Gong, F. Kleinert, M. Langguth, L. H. Leufen, A. Mozaffari and S. Stadtler, all of the Jülich Supercomputing Center in Germany.

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

Organizations Partner to Rescue Petabytes of Data from the Arecibo Observatory

April 21, 2021

The Arecibo Observatory in Puerto Rico stood as the world’s largest single-aperture telescope for more than half a century, its grandiosity earning it a turn as a major filming location in the James Bond movie GoldenEy Read more…

MLPerf Issues New Inferencing Results, Adds Power Metrics, Nvidia Wins (Again)

April 21, 2021

MLPerf.org, the young ML benchmarking organization, today issued its third round of inferencing results (MLPerf Inference v1.0) intended to compare how well various systems and accelerators perform inferencing on a suite Read more…

Cerebras Doubles AI Performance with Second-Gen 7nm Wafer Scale Engine

April 20, 2021

Nearly two years since its massive 1.2 trillion transistor Wafer Scale Engine chip debuted at Hot Chips, Cerebras Systems is announcing its second-generation technology (WSE-2), which its says packs twice the performance Read more…

The New Scalability

April 20, 2021

HPC is all about scalability. The most powerful systems. The biggest data sets. The most cores, the most bytes, the most flops, the most bandwidth. HPC scales! Notwithstanding a few recurring arguments over the last twenty years about scaling up versus scaling out, the definition of scalability... Read more…

Supercomputer-Powered Climate Model Makes Startling Sea Level Rise Prediction

April 19, 2021

The climate science community is tasked with striking a difficult balance: inspiring precisely the amount of alarm commensurate to the climate crisis. Make estimates that are too conservative, and the public might not re Read more…

AWS Solution Channel

Research computing with RONIN on AWS

To allow more visibility into and management of Amazon Web Services (AWS) resources and expenses and minimize the cloud skills training required to operate these resources, AWS Partner RONIN created the RONIN research computing platform. Read more…

San Diego Supercomputer Center Opens ‘Expanse’ to Industry Users

April 15, 2021

When San Diego Supercomputer Center (SDSC) at the University of California San Diego was getting ready to deploy its flagship Expanse supercomputer for the large research community it supports, it also sought to optimize Read more…

MLPerf Issues New Inferencing Results, Adds Power Metrics, Nvidia Wins (Again)

April 21, 2021

MLPerf.org, the young ML benchmarking organization, today issued its third round of inferencing results (MLPerf Inference v1.0) intended to compare how well var Read more…

Cerebras Doubles AI Performance with Second-Gen 7nm Wafer Scale Engine

April 20, 2021

Nearly two years since its massive 1.2 trillion transistor Wafer Scale Engine chip debuted at Hot Chips, Cerebras Systems is announcing its second-generation te Read more…

The New Scalability

April 20, 2021

HPC is all about scalability. The most powerful systems. The biggest data sets. The most cores, the most bytes, the most flops, the most bandwidth. HPC scales! Notwithstanding a few recurring arguments over the last twenty years about scaling up versus scaling out, the definition of scalability... Read more…

San Diego Supercomputer Center Opens ‘Expanse’ to Industry Users

April 15, 2021

When San Diego Supercomputer Center (SDSC) at the University of California San Diego was getting ready to deploy its flagship Expanse supercomputer for the larg Read more…

GTC21: Dell Building Cloud Native Supercomputers at U Cambridge and Durham

April 14, 2021

In conjunction with GTC21, Dell Technologies today announced new supercomputers at universities across DiRAC (Distributed Research utilizing Advanced Computing) in the UK with plans to explore use of Nvidia BlueField DPU technology. The University of Cambridge will expand... Read more…

The Role and Potential of CPUs in Deep Learning

April 14, 2021

Deep learning (DL) applications have unique architectural characteristics and efficiency requirements. Hence, the choice of computing system has a profound impa Read more…

GTC21: Nvidia Launches cuQuantum; Dips a Toe in Quantum Computing

April 13, 2021

Yesterday Nvidia officially dipped a toe into quantum computing with the launch of cuQuantum SDK, a development platform for simulating quantum circuits on GPU-accelerated systems. As Nvidia CEO Jensen Huang emphasized in his keynote, Nvidia doesn’t plan to build... Read more…

Nvidia Aims Clara Healthcare at Drug Discovery, Imaging via DGX

April 12, 2021

Nvidia Corp. continues to expand its Clara healthcare platform with the addition of computational drug discovery and medical imaging tools based on its DGX A100 platform, related InfiniBand networking and its AGX developer kit. The Clara partnerships announced during... Read more…

Julia Update: Adoption Keeps Climbing; Is It a Python Challenger?

