

Metaverse
A new way to predict ship-killing rogue waves – Crypto News
Artificial-intelligence (AI) models are modern oracles. The neural networks that power them are flexible mathematical tools, capable of finding any pattern, fitting any shape and drawing any line. They are used to forecast the weather, anticipate road maintenance and diagnose diseases. The problem is, since they train themselves to accomplish those tasks, no one really knows exactly how they do it.
This “black-box problem” makes it hard to rely on such models, especially when, as in health care, they are making high-stakes decisions. It makes them less useful for scientists, too, who are interested not only in predicting an outcome but also in understanding why that outcome happened.
In a paper in Proceedings of the National Academy of Sciences, a group of researchers led by Dion Häfner, a computer scientist at the University of Copenhagen, describe a clever way to make AI more understandable. They have managed to build a neural network, use it to solve a tricky problem, and then capture its insights in a relatively simple five-part equation that human scientists can use and understand.
The researchers were investigating “rogue waves”, those that are much bigger than expected given the sea conditions in which they form. Maritime lore is full of walls of water suddenly swallowing ships. But it took until 1995 for scientists to measure such a wave—a 26-metre monster, amid other waves averaging 12 metres—off the coast of Norway, proving these tales to be tall only in the literal sense.
Scientists have a few ideas about what causes rogue waves, but not a complete picture. Waves can merge and stack, or break in ways that make them unusually big. Currents, the wind and the shape of the sea floor matter too. All those factors mix in chaotic ways, in the mathematical sense of the word: a small change in one can lead to a drastically and unpredictably different outcome.
A good problem, then, for AI to get its teeth into. To produce something a human could follow, the researchers restricted their neural network to around a dozen inputs, each based on ocean-wave maths that scientists had already worked out. Knowing the physical meaning of each input meant the researchers could trace their paths through the network, helping them work out what the computer was up to.
The researchers trained 24 neural networks, each combining the inputs in different ways. They then chose the one that was the most consistent at making accurate predictions in a variety of circumstances, which turned out to rely on only five of the dozen inputs.
To generate a human-comprehensible equation, the researchers used a method inspired by natural selection in biology. They told a separate algorithm to come up with a slew of different equations using those five variables, with the aim of matching the neural network’s output as closely as possible. The best equations were mixed and combined, and the process was repeated. The result, eventually, was an equation that was simple and almost as accurate as the neural network. Both predicted rogue waves better than existing models.
The first part of the equation rediscovered a bit of existing theory: it is an approximation of a well-known equation in wave dynamics. Other parts included some terms that the researchers suspected might be involved in rogue-wave formation but are not in standard models. There were some puzzlers, too: the final bit of the equation includes a term that is inversely proportional to how spread out the energy of the waves is. Current human theories include a second variable that the machine did not replicate. One explanation is that the network was not trained on a wide enough selection of examples. Another is that the machine is right, and the second variable is not actually necessary.
Better methods for predicting rogue waves are certainly useful: some can sink even the biggest ships. But the real prize is the visibility that Dr Häfner’s approach offers into what the neural network was doing. That could give scientists ideas for tweaking their own theories—and should make it easier to know whether to trust the computer’s predictions.
© 2023, The Economist Newspaper Limited. All rights reserved.
From The Economist, published under licence. The original content can be found on www.economist.com
-
Blockchain1 week ago
Change In US Crypto Laws May Affect Charges In Do Kwon’s Criminal Case – Crypto News
-
others1 week ago
Gold retreats while Fed Powell and President Trump clash over interest rates – Crypto News
-
Technology1 week ago
Branded smartwatches under ₹5000 for style and functionality: Top 10 picks for everyday wear – Crypto News
-
Blockchain1 week ago
Best Crypto to Buy as Polymarket Nears $1B Valuation – Crypto News
-
others1 week ago
Tariffs may be adding a quarter of a percentage point to inflation right now – Crypto News
