ERA5

The electron beam of a microscope usually flies through emptiness, like a courier on an empty highway. Any air molecule is a bump that makes it bounce and lose direction. So before, to examine a sample, you had to freeze it, dry it, or coat it with metal—and still you could only look in a vacuum.

Imagine a quiet room where you need to pick out a single melody among many barely audible rustles. That's roughly what it's like to search for signals from extreme systems of two black holes — one huge, the other millions of times smaller.

The quantum world does not forgive forgetfulness. Throw a stone into a pond — the ripples spread and vanish, the information about the impact dissipates without a trace. In quantum mechanics, everything is different: the evolution of a system is reversible, and the past is never completely erased.

Meteorologists have grown used to trusting neural networks: the GraphCast model predicts Earth's weather days ahead by drawing on global snapshots of the atmosphere. But this 'brain' can be transplanted to another planet — where the air is thin and the Sun warms differently.

DNA methylation consists of tiny chemical marks on our genes. Over the years, they change on a fairly strict schedule. Standard epigenetic clocks look at these marks and output a single number: biological age. But a number can't tell you how the pattern of marks rearranged day by day, year by year. The authors of this work decided to turn a static photograph into a continuous film.

For decades, global atmospheric models resembled artists forced to paint planetary storms with coarse brushstrokes: a resolution of 25–100 km forced them to 'guess' convection through approximate schemes, introducing systematic errors in rainfall and climate forecasts.

A student who has spent years solving problems from other people's textbooks suddenly receives three notebooks with real ocean observations. There are few problems, but they have already seen hundreds of similar ones, and now a couple of examples suffice to catch the new teacher's style.

The open archives OpenNeuro and NEMAR hold 791 recordings of the brain's electrical activity from nearly forty thousand people. In total, that's 86,051 hours of signals — roughly ten years of continuous listening. Previously, to take even one such recording off the shelf, you had to write thousands of lines of code: download, unzip, fix format errors, and slice it into chunks of the desired length.

In the Pacific Ocean, there is a warm current that flows eastward against all the others. It is called the North Equatorial Countercurrent, or NECC. In normal years, this band of warm water, a few hundred kilometers wide, quietly carries heat from Indonesia toward the Americas.

Neutrinos are often compared to a radio broadcast picked up by different receivers. One station sends a signal, but antennas in Japan, Antarctica, and at the bottom of the Mediterranean Sea hear it differently — due to distance, interference, and antenna orientation.

In the Atlantic, a giant invisible conveyor operates: warm surface waters flow north, cool, sink, and return south. This circulation, AMOC, carries heat, making Europe noticeably milder than Canada at the same latitudes. But the conveyor isn't eternal: if diluted by fresh water from melting Greenland ice, the engine stalls.

A mosaic of large colored tiles. Each tile is the average precipitation over an entire month for an area the size of a small country. For a general understanding, the picture is fine, but if you need to know whether a downpour hit a specific city yesterday, it's useless.

When a planet passes in front of a star, the light pierces its atmosphere and absorbs the flavor of gases. Each gas leaves its color fingerprint in the light — a bitter or sweet stroke. Scientists try to read this recipe: what substances and in what proportions are mixed in the air of an alien world.

The atmosphere is a chaotic system, and a detailed global forecast requires monstrous computing power. StretchCast sidesteps this by working like the human eye: it creates 'sharp vision' over a selected region with an ultra-fine grid, while seeing the rest of the world blurry, but sharp enough to capture global connections.

Solar flares — sudden energy releases on the Sun — can knock out satellites and power grids. Previous models often either cried wolf or missed a real blow. The fix: attach a reliability estimate to every prediction.

The light of every star is its unique passport, but the entries are written in the language of spectra and colors. For old giants, such documents are almost indistinguishable: their spectra overlap, and deciphering the details by hand was practically impossible.

The weather on the next street can differ from yours: cooler by the river, hotter over asphalt, windier between buildings. A regular forecast misses this: its grid cell is the size of a city, not a backyard.

A student learned physics from a textbook and is taking an exam. The first two problems are solved brilliantly, but on the third, they err on something not covered in the book. That is roughly what the hybrid atmospheric model NeuralGCM faced when run through three levels of testing: cyclones, El Niño, and anomalous warming.

Old Chinese chronicles are full of weather entries: "no rain in the third month," "the river overflowed its banks." But these are words, not numbers. Until now, turning them into precise precipitation data was nearly impossible. The new approach works like a translator from the language of chronicles to the language of climatology.

At the Large Hadron Collider, protons smash into each other like two trucks full of confetti. The debris, dozens of new particles, scatters in all directions. The detector records their tracks, and then the real work begins: piecing together a complete picture of the collision from those tracks. Previously, this was done by a set of rules devised by physicists.

