ScarpLearn: an automatic scarp height measurement of normal fault scarps using convolutional neural networks

Authors

DOI:

https://doi.org/10.26443/seismica.v4i2.1387

Keywords:

active faults, deep learning, geomorphology, Morphotectonic Features

Abstract

Geomorphic markers such as displaced surfaces, offset rivers or scarps are witnesses to the neotectonic activity of the faults.
The characterization (such as fault detailed surface trace, the scarp height, etc.) of these geomorphological markers is currently a time-consuming step with expert-dependent results, often qualitative and with uncertainties that are difficult to estimate. To overcome those issues, we present a proof of concept study for the use of deep learning in morphotectonics, specifically on fault markers. We developed a Bayesian supervised machine learning method using one-dimentional (1D) convolutional neural networks (CNN) trained on a database of simulated topographic profiles across normal fault scarps, called ScarpLearn. From a topographic profile, ScarpLearn is able to automatically give the cumulative scarp height with an uncertainty. We have developed two versions: one designed for more generalized cases involving profiles with multiple fault scarp (ScarpLearn), and another specifically trained to handle profiles featuring a single fault scarp (ScarpLearn_1F). We apply ScarpLearn for the characterization of active normal faults in extensional settings such as the Trans-Mexican Volcanic Belt and Malawi Rift system. From those specific case studies, we explore the progress (computation time, accuracy, uncertainties) that machine learning methods bring to the field of morphotectonics, as well as the current limits (such as
bias). Our results show that we are able to develop a CNN model that is estimating scarp heights on topographic profiles from 5m resolution digital elevation model. We compared the results obtained with ScarpLearn and other non deep-learning methods. ScarpLearn achieves similar accuracy while being much faster and having smaller uncertainties. We invite readers to use and to extend our study: codes to build the synthetic scarp database and for the CNN model ScarpLearn are available at: https://gricad-gitlab.univ-grenoble-alpes.fr/poussel/scarplearn.

References

Andrews, D. J., & Hanks, T. C. (1985). Scarp Degraded by Linear Diffusion: Inverse Solution for Age. Journal of Geophysical Research: Solid Earth, 90(B12), 10193–10208. https://doi.org/10.1029/JB090iB12p10193

Arrowsmith, J. Ramón, Pollard, D. D., & Rhodes, D. D. (1996). Hillslope Development in Areas of Active Tectonics. Journal of Geophysical Research: Solid Earth, 101(B3), 6255–6275. https://doi.org/10.1029/95JB02583

Arrowsmith, J. Ramón, Rhodes, D. D., & Pollard, D. D. (1998). Morphologic Dating of Scarps Formed by Repeated Slip Events along the San Andreas Fault, Carrizo Plain, California. Journal of Geophysical Research: Solid Earth, 103(B5), 10141–10160. https://doi.org/10.1029/98JB00505

Arrowsmith, J Ramon, Rockwell, T. K., Madugo, K. S., & Zielke, O. (2012). Repeatability, Accuracy, and Precision of Surface Slip Measurements from High-Resolution Topographic Data: Collaborative Research with Arizona State University and San Diego State University. Final Technical Report US Geological Survey National Earthquake Hazards Reduction External Research Program.

Avouac, J.-P., & Peltzer, G. (1993). Active Tectonics in Southern Xinjiang, China: Analysis of Terrace Riser and Normal Fault Scarp Degradation along the Hotan-Qira Fault System. Journal of Geophysical Research: Solid Earth, 98(B12), 21773–21807. https://doi.org/10.1029/93JB02172

Bello, S., Scott, C. P., Ferrarini, F., Brozzetti, F., Scott, T., Cirillo, D., de Nardis, R., Arrowsmith, J. R., & Lavecchia, G. (2021). High-Resolution Surface Faulting from the 1983 Idaho Lost River Fault Mw 6.9 Earthquake and Previous Events. Scientific Data, 8(1), 68. https://doi.org/10.1038/s41597-021-00838-6

Blundell, C., Cornebise, J., Kavukcuoglu, K., & Wierstra, D. (2015). Weight Uncertainty in Neural Network. International Conference on Machine Learning, 1613–1622.