-
Technology1 week ago
Best laptops under ₹40,000 (June 2025) with latest processors, SSD storage, and Windows 11 features, Top 10 picks – Crypto News
-
Technology1 week ago
Top 10 air coolers for monsoon: Handpicked products for effective cooling from trusted brands – Crypto News
-
Cryptocurrency1 week ago
SHIB Price Prediction for June 26 – Crypto News
-
others1 week ago
EUR/JPY steadies near 169.00 as traders await the next catalyst – Crypto News
-
Cryptocurrency6 days ago
Friday charts: Retail is one-upping Wall Street – Crypto News
-
Cryptocurrency1 week ago
Bitcoin rallies to $106K on Mideast ceasefire news; Circle shares continue explosive climb – Crypto News
-
Cryptocurrency1 week ago
What next for XRP after breaking above the $2.15 resistance? – Crypto News
-
Technology1 week ago
US judge rules Anthropic’s use of books for AI training is fair use: All you need to know – Crypto News
-
Blockchain1 week ago
Bitcoin Price Could Rally To $110,000 ATH As These Macroeconomic Factors Align – Crypto News
-
Blockchain1 week ago
Cutting Block Times To Boost Performance – Crypto News
-
others1 week ago
Bank of America, Netflix and Apple Customers Targeted by Widescale Google Search Scams: Report – Crypto News
-
Technology1 week ago
OpenAI and Jony Ive’s AI hardware ambitions hit roadblock over trademark dispute: Report – Crypto News
-
Technology1 week ago
Turkey plans stricter crypto rules to fight money laundering – Crypto News
-
others1 week ago
Winnebago Industries (WGO) tops Q3 earnings estimates – Crypto News
-
Cryptocurrency1 week ago
US Housing Chief Orders Fannie Mae, Freddie Mac to Prepare for Crypto Assessment in Mortgages – Crypto News
-
others7 days ago
AI-Focused Layer-1 Blockchain Altcoin SAHARA Flames Out Following New Binance Listing – Crypto News
-
others6 days ago
USD/INR drops to two-week low as Rupee gains on weak US Dollar – Crypto News
-
Cryptocurrency6 days ago
TRON price forecast as USDT supply surpasses $80 billion – Crypto News
-
others1 week ago
US stocks downplay Iran retaliation concerns as indices edge higher – Crypto News
-
Blockchain1 week ago
Taker Buy Volume Spikes Sharply – Crypto News
-
Cryptocurrency1 week ago
Solana-based StarFun lets projects raise capital with crypto – Crypto News
-
De-fi1 week ago
Synaptogenix Acquires Bittensor’s TAO for AI Crypto Treasury – Crypto News
-
others1 week ago
Right now, we’re in watch and wait mode – Crypto News
-
De-fi1 week ago
Barclays to Ban Crypto Purchases via Credit Card – Crypto News
-
De-fi1 week ago
Sei Soars 70% as Wallet Growth and On-Chain Activity Hit New Highs – Crypto News
-
Technology1 week ago
Too many messages to read? WhatsApp launches AI-enabled summary feature for unread chats. Here’s how it works – Crypto News
-
Blockchain1 week ago
Breakout To $2,800 Or Crash To $2,000? – Crypto News
-
Technology1 week ago
Microsoft launches Mu AI model for smart local tasks on Windows PCs – Crypto News
-
De-fi1 week ago
Russia’s Central Bank Pushes CBDC Launch to 2026 – Crypto News
-
Cryptocurrency1 week ago
Wormhole price jumps 12% amid Ripple’s XRPL integration – Crypto News
-
De-fi7 days ago
U.S Judge Denies Ripple-SEC Request to Lift Injunction and Reduce $125 Million Fine – Crypto News
-
Cryptocurrency7 days ago
Vodafone Share Price Tests 78p Ahead of July Earnings, Is a Breakout Imminent? – Crypto News
-
others1 week ago
Bitcoin (BTC) and Ethereum (ETH) Lead $1,240,000,000 of Inflows to Crypto Products Despite Geopolitical Tensions: CoinShares – Crypto News
-
others1 week ago
German IFO Business Climate Index rises further to 88.4 in June vs. 88.3 expected – Crypto News
-
others1 week ago
Jerome Powell testifies Fed is well-positioned to wait to learn more about economy – Crypto News
-
Blockchain1 week ago
Aptos and Jump Crypto Launch Shelby, a Web3 Cloud Storage Platform – Crypto News
-
De-fi1 week ago
Dragonfly-Backed Codex Launches Blockchain for Stablecoins with Native USDC Support – Crypto News
-
Technology1 week ago
US judge rules Anthropic’s use of books for AI training is fair use: All you need to know – Crypto News
-
others1 week ago
United States 2-Year Note Auction fell from previous 3.955% to 3.786% – Crypto News
-
Blockchain1 week ago
Many Senators Absent From ‘Bipartisan’ Crypto Market Structure Hearing – Crypto News
-
Blockchain1 week ago
Bunker Buster: Ethereum Titans Stake $100 Million Amid US-Iran Hostilities – Crypto News
-
others1 week ago
Australian Dollar advances as US Dollar struggles following Israel-Iran ceasefire – Crypto News
-
Cryptocurrency1 week ago
BTC holds $106K; analysts point to institutional integration, on-chain innovation – Crypto News
-
Cryptocurrency1 week ago
XRP crashes 12.5% in TVL, ETF delay and war fears trigger selloff – Crypto News
-
others1 week ago
Employee at Billion Dollar Bank Embezzles $44,000 From Customer Accounts Before Being Banned From Industry – Crypto News