Tuning an old radio receiver requires patience: you slowly turn the dial, catch a crackle, turn it again, until a voice emerges through the static. In much the same way, a reinforcement learning agent searched the ocean for two patches whose temperature difference best predicts rains in Thailand.

An ice core from Antarctica is a time machine that recorded the climate for 130,000 years straight, year after year, with no gaps. Air bubbles trapped in the ice preserve the carbon dioxide of those ancient eras.

Every day, about 40,000 thunderstorms flash across the planet. In that moment, the atmosphere resembles an orchestra without sheet music: warm air rises like a bow stroke, winds aloft carry the melody, and lightning punctuates the finale. But who conducts this orchestra?

An orchestra of a thousand musicians plays in harmony as long as the conductor keeps the tempo. But the moment he changes the score, the violins in one corner start playing louder, while the brass in another come in late.

A bus schedule drifts: if you don't check it, you'll miss your ride. Planets around other stars have the same problem – their crossings of the star's disk gradually shift. The ExoClock project pooled 30,000 observations from Earth and space to refine the schedule for 620 distant worlds. For 45% of the planets, transits were found to be off by hours.

Climate forecasting is like a complex recipe: one wrong pinch and the whole dish is ruined. So it is with clouds — small but decisive. Climate models divide the sky into 50–100 km cells and don't see individual clouds. It's like throwing pepper by the handful when the recipe calls for a pinch.

An orchestra of two musicians plays from the same score, but each hears only their own line. The atmosphere and ocean in a climate model resemble such a duet: they exchange heat and moisture every few hours, yet until recently their neural network counterparts could not keep a common rhythm.

In a room with 80 advisors, each shouts their own opinion, and if you simply listen to everyone and take the average, you get mush. So it is with El Niño forecasts: a model produces 80 possible futures, but not all are equally useful. Some err less often, others more, and still others talk about something else entirely.

A translator at a high-stakes negotiation doesn't just render words quickly; they make sure the meaning doesn't get lost. CAMulator does the same: it takes the complex climate model CAM6 and translates it into the language of a neural network that runs hundreds of times faster, without losing the physical essence.

Two dancers stand facing each other but cannot see each other's faces. One is the atmosphere, fast and noisy, forgetting its moves after just a couple of weeks. The other is the ocean, slow and heavy, remembering every touch for months. For the dance to work, they need to learn to lead each other while only looking at their partner's hands.

A translator at negotiations picks up not only the words but also the tone in which they are spoken. If they focus only on vocabulary, they might miss sarcasm or fatigue in the voice. If only on intonation, they could mistranslate the details of the contract.

A translator at an important negotiation starts by simply repeating words, but gradually begins to anticipate what the counterpart will say. The new weather model works similarly: physics provides the framework, and machine learning learns from errors and fills in the gaps.

In February 2022, the eastern coast of Australia was hit by rains that lasted several days in a row. Water inundated towns in Queensland and New South Wales, insurers paid out 3.35 billion dollars, and the flood became the costliest in the country's history.

Every year, the same drama unfolds over West Africa: from June to September, the sky fills with moisture and releases rains that determine the harvests of millet, sorghum, and maize. This rainy season is driven by the West African monsoon, a giant atmospheric pump that pulls moist air from the ocean deep into the continent.

Seventy-five years of weather observations in India, when plotted on a graph, resemble the cardiogram of a vast organism. Instead of a single steady pulse, there are fifteen different lines, each with its own rhythm. Somewhere the heartbeat is as steady as a sleeping person's, while elsewhere it falters, as if after a quick run.

In the mountains, an echo repeats any shout, and you can't immediately tell who shouted: a person or the wind. That's roughly how climate scientists work when they try to understand why an unusual heat wave or drought happened. They look for a human fingerprint in a weather disaster, but nature has its own voices that can sound similar.

A fisherman in Queensland notices that in some years snapper are harder to catch, even though the nets and boat are the same. The reason hides not in the catch itself but in the water temperature several months earlier, when the fry were just hatching. A warm current arrived not for the whole year but only for a few weeks, and that short episode decided the fate of an entire fish generation.

A meteorologist looks at a map where clouds gather in flocks, like birds before a storm. Each spot on the radar could be a future downpour or just noise. Earth system forecasting is like trying to assemble a puzzle with thousands of pieces that keep changing shape.

In 1960, a meteorologist at a station in Peru records water temperature, while a farmer in India watches the sky waiting for the monsoon. There is no direct link between these two events, but months later one will echo in the other.

A gunner adjusts the eyepiece of a telescope: one more click, and the blurry blob becomes a crisp image. Climate scientists at the Institute of Atmospheric Physics, Chinese Academy of Sciences, made a similar adjustment to their model ICM.