Bond, C. E., Gibbs, A. D., Shipton, Z. K., & Jones, S. (2007). What Do You Think This Is? “Conceptual Uncertainty” in Geoscience Interpretation. GSA Today, 17(11), 4. https://doi.org/10.1130/GSAT01711A.1

Campbell, G. E., Walker, R. T., Abdrakhmatov, K., Jackson, J., Elliott, J. R., Mackenzie, D., Middleton, T., & Schwenninger, J.-L. (2015). Great Earthquakes in Low Strain Rate Continental Interiors: An Example from SE Kazakhstan. Journal of Geophysical Research: Solid Earth, 120(8), 5507–5534. https://doi.org/10.1002/2015JB011925

Carretier, S., Ritz, J.-F., Jackson, J., & Bayasgalan, A. (2002). Morphological Dating of Cumulative Reverse Fault Scarps: Examples from the Gurvan Bogd Fault System, Mongolia: Morphological Dating of Cumulative Reverse Fault Scarps. Geophysical Journal International, 148(2), 256–277. https://doi.org/10.1046/j.1365-246X.2002.01007.x

Chen, Z., Scott, C., Keating, D., Clarke, A., Das, J., & Arrowsmith, R. (2023). Quantifying and Analysing Rock Trait Distributions of Rocky Fault Scarps Using Deep Learning. Earth Surface Processes and Landforms, 48(6), 1234–1250. https://doi.org/10.1002/esp.5545

Crone, A. J., & Haller, K. M. (1991). Segmentation and the Coseismic Behavior of Basin and Range Normal Faults: Examples from East-Central Idaho and Southwestern Montana, U.S.A. Journal of Structural Geology, 13(2), 151–164. https://doi.org/10.1016/0191-8141(91)90063-O

Esposito, P. (2020). BLiTZ - Bayesian Layers in Torch Zoo (a Bayesian Deep Learing Library for Torch). In GitHub repository. GitHub.

Gray, H., DuRoss, C., Nicovich, S., & Gold, R. (2021). A Geomorphic-Process-Based Cellular Automata Model of Colluvial Wedge Morphology and Stratigraphy. Earth Surface Dynamics Discussions, 1–34. https://doi.org/10.5194/esurf-2021-70

Hanks, T. C. (2000). The Age of Scarplike Landforms from Diffusion-Equation Analysis. Quaternary Geochronology: Methods and Applications, 4, 313–338. https://doi.org/10.1029/rf004p0313

Hanks, T. C., Bucknam, R. C., Lajoie, K. R., & Wallace, R. E. (1984). Modification of Wave-cut and Faulting-controlled Landforms. Journal of Geophysical Research: Solid Earth, 89(B7), 5771–5790. https://doi.org/10.1029/JB089iB07p05771

Hodge, M., Biggs, J., Fagereng, AA., Mdala, H., Wedmore, L. N. J., & Williams, J. N. (2020). Evidence From High-Resolution Topography for Multiple Earthquakes on High Slip-to-Length Fault Scarps: The Bilila-Mtakataka Fault, Malawi. Tectonics, 39(2), e2019TC005933. https://doi.org/10.1029/2019TC005933

Hodge, M., Biggs, J., Fagereng, AAke, Elliott, A., Mdala, H., & Mphepo, F. (2019). A Semi-Automated Algorithm to Quantify Scarp Morphology (SPARTA): Application to Normal Faults in Southern Malawi. Solid Earth, 10(1), 27–57. https://doi.org/10.5194/se-10-27-2019

Hodge, M., Fagereng, AA., Biggs, J., & Mdala, H. (2018). Controls on Early-Rift Geometry: New Perspectives From the Bilila-Mtakataka Fault, Malawi. Geophysical Research Letters, 45(9), 3896–3905. https://doi.org/10.1029/2018GL077343

Hodge, Michael, Biggs, J., Fagereng, AAke, & Wedmore, L. (2019). Bilila-Mtakataka Fault - Mua Segment. Distributed by OpenTopography. https://doi.org/10.5069/G92R3PSV

Holtmann, R., Cattin, R., Simoes, M., & Steer, P. (2023). Revealing the Hidden Signature of Fault Slip History in the Morphology of Degrading Scarps. Scientific Reports, 13(1), 3856. https://doi.org/10.1038/s41598-023-30772-z

Jackson, J., & Blenkinsop, T. (1997). The Bilila-Mtakataka Fault in Malaŵi: An Active, 100-Km Long, Normal Fault Segment in Thick Seismogenic Crust. Tectonics, 16(1), 137–150. https://doi.org/10.1029/96TC02494

Johnson, K. L., Nissen, E., & Lajoie, L. (2018). Surface Rupture Morphology and Vertical Slip Distribution of the 1959 Mw 7.2 Hebgen Lake (Montana) Earthquake From Airborne Lidar Topography. Journal of Geophysical Research: Solid Earth, 123(9), 8229–8248. https://doi.org/10.1029/2017JB015039

