Can Earth's Digital Twins Help Us Navigate the Climate Crisis?

Nvidia's Earth-2 will use machine learning for greater model resolution

4 min read
A gif of Nvidia's Earth-2 digital earth model showing wind and cloud patterns circling the globe.

Powerful climate models have helped dispel any uncertainty about the scale of the climate crisis the world faces. But these models are large global simulations that can't tell us much about how climate change will impact our daily lives or how to respond at a local level. That's where a digital twin of the Earth could help.

A digital twin is a virtual model of a real-world object, machine, or system that can be used to assess how the real-world counterpart is performing, diagnose or predict faults, or simulate how future changes could alter its behavior. Typically, a digital twin involves both a digital simulation and live sensor data from the real world system to keep the model up to date.

So far, digital twins have primarily been used in industrial contexts. For example, a digital twin could monitor an electric grid or manufacturing equipment. But there's been growing interest in applying similar ideas to the field of climate simulation to provide a more interactive, and detailed, way to track and predict changes in the systems, such as the atmosphere and oceans, that drive the Earth's climate.

Now chipmaker Nvidia has committed to building the world's most powerful supercomputer dedicated to modeling climate change. Speaking at the company's GPU Technology Conference, CEO Jensen Huang said Earth-2 would be used to create a digital twin of Earth in the Omniverse—a virtual collaboration platform that is Nvidia's attempt at a metaverse.

"We may finally have a way to simulate the earth's climate 10, 20, or 30 years from now, predict the regional impact of climate change, and take action to mitigate and adapt before it's too late," said Huang.

The announcement was light on details, and a spokesman for Nvidia said the company was currently unable to confirm what the architecture of the computer would look like or who would have access to it. But in his talk Huang emphasized the significant role the company sees for machine learning to boost the resolution and speed of climate models and create a digital twin of the Earth.

Today, most climate simulation is driven by complex equations that describe the physics behind key processes. Many of these equations are very computationally expensive to solve and so, even on the most powerful supercomputers, models normally only achieve resolutions of 10 to 100 kilometers.

Some important processes, such as the behavior of clouds that reflect the Sun's radiation back to space, operate at scales of just a few meters though, said Huang. He thinks machine learning could help here. Alongside announcing Earth-2, the company also unveiled a new machine learning framework called Modulus designed to help researchers train neural networks to simulate complex physical systems by learning from observed data or the output of physical models.

"The resulting model can emulate physics 1,000 to 100,000 times faster than simulation," said Huang. "With Modulus, scientists will be able to create digital twins to better understand large systems like never before."

Improving the resolution of climate models is a key ingredient for an effective digital twin of Earth, says Bjorn Stevens, director of the Max Planck Institute for Meteorology. Today's climate models currently rely on statistical workarounds that work well for assessing the climate at a global scale, but make it hard to understand local effects. That will be crucial for predicting the regional impacts of climate change so that we can better inform adaptation efforts, he says.

But Steven is skeptical that machine learning is some kind of magic bullet to solve this problem. "There is this fantasy somehow that the machine learning will replace the things that we know how to solve physically, but I think it will always have a disadvantage there."

The key to creating a digital twin is making a system that is highly interactive, he says, and the beauty of a physical model is that it replicates every facet of the process in an explainable way. That's something that a machine learning model trained to mimic the process may not be able to do.

That's not to say there is no place for machine learning, he adds. It is likely to prove useful in helping speeding up workflows, compressing data and potentially developing new models in areas where we have lots of data but little understanding of the physics—for instance how water moves through earth and land. But he thinks the rapid advances in supercomputing power means that running physical models at much higher resolution is more a case of will and resources than capabilities.

The European Union hopes to fill that gap with a new initiative called Destination Earth, which was formally launched in January. The project is a joint effort by the European Space Agency, the European Organisation for the Exploitation of Meteorological Satellites, and the European Centre for Medium-Range Weather Forecasts (ECMWF).

