Monitoring of Greenhouse Gas Emissions
Bertrand Rouet-Leduc, Claudia Hulbert
Automatic Detection of Methane Emissions in Multi-Spectral Satellite Imagery Using Transformers
In press
In this paper we show that deep learning can be leveraged to overcome the trade-off in terms of spectral resolution that comes with multi-spectral satellite data, resulting in a methane detection tool with global coverage and high temporal and spatial resolution. The assessment of our model on synthetic data as well as on real methane plumes results in an order of magnitude improvement over the state-of-the-art, providing a significant step towards the automated, high resolution detection of methane emissions at a global scale, every few days.
Machine Learning in Geophysics
Andrea Licciardi, Quentin Bletery, Bertrand Rouet-Leduc, Jean-Paul Ampuero, Kévin Juhel
Instantaneous tracking of earthquake growth with elastogravity signals
In this paper we show that deep learning can be used to track the growth of very large earthquakes in real time, by detecting faint elastogravity signals. Our model unlocks ‘true real-time’ access to the rupture evolution of large earthquakes using a portion of seismograms that is routinely treated as noise, and can be immediately transformative for tsunami early warning
Bertrand Rouet-Leduc, Romain Jolivet, Manon Dalaison, Paul A. Johnson, Claudia Hulbert
Autonomous Extraction of Millimeter-scale Deformation in InSAR Time Series Using Deep Learning
Nature Communications 12 (2021)
In this paper we show that a deep auto-encoder architecture tailored to untangle ground deformation from noise in InSAR time series autonomously extracts deformation signals, without prior knowledge of a fault's location or slip behaviour. Applied to InSAR data over the North Anatolian Fault, our method reaches 2 mm detection, revealing a slow earthquake twice as extensive as previously recognized. We further explore the generalization of our approach to inflation/deflation-induced deformation, applying the same methodology to the geothermal field of Coso, California.
Bertrand Rouet‐Leduc, Claudia Hulbert, Ian W. McBrearty, Paul A. Johnson
Probing Slow Earthquakes With Deep Learning
Geophysical Research Letters 47 (2020)
By training a convolutional neural network to detect known tremor on a single seismic station in Cascadia, we isolate and identify tremor and slip preceding and following known larger slow events. The deep neural network can be used for the detection of quasi‐continuous tremor, providing a proxy that quantifies the slow slip rate.
Claudia Hulbert, Bertrand Rouet-Leduc, Romain Jolivet, Paul A. Johnson
An exponential build-up in seismic energy suggests a months-long nucleation of slow slip in Cascadia
Nature Communications 11 (2020)
In this paper we show that seismic power exponentially increases as the slowly slipping portion of the subduction zone approaches failure, a behavior that shares a striking similarity with the increase in acoustic power observed prior to laboratory slow slip events. Our results suggest that the nucleation phase of Cascadia slow slip events may last from several weeks up to several months.
Bertrand Rouet-Leduc, Claudia Hulbert, Paul A. Johnson
Continuous chatter of the Cascadia subduction zone revealed by machine learning
Nature Geoscience 12 (2018)
In this paper we show that the Cascadia subduction zone is apparently continuously broadcasting a low-amplitude, tremor-like signal that precisely informs of the fault displacement rate throughout the slow slip cycle.
Fault Physics in the Laboratory
Bertrand Rouet‐Leduc, Claudia Hulbert, Nicholas Lubbers, Kipton Barros, Colin J. Humphreys, Paul A. Johnson
Machine Learning Predicts Laboratory Earthquakes
Geophysical Research Letters 44 (2017)
In this paper, we applied machine learning to data sets from shear laboratory experiments, with the goal of identifying hidden signals that precede earthquakes. Here we show that by listening to the acoustic signal emitted by a laboratory fault, machine learning can predict the time remaining before it fails with great accuracy. These predictions are based solely on the instantaneous physical characteristics of the acoustical signal and do not make use of its history.
Bertrand Rouet‐Leduc, Claudia Hulbert, David C. Bolton, Christopher X. Ren, Jacques Riviere, Chris Marone, Robert A. Guyer, Paul Johnson
Estimating Fault Friction From Seismic Signals in the Laboratory
Geophysical Research Letters 45 (2018)
We show that fault friction can be determined at any time, from the continuous seismic signal. In a classic laboratory experiment of repeating earthquakes, we find that the seismic signal follows a specific pattern with respect to fault friction, allowing us to determine the fault's position within its failure cycle. Using machine learning, we show that instantaneous statistical characteristics of the seismic signal are a fingerprint of the fault zone shear stress and frictional state.
Claudia Hulbert, Bertrand Rouet-Leduc, Paul A Johnson, Christopher X Ren, Jacques Riviere, David C Bolton, Chris Marone
Similarity of fast and slow earthquakes illuminated by machine learning
Nature Geoscience 12 (2018)
In this paper, we report on laboratory earthquakes and show that both slow and fast slip modes are preceded by a cascade of micro-failure events that radiate elastic energy in a manner that foretells catastrophic failure. Using machine learning, we find that acoustic emissions generated during shear of quartz fault gouge under normal stress of 1–10 MPa predict the timing and duration of laboratory earthquakes.
Simulations and High Performance Computing
Christopher X Ren, Omid Dorostkar, Bertrand Rouet‐Leduc, Claudia Hulbert, Dominik Strebel, Robert A Guyer, Paul Allan Johnson, Jan Carmeliet
Machine Learning Reveals the State of Intermittent Frictional Dynamics in a Sheared Granular Fault
Geophysical Research Letters 46 (2019)
In this paper we use machine learning to show that statistical features of velocity signals from individual particles in a simulated sheared granular fault contain information regarding the instantaneous global state of intermittent frictional stick‐slip dynamics.
Bertrand Rouet-Leduc, Kipton Barros, Turab Lookman, Colin J. Humphreys
Optimisation of GaN LEDs and the reduction of efficiency droop using active machine learning
Scientific Reports 6 (2016)
Statistical analysis and machine learning effectively guide the selection of the next LED structure to be examined based upon its expected efficiency as well as model uncertainty.
Bertrand Rouet-Leduc, Jean-Bernard Maillet, Christophe Denoual
Kinetics of heterogeneous nucleation and growth: An approach based on a grain explicit model
Modelling and Simulation in Materials Science and Engineering 22 (2014)
A model for phase transitions initiated on grain boundaries is proposed and tested against numerical simulations: this approach, based on a grain explicit model, allows us to consider the granular structure, resulting in accurate predictions for a wide span of nucleation processes. Comparisons are made with classical models of homogeneous as well as heterogeneous nucleation. A transition scale based on material properties is proposed, allowing us to discriminate between random and site-saturated regimes.
Bertrand Rouet-Leduc, Kipton Barros, Emmanuel Cieren, Venmugil Elango, Christoph Junghans, Turab Lookman, Jamaludin Mohd-Yusof, Robert S Pavel, Axel Y Rivera, Dominic Roehm, Allen L McPherson, Timothy C Germann
Spatial adaptive sampling in multiscale simulation
Computer Physics Communications 185 (2014)
In this paper we propose an approach to multiscale simulation that is local in space and time, avoids the need for a central database, and is designed to parallelize well on large computer clusters. To demonstrate our method, we simulate one-dimensional elastodynamic shock propagation. We find that spatial adaptive sampling requires only fine-scale simulations to reconstruct the stress field at all grid points.