
AI built for speech is now decoding the language of earthquakes.
A team of researchers from the Earth and environmental sciences division at Los Alamos National Laboratory repurposed Meta's Wav2Vec-2.0, an AI model designed for speech recognition, to analyze seismic signals from Hawaii's 2018 K lauea volcano collapse.
Their findings, published in Nature Communications, suggest that faults emit distinct signals as they shift - patterns that AI can now track in real time. While this doesn't mean AI can predict earthquakes, the study marks an important step toward understanding how faults behave before a slip event.
Seismic records are acoustic measurements of waves passing through the solid Earth, said Christopher Johnson, one of the study's lead researchers. From a signal processing perspective, many similar techniques are applied for both audio and seismic waveform analysis.
The AI model was tested using data from the 2018 collapse of Hawaii's K lauea caldera, which triggered months of earthquakes and reshaped the volcanic landscape. The lava lake in Halema uma u during the 2020-2021 eruption (USGS/F. Trusdell) is a striking reminder of K lauea's ongoing activity. Big earthquakes don't just shake the ground - they upend economies. In the past five years, quakes in Japan, Turkey and California have caused tens of billions of dollars in damage and displaced millions of people.
That's where AI comes in. Led by Johnson, along with Kun Wang and Paul Johnson, the Los Alamos team tested whether speech-recognition AI could make sense of fault movements - deciphering the tremors like words in a sentence.
To test their approach, the team used data from the dramatic 2018 collapse of Hawaii's K lauea caldera, which triggered a series of earthquakes over three months.
The AI analyzed seismic waveforms and mapped them to real-time ground movement, revealing that faults might speak in patterns resembling human speech.
Speech recognition models like Wav2Vec-2.0 are well-suited for this task because they excel at identifying complex, time-series data patterns - whether involving human speech or the Earth's tremors.
The AI model outperformed traditional methods, such as gradient-boosted trees, which struggle with the unpredictable nature of seismic signals. Gradient-boosted trees build multiple decision trees in sequence, refining predictions by correcting previous errors at each step.
However, these models struggle with highly variable, continuous signals like seismic waveforms. In contrast, deep learning models like Wav2Vec-2.0 excel at identifying underlying patterns.
How AI Was Trained to Listen to the Earth Unlike previous machine learning models that required manually labeled training data, the researchers used a self-supervised learning approach to train Wav2Vec-2.0. The model was pretrained on continuous seismic waveforms and then fine-tuned using real-world data from K lauea's collapse sequence.
NVIDIA accelerated computing played a crucial role in processing vast amounts of seismic waveform data in parallel. High-performance NVIDIA GPUs accelerated training, enabling the AI to efficiently extract meaningful patterns from continuous seismic signals.
What's Still Missing: Can AI Predict Earthquakes? While the AI showed promise in tracking real-time fault shifts, it was less effective at forecasting future displacement. Attempts to train the model for near-future predictions - essentially, asking it to anticipate a slip event before it happens - yielded inconclusive results.
We need to expand the training data to include continuous data from other seismic networks that contain more variations in naturally occurring and anthropogenic signals, he explained.
A Step Toward Smarter Seismic Monitoring Despite the challenges in forecasting, the results mark an intriguing advancement in earthquake research. This study suggests that AI models designed for speech recognition may be uniquely suited to interpreting the intricate, shifting signals faults generate over time.
This research, as applied to tectonic fault systems, is still in its infancy, Johnson. The study is more analogous to data from laboratory experiments than large earthquake fault zones, which have much longer recurrence intervals. Extending these efforts to real-world forecasting will require further model development with physics-based constraints.
So, no, speech-based AI models aren't predicting earthquakes yet. But this research suggests they could one day - if scientists can teach it to listen more carefully.
Read the full paper, Automatic Speech Recognition Predicts Contemporaneous Earthquake Fault Displacement, to dive deeper into the science behind this groundbreaking research.
Most recent headlines
05/01/2027
Worlds first 802.15.4ab-UWB chip verified by Calterah and Rohde & Schwarz to be ...
07/10/2026
Dalet, a leading technology and service provider for media-rich organizations, today announced the latest Long-Term Supported (LTS) release of Dalet Flex. Build...
06/09/2026
June 9 2026, 23:00 (PDT) Dolby and MagentaTV Bring Fans Closer to the FIFA Worl...
21/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
21/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
21/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
21/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
21/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
21/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
21/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
21/08/2026
When hundreds of thousands of people gather to hear a single voice, there is no room for compromise. Every word must be delivered clearly, every wireless transm...
21/08/2026
Telestream, a global leader in media workflow technologies, today announced a strategic partnership with ScorePlay, the AI-powered media infrastructure that spo...
21/08/2026
NUGEN Audio announces the launch of its new Post Plan and Producer Plan, two flexible subscription offerings designed to give audio professionals short term acc...
21/08/2026
Join the Screen Currency 2026 Ask Me Anything (AMA) Online 20 August 2026
(L-R): Adrian Coates, Grainne Brunsdon, Deirdre Brennan, Rachael Perkins
Got questio...
20/08/2026
From host-broadcaster and rightsholder support in June and July to MLS, NWSL, US...
20/08/2026
In-venue and creative video staffers at the professional and collegiate level ha...
20/08/2026
At IBC this year, Veritone (14.A56) is bringing two connected themes to the booth: architectural independence in enterprise AI, and the automation of the media ...
20/08/2026
Telestream and ScorePlay have announced a partnership combining Telestream's...
20/08/2026
The Grand Slam of Curling and Rock League have announced a three-year agreement with ESPN, bringing more than 300 hours of live curling coverage to U.S. audienc...
20/08/2026
Nielsen has announced a series of enhancements to its Big Data + Panel currency measurement methodology, taking effect August 31. The updates were developed in ...
20/08/2026
Net Insight has been selected by service provider Big Blue Marble (formerly ORS Group) to provide its Nimbra platform as the core media transport solution for a...
20/08/2026
The 2026 US Open will bring a series of free fan activations across New York City ahead of and during the tournament, which runs August 23-September 13.
We...
20/08/2026
Bridge Technologies will announce a transport stream (TS) playout feature for its VB330 and VB220 compressed monitoring probes at IBC2026 (Booth 1.A71).
The fe...
20/08/2026
ENCO will demonstrate solutions across captioning, translation, AI production tools, automation, and virtual production at IBC2026 (Stand 7.A34, Amsterdam RAI, ...
20/08/2026
MultiDyne Video and Fiber Optic Systems will demonstrate camera robotics and mot...
20/08/2026
Chyron will demonstrate news workflow solutions at IBC2026 (Stand 7.A23), marking the company's 60th anniversary. Highlights include updates to PRIME HTML, ...
20/08/2026
Spectrum SportsNet LA, the exclusive television home of the Los Angeles Dodgers, is now available to Spectrum customers in former Cox markets following the clos...
20/08/2026
swXtch.io will unveil expanded Global SRT Distribution and native multicast tran...
20/08/2026
Riedel Communications has announced that Transformation Church in the United States has deployed a communications system built around the Artist intercom ecosys...
20/08/2026
The bestselling author and longtime Apple observer explores how product launches...
20/08/2026
The Orlando Magic entered last season with a dramatically upgraded in-venue prod...
20/08/2026
Pacers Sports and Entertainment has announced a partnership with DAZN, making it the exclusive streaming home of Indiana Pacers basketball. A team-branded strea...
20/08/2026
Ratings Roundup is a rundown of recent ratings news and is derived from press re...
20/08/2026
The NHL has announced two major developments tied to its Germany growth strategy...
20/08/2026
Set up your own private remote collaboration infrastructure
SoundBridge have recently put together a tutorial video that provides users with a step-by-step ...
20/08/2026
New V-Control Pro features restore basic functionality
Neyrinck's V-Control software has long been keeping older Avid control surfaces compatible with n...
20/08/2026
TV, BritBox and Mammoth Screen have announced that filming is now underway on th...
20/08/2026
New York August 19, 2026 Nielsen today shared a number of key enhancements t...
20/08/2026
New Gracenote Data Hub analysis finds sports program titles up 31.2% and individ...
20/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
20/08/2026
At IBC, Profuz Digital will showcase at stand 8.A88 the SubtitleNEXT platform delivering innovative AI transcription integrations and stunning new features boos...
20/08/2026
Riedel Communications today announced that Transformation Church, one of the fastest-growing and most influential digital ministries in the United States, has d...
20/08/2026
QuickLink Showcases New 4K Capabilities Across StudioEdge and StudioCall at IBC ...
20/08/2026
The Boys Season Five Graded with DaVinci Resolve Studio
Brie Clayton August 20, 2026
0 Comments
Colorist Siggy Ferstl uses Depth Map to bring a three ...
20/08/2026
Adobe Firefly expands its creative AI studio: generate music, speech, and sound ...
20/08/2026
Multiview available via SaaS for streaming platforms and operators through broadpeak.io, with live demonstrations at IBC2026
Broadpeak , a leader in streaming ...
20/08/2026
Techex, a leading provider of live broadcast infrastructure solutions, has appointed Stuart Almond as Chief Revenue Officer, further strengthening its executive...
20/08/2026
Avid today announced that MediaCity Studios has upgraded its production infrastructure with an enhanced end-to-end Avid production ecosystem, including the dep...
20/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
20/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...