January 13, 2021

The rapid adoption of Julia, the open source, high level programing language with roots at MIT, shows no sign of slowing according to data from Julialang.org. I Read more…

Intel Launches 10nm ‘Ice Lake’ Datacenter CPU with Up to 40 Cores

April 6, 2021

The wait is over. Today Intel officially launched its 10nm datacenter CPU, the third-generation Intel Xeon Scalable processor, codenamed Ice Lake. With up to 40 Read more…

CERN Is Betting Big on Exascale

April 1, 2021

The European Organization for Nuclear Research (CERN) involves 23 countries, 15,000 researchers, billions of dollars a year, and the biggest machine in the worl Read more…

Programming the Soon-to-Be World’s Fastest Supercomputer, Frontier

January 5, 2021

What’s it like designing an app for the world’s fastest supercomputer, set to come online in the United States in 2021? The University of Delaware’s Sunita Chandrasekaran is leading an elite international team in just that task. Chandrasekaran, assistant professor of computer and information sciences, recently was named... Read more…

HPE Launches Storage Line Loaded with IBM’s Spectrum Scale File System

April 6, 2021

HPE today launched a new family of storage solutions bundled with IBM’s Spectrum Scale Erasure Code Edition parallel file system (description below) and featu Read more…

10nm, 7nm, 5nm…. Should the Chip Nanometer Metric Be Replaced?

June 1, 2020

The biggest cool factor in server chips is the nanometer. AMD beating Intel to a CPU built on a 7nm process node* – with 5nm and 3nm on the way – has been i Read more…

Saudi Aramco Unveils Dammam 7, Its New Top Ten Supercomputer

January 21, 2021

By revenue, oil and gas giant Saudi Aramco is one of the largest companies in the world, and it has historically employed commensurate amounts of supercomputing Read more…

Quantum Computer Start-up IonQ Plans IPO via SPAC

March 8, 2021

IonQ, a Maryland-based quantum computing start-up working with ion trap technology, plans to go public via a Special Purpose Acquisition Company (SPAC) merger a Read more…

Leading Solution Providers

Contributors

Can Deep Learning Replace Numerical Weather Prediction?

March 3, 2021

Numerical weather prediction (NWP) is a mainstay of supercomputing. Some of the first applications of the first supercomputers dealt with climate modeling, and Read more…

Livermore’s El Capitan Supercomputer to Debut HPE ‘Rabbit’ Near Node Local Storage

February 18, 2021

A near node local storage innovation called Rabbit factored heavily into Lawrence Livermore National Laboratory’s decision to select Cray’s proposal for its CORAL-2 machine, the lab’s first exascale-class supercomputer, El Capitan. Details of this new storage technology were revealed... Read more…

New Deep Learning Algorithm Solves Rubik’s Cube

July 25, 2018

Solving (and attempting to solve) Rubik’s Cube has delighted millions of puzzle lovers since 1974 when the cube was invented by Hungarian sculptor and archite Read more…

African Supercomputing Center Inaugurates ‘Toubkal,’ Most Powerful Supercomputer on the Continent

February 25, 2021

Historically, Africa hasn’t exactly been synonymous with supercomputing. There are only a handful of supercomputers on the continent, with few ranking on the Read more…

AMD Launches Epyc ‘Milan’ with 19 SKUs for HPC, Enterprise and Hyperscale

March 15, 2021

At a virtual launch event held today (Monday), AMD revealed its third-generation Epyc “Milan” CPU lineup: a set of 19 SKUs -- including the flagship 64-core, 280-watt 7763 part --  aimed at HPC, enterprise and cloud workloads. Notably, the third-gen Epyc Milan chips achieve 19 percent... Read more…

The History of Supercomputing vs. COVID-19

March 9, 2021

The COVID-19 pandemic poses a greater challenge to the high-performance computing community than any before. HPCwire's coverage of the supercomputing response t Read more…

HPE Names Justin Hotard New HPC Chief as Pete Ungaro Departs

March 2, 2021

HPE CEO Antonio Neri announced today (March 2, 2021) the appointment of Justin Hotard as general manager of HPC, mission critical solutions and labs, effective Read more…

GTC21: Nvidia Launches cuQuantum; Dips a Toe in Quantum Computing

April 13, 2021

Yesterday Nvidia officially dipped a toe into quantum computing with the launch of cuQuantum SDK, a development platform for simulating quantum circuits on GPU-accelerated systems. As Nvidia CEO Jensen Huang emphasized in his keynote, Nvidia doesn’t plan to build... Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire