Sony Pixel Power calrec Sony

When the Earth Talks, AI Listens

06/02/2025

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.
LINK: https://blogs.nvidia.com/blog/earth-ai/...
See more stories from nvidia

Most recent headlines

05/01/2027

Worlds first 802.15.4ab-UWB chip verified by Calterah and Rohde & Schwarz to be demoed at CES 2026

Worlds first 802.15.4ab-UWB chip verified by Calterah and Rohde & Schwarz to be ...

04/08/2026

Dalet Announces Commercial Availability of Dalia, Bringing Media-Aware Agentic AI to Enterprise Productions

Dalet, a leading technology and service provider for media-rich organizations, t...

04/07/2026

Detective Conan: Fallen Angel of the Highway Opens in Dolby Cinemas Across Japan, Presented in Dolby Atmos and Dolby ...

April 7 2026, 19:00 (PDT) Detective Conan: Fallen Angel of the Highway Opens in...

01/06/2026

Dolby Sets the New Standard for Premium Entertainment at CES 2026

January 6 2026, 05:30 (PST) Dolby Sets the New Standard for Premium Entertainment at CES 2026 Throughout the week, Dolby brings to life the latest innovatio...

02/05/2026

Dalet Flex LTS Delivers Smarter Search, Faster Editing, and an AI-Ready Foundation for Modern Media

Dalet, a leading technology and service provider for media-rich organizations, t...

01/05/2026

NBCUniversal's Peacock to Be First Streamer to Integrate Dolby's Full Suite of Premium Picture and Sound Innovations

January 5 2026, 18:30 (PST) NBCUniversal's Peacock to Be First Streamer to ...

13/04/2026

ToolsOnAir Composition Builder 2026 Boilerplate

ToolsOnAir Composition Builder 2026 Boilerplate More Details: The Composition Builder 2026 application for macOS enables TV stations and Live Event broadcast...

13/04/2026

ToolsOnAr just:live pro 2026 Boilerplate

ToolsOnAr just:live pro 2026 Boilerplate More Details: just:live pro 2026 is a Multi-Channel Live Production Playout solution for video and static or real-ti...

13/04/2026

ToolsOnAr just:play pro 2026 Boilerplate

ToolsOnAr just:play pro 2026 Boilerplate More Details: just:play pro 2026 is a Multi-Channel automated 24/7 Master Control playout solution with SD, HD and U...

13/04/2026

ToolsOnAr live:cut 2026 Boilerplate

ToolsOnAr live:cut 2026 Boilerplate More Details: live:cut is an option to just:in mac pro 2025 and enables multicamera production workflows for up to 16 cam...

13/04/2026

ToolsOnAir Just In Mac Lite NDI 2026 Boilerplate

ToolsOnAir Just In Mac Lite NDI 2026 Boilerplate More Details: The Just In Mac Lite NDI application is a streamlined media capture solution designed specific...

13/04/2026

ToolsOnAir Just In Mac Lite 2026 Boilerplate

ToolsOnAir Just In Mac Lite 2026 Boilerplate More Details: The Just In Mac Lite application is a streamlined media capture solution designed specifically for...

13/04/2026

ToolsOnAir just:in mac pro 2026 Boilerplate

ToolsOnAir just:in mac pro 2026 Boilerplate More Details: just:in mac pro is a macOS-based client-server multichannel capture solution to record SDI, HDMI, N...

13/04/2026

Jnger Audio Joins EBU ADM Implementers Group as Founding Member

Telos Alliance has announced that J nger Audio has joined the EBU ADM Implementers Group (ADM-IG) as a founding member. The group is focused on advancing ADM an...

13/04/2026

NAB 2026: Grass Valley to Showcase Alliance Partner Ecosystem

Grass Valley will demonstrate its Alliance Partner ecosystem at NAB Show 2026 (Booth C2408, Central Hall, April 19-22), showing AMPP integrations across live pr...

13/04/2026

NAB 2026: Media Links to Demonstrate IP Transport Solutions

Media Links will exhibit at NAB Show 2026 (Booth W2033), demonstrating IP transport solutions for live production including hitless protection technology, Xscen...

13/04/2026

NBC Sports Partners with Overtime for OT7 Football League and Navy All-American Bowl

NBC Sports has announced a programming, distribution, and sales partnership with...

13/04/2026

FloSports Promotes Jayar Donlan from COO to President

FloSports has promoted Chief Operating Officer Jayar Donlan to President, effective immediately. In his new role, Donlan will lead the company's commercial,...

13/04/2026

MASV Case Study: PanCam Pictures Uses MASV for Remote Post-Production at Senior Bowl 2026

PanCam Pictures, the documentary production company founded by Paul Camarata, us...

13/04/2026

NAB 2026: Mimir to Showcase Cloud Production Platform

Mimir will exhibit at NAB Show 2026 (North Hall, Booth N2850), demonstrating its cloud-native media production platform with new capabilities including Mimir Cu...

13/04/2026

NAB 2026: BBright Adds RIST Protocol Support to IP Gateway

BBright has announced that its IP Gateway now supports the Reliable Internet Stream Transport (RIST) protocol. The addition will be introduced at NAB Show 2026 ...

13/04/2026

Net Insight Awarded ESA NAVISP Development Project for PNT Technology

Net Insight has been awarded a development project through the European Space Agency's Navigation Innovation and Support Program (NAVISP), with co-funding f...

13/04/2026

NAB 2026: intoPIX to Showcase JPEG XS, IPMX, and SMPTE 2110 Solutions

intoPIX will exhibit at NAB Show 2026, marking the company's 20th anniversary. The company will demonstrate its JPEG XS compression portfolio and IPMX-appro...

13/04/2026

Inside the Launch of BravesVision: How Braves, Raycom Sports Pulled Off One of the Most Ambitious Efforts in Regional-Sports-Media History

Starting from scratch, the team built an in-house content platform comprising ga...

13/04/2026

NAB 2026: AI Will Make Its Presence Felt in Audio Offerings, Presentations

Here's a look at some of the new products and updates, along with audio-centric conferences, that attendees will find next week at the show When the 2026 N...

13/04/2026

NAB 2026: Avid to Demonstrate Integrated Newsroom Capabilities

Avid will launch new integrated newsroom capabilities for Avid for News at NAB Show 2026 (Booth N2226, April 18-22), demonstrating how Avid Content Core connect...

13/04/2026

NAB 2026: Synamedia Launches Cloud-Controlled Edge Playout Version of Quortex PowerVu

Synamedia has announced a new version of Quortex PowerVu, an IP-native, software...

13/04/2026

NAB 2026: Mediaproxy Adds AI Brand and Advertisement Tracking to LogServer

Mediaproxy has developed a suite of AI-powered tools for brand and advertisement tracking, integrated into its LogServer compliance logging and analysis platfor...

13/04/2026

NAB 2026: Disguise to Demonstrate Media Server and Software Integrations

Disguise will demonstrate its media servers and software at NAB Show 2026, appearing across five partner booths in Central Hall: MRMC, B&H, Planar, CarbonBlack,...

13/04/2026

NAB 2026: OpenDrives Introduces Edge Hybrid Cloud-Edge Performance Accelerator

OpenDrives is introducing OpenDrives Edge at NAB Show 2026, a hybrid cloud-edge performance accelerator for distributed video and rich media workflows. The prod...

13/04/2026

ESPN Returns to The Shed for 2026 WNBA Draft, Expanding Camera Arsenal and Deepening Fan Coverage

The show will deploy 18 cameras across two sets and the draft floor, including a...

13/04/2026

Musik Hack update SweetEQ

Intuitive EQ plug-in gets an upgrade Following its official launch back in February 2026, Musik Hack's intuitive EQ plug-in has been treated to its firs...

13/04/2026

Vintage Vault 5 from UVI

Flagship soft synth collection expanded The latest version of UVI's flagship vintage-inspired soft synth collection has just arrived, expanding the suit...

13/04/2026

Sonuscore launch Lux Orchestral Strings Elements

Free version of innovative string library arrives Released in October 2025, Lux Orchestral Strings was said to be Sonuscore's most ambitious library to ...

13/04/2026

Girls' Research Camp at SGL Carbon in Meitingen inspires young women to pursue STEM careers

The Girls' Research Camp is part of the Technology - Future in Bavaria edu...

13/04/2026

Rohde & Schwarz transforms submarine communications for realtime underwater dominance at UDT 2026

Rohde & Schwarz transforms submarine communications for real time underwater dom...

13/04/2026

Rohde & Schwarz enables Pulsar signal simulation to support next-generation navigation devices

Rohde & Schwarz enables Pulsar signal simulation to support next-generation navi...

13/04/2026

When Missiles Move at 5X the Speed of Sound, Timing Is Everything

L3Harris is accelerating the development of infrared payloads for Space Development Agency's Tranche 2 Tracking Layer, to help meet urgent national defense ...

13/04/2026

US Army Selects L3Harris for Next-Generation Night-Vision System

By leveraging cutting-edge unfilmed Gen III image intensifier technology, NOVA delivers unmatched clarity, range, and reliability in low-light environments - en...

13/04/2026

Harvey Arnold Represents the Best of Broadcast Engineering

Share Copy link Facebook X Linkedin Bluesky Email...

13/04/2026

Ross Video and HighField AI to Deliver AI-Assisted Graphics Creation

Share Copy link Facebook X Linkedin Bluesky Email...

13/04/2026

Disguise to Showcase Cutting-Edge Experience Tech for Bro...

Explore new Disguise plugins, including Sony's VP integration; Listen to panels across partner booths at Sony and B&H Disguise, the company powering everyt...

13/04/2026

TAG Video Systems Joins MXL Interoperability Initiative t...

TAG Video Systems, the leading IP-native Realtime Media Platform, has announced its participation in the Media Exchange Layer (MXL) interop initiative. TAG has ...

13/04/2026

Chaos Launches Free V-Ray for Blender Community Edition a...

Today, Chaos launched V-Ray for Blender Community Edition at BCON Austin 2026, making its production-proven 3D renderer free for all Blender users. The same Aca...

13/04/2026

LTN Appoints Mark Romano as Vice President Multichannel P...

Additions strengthen LTN's leadership as broadcasters scale satellite-to-IP transition LTN today announced the appointments of Mark Romano as Vice Presiden...

13/04/2026

NUGEN Audio Updates Halo Vision With New Precision Analys...

LEEDS, UK, APRIL 13, 2026 NUGEN Audio releases Halo Vision v1.2, a significant update to its real time, customizable audio analysis suite for 3D, surround and...

13/04/2026

Atomos to Acquire Flanders Scientific

Atomos today announced the acquisition of Flanders Scientific (FSI), one of the most respected names in professional reference monitoring. This strategic move r...

13/04/2026

How Mei Semones Built Her Sound from J-Pop, Jazz, and Bilingual Songwriting

How Mei Semones Built Her Sound from J-Pop, Jazz, and Bilingual Songwriting The indie-pop artist combines agile guitar lines, rhythmic shifts, and lyrics that...

13/04/2026

Cue the Change: Jonathon Heyward Is Making Classical Music More Relatable

Cue the Change: Jonathon Heyward Is Making Classical Music More Relatable Nicknamed the Converse Conductor, the Boston Conservatory alum holds top conductin...

13/04/2026

Heat Wave: Inside Miamis Sizzling, Boundary-Blurring Latin Music Scene

Heat Wave: Inside Miamis Sizzling, Boundary-Blurring Latin Music Scene In a city shaped by migration and exchange, Berklee alumni are helping drive a Latin mu...