The goal is to create a platform that can bring together a wide variety of models, simulating both key aspects of the climate like the atmosphere and the oceans, but also human systems, says Peter Bauer, deputy director of research at ECMWF. "So you're not only monitoring and simulating precipitation and temperature, but also what that means for agriculture, or water availability, or infrastructure," he says.

The result won't be a single homogeneous simulation of every aspect of Earth, says Bauer, but an interactive platform that allows users to pull in whatever models and data are necessary to answer the questions they're interested in.

The project will be implemented gradually over the coming decade, but the first two digital twins they hope to deliver will include one aimed at anticipating extreme weather events like floods and forest fires, and another aimed at providing longer-term predictions to support climate adaptation and mitigation efforts.

While Nvidia's announcement of a new supercomputer dedicated to climate modeling is welcome, Bauer says the challenge today is more about software engineering than developing new hardware. Most of the critical models have been developed in isolation using very different approaches, so getting them to talk to each other and finding ways to interface highly disparate data streams is an outstanding problem.

"Part of the challenge to actually hide the diversity and complexity of these components away from the user and make them work together," Bauer says.

Correction 24 Nov. 2021: An update was made to the description of machine learning’s utility for digital earths—it could be useful, the story now reads, in understanding how water moves through earth on land (not the mechanics of dirt as the original version of the story stated).

The Conversation (0)

The Inner Beauty of Basic Electronics

Open Circuits showcases the surprising complexity of passive components

5 min read
A photo of a high-stability film resistor with the letters "MIS" in yellow.
All photos by Eric Schlaepfer & Windell H. Oskay

Eric Schlaepfer was trying to fix a broken piece of test equipment when he came across the cause of the problem—a troubled tantalum capacitor. The component had somehow shorted out, and he wanted to know why. So he polished it down for a look inside. He never found the source of the short, but he and his collaborator, Windell H. Oskay, discovered something even better: a breathtaking hidden world inside electronics. What followed were hours and hours of polishing, cleaning, and photography that resulted in Open Circuits: The Inner Beauty of Electronic Components (No Starch Press, 2022), an excerpt of which follows. As the authors write, everything about these components is deliberately designed to meet specific technical needs, but that design leads to “accidental beauty: the emergent aesthetics of things you were never expected to see.”

From a book that spans the wide world of electronics, what we at IEEE Spectrum found surprisingly compelling were the insides of things we don’t spend much time thinking about, passive components. Transistors, LEDs, and other semiconductors may be where the action is, but the simple physics of resistors, capacitors, and inductors have their own sort of splendor.

High-Stability Film Resistor

A photo of a high-stability film resistor with the letters "MIS" in yellow.

All photos by Eric Schlaepfer & Windell H. Oskay

This high-stability film resistor, about 4 millimeters in diameter, is made in much the same way as its inexpensive carbon-film cousin, but with exacting precision. A ceramic rod is coated with a fine layer of resistive film (thin metal, metal oxide, or carbon) and then a perfectly uniform helical groove is machined into the film.

Instead of coating the resistor with an epoxy, it’s hermetically sealed in a lustrous little glass envelope. This makes the resistor more robust, ideal for specialized cases such as precision reference instrumentation, where long-term stability of the resistor is critical. The glass envelope provides better isolation against moisture and other environmental changes than standard coatings like epoxy.

15-Turn Trimmer Potentiometer

A photo of a blue chip
A photo of a blue chip on a circuit board.

It takes 15 rotations of an adjustment screw to move a 15-turn trimmer potentiometer from one end of its resistive range to the other. Circuits that need to be adjusted with fine resolution control use this type of trimmer pot instead of the single-turn variety.

The resistive element in this trimmer is a strip of cermet—a composite of ceramic and metal—silk-screened on a white ceramic substrate. Screen-printed metal links each end of the strip to the connecting wires. It’s a flattened, linear version of the horseshoe-shaped resistive element in single-turn trimmers.