Kokkalas, S., & Koukouvelas, I. K. (2005). Fault-Scarp Degradation Modeling in Central Greece: The Kaparelli and Eliki Faults (Gulf of Corinth) as a Case Study. Journal of Geodynamics, 40(2–3), 200–215. https://doi.org/10.1016/j.jog.2005.07.006

Kozacı, Ö., Madugo, C. M., Bachhuber, J. L., Hitchcock, C. S., Kottke, A. R., Higgins, K., Wade, A., & Rittenour, T. (2021). Rapid Postearthquake Field Reconnaissance, Paleoseismic Trenching, and GIS-Based Fault Slip Variability Measurements along the Mw 6.4 and Mw 7.1 Ridgecrest Earthquake Sequence, Southern California. Bulletin of the Seismological Society of America, 111(5), 2334–2357. https://doi.org/10.1785/0120200262

Kurtz, R., Klinger, Y., Ferry, M., & Ritz, J. F. (2018). Horizontal Surface-Slip Distribution through Several Seismic Cycles: The Eastern Bogd Fault, Gobi-Altai, Mongolia. Tectonophysics, 734–735, 167–182. https://doi.org/10.1016/j.tecto.2018.03.011

Lacan, P., Ortuño, M., Audin, L., Perea, H., Baize, S., Aguirre-Díaz, G., & Zúñiga, F. R. (2018). Sedimentary Evidence of Historical and Prehistorical Earthquakes along the Venta de Bravo Fault System, Acambay Graben (Central Mexico). Sedimentary Geology, 365, 62–77. https://doi.org/10.1016/j.sedgeo.2017.12.008

Mattéo, L., Manighetti, I., Tarabalka, Y., Gaucel, J.-M., van den Ende, M., Mercier, A., Tasar, O., Girard, N., Leclerc, F., Giampetro, T., Dominguez, S., & Malavieille, J. (2021). Automatic Fault Mapping in Remote Optical Images and Topographic Data With Deep Learning. Journal of Geophysical Research: Solid Earth, 126(4). https://doi.org/10.1029/2020JB021269

McCalpin, J. P. (2009). Paleoseismology (Vol. 95). Academic press.

McCalpin, J. P., & Slemmons, D. B. (1998). Statistics of Paleoseismic Data. The Company.

Mitchell, S. G., Matmon, A., Bierman, P. R., Enzel, Y., Caffee, M., & Rizzo, D. (2001). Displacement History of a Limestone Normal Fault Scarp, Northern Israel, from Cosmogenic 36Cl. Journal of Geophysical Research: Solid Earth, 106(B3), 4247–4264. https://doi.org/10.1029/2000JB900373

Nash, D. B. (1980). Morphologic Dating of Degraded Normal Fault Scarps. The Journal of Geology, 88(3), 353–360. https://doi.org/10.1086/628513

Núñez Meneses, A., Lacan, P., Zúñiga, F. R., Audin, L., Ortuño, M., Rosas Elguera, J., León-Loya, R., & Márquez, V. (2021). First Paleoseismological Results in the Epicentral Area of the Sixteenth Century Ameca Earthquake, Jalisco – México. Journal of South American Earth Sciences, 107, 103121. https://doi.org/10.1016/j.jsames.2020.103121

Nurminen, F., Baize, S., Boncio, P., Blumetti, A. M., Cinti, F. R., Civico, R., & Guerrieri, L. (2022). SURE 2.0 – New Release of the Worldwide Database of Surface Ruptures for Fault Displacement Hazard Analyses. Scientific Data, 9(1), 729. https://doi.org/10.1038/s41597-022-01835-z

Pousse-Beltran, L., Benedetti, L., Fleury, J., Boncio, P., Guillou, V., Pace, B., Rizza, M., Puliti, I., & Socquet, A. (2022). 36Cl Exposure Dating of Glacial Features to Constrain the Slip Rate along the Mt. Vettore Fault (Central Apennines, Italy). Geomorphology, 108302. https://doi.org/10.1016/j.geomorph.2022.108302

Pucci, S., Pizzimenti, L., Civico, R., Villani, F., Brunori, C. A., & Pantosti, D. (2021). High Resolution Morphometric Analysis of the Cordone Del Vettore Normal Fault Scarp (2016 Central Italy Seismic Sequence): Insights into Age, Earthquake Recurrence and Throw Rates. Geomorphology, 388, 107784. https://doi.org/10.1016/j.geomorph.2021.107784

Ren, C. X., Hulbert, C., Johnson, P. A., & Rouet-Leduc, B. (2020). Chapter Two - Machine Learning and Fault Rupture: A Review. In B. Moseley & L. Krischer (Eds.), Advances in Geophysics (Vol. 61, pp. 