Turning the adjustment screw moves a plastic slider along a track. The wiper is a spring finger, a spring-loaded metal contact, attached to the slider. It makes contact between a metal strip and the selected point on the strip of resistive film.

Ceramic Disc Capacitor

A cutaway of a Ceramic Disc Capacitor
A photo of a Ceramic Disc Capacitor

Capacitors are fundamental electronic components that store energy in the form of static electricity. They’re used in countless ways, including for bulk energy storage, to smooth out electronic signals, and as computer memory cells. The simplest capacitor consists of two parallel metal plates with a gap between them, but capacitors can take many forms so long as there are two conductive surfaces, called electrodes, separated by an insulator.

A ceramic disc capacitor is a low-cost capacitor that is frequently found in appliances and toys. Its insulator is a ceramic disc, and its two parallel plates are extremely thin metal coatings that are evaporated or sputtered onto the disc’s outer surfaces. Connecting wires are attached using solder, and the whole assembly is dipped into a porous coating material that dries hard and protects the capacitor from damage.

Film Capacitor

An image of a cut away of a capacitor
A photo of a green capacitor.

Film capacitors are frequently found in high-quality audio equipment, such as headphone amplifiers, record players, graphic equalizers, and radio tuners. Their key feature is that the dielectric material is a plastic film, such as polyester or polypropylene.

The metal electrodes of this film capacitor are vacuum-deposited on the surfaces of long strips of plastic film. After the leads are attached, the films are rolled up and dipped into an epoxy that binds the assembly together. Then the completed assembly is dipped in a tough outer coating and marked with its value.

Other types of film capacitors are made by stacking flat layers of metallized plastic film, rather than rolling up layers of film.

Dipped Tantalum Capacitor

A photo of a cutaway of a Dipped Tantalum Capacitor

At the core of this capacitor is a porous pellet of tantalum metal. The pellet is made from tantalum powder and sintered, or compressed at a high temperature, into a dense, spongelike solid.

Just like a kitchen sponge, the resulting pellet has a high surface area per unit volume. The pellet is then anodized, creating an insulating oxide layer with an equally high surface area. This process packs a lot of capacitance into a compact device, using spongelike geometry rather than the stacked or rolled layers that most other capacitors use.

The device’s positive terminal, or anode, is connected directly to the tantalum metal. The negative terminal, or cathode, is formed by a thin layer of conductive manganese dioxide coating the pellet.

Axial Inductor

An image of a cutaway of a Axial Inductor
A photo of a collection of cut wires

Inductors are fundamental electronic components that store energy in the form of a magnetic field. They’re used, for example, in some types of power supplies to convert between voltages by alternately storing and releasing energy. This energy-efficient design helps maximize the battery life of cellphones and other portable electronics.

Inductors typically consist of a coil of insulated wire wrapped around a core of magnetic material like iron or ferrite, a ceramic filled with iron oxide. Current flowing around the core produces a magnetic field that acts as a sort of flywheel for current, smoothing out changes in the current as it flows through the inductor.

This axial inductor has a number of turns of varnished copper wire wrapped around a ferrite form and soldered to copper leads on its two ends. It has several layers of protection: a clear varnish over the windings, a light-green coating around the solder joints, and a striking green outer coating to protect the whole component and provide a surface for the colorful stripes that indicate its inductance value.

Power Supply Transformer

A photo of a collection of cut wires
A photo of a yellow element on a circuit board.

This transformer has multiple sets of windings and is used in a power supply to create multiple output AC voltages from a single AC input such as a wall outlet.

The small wires nearer the center are “high impedance” turns of magnet wire. These windings carry a higher voltage but a lower current. They’re protected by several layers of tape, a copper-foil electrostatic shield, and more tape.

The outer “low impedance” windings are made with thicker insulated wire and fewer turns. They handle a lower voltage but a higher current.

All of the windings are wrapped around a black plastic bobbin. Two pieces of ferrite ceramic are bonded together to form the magnetic core at the heart of the transformer.

This article appears in the February 2023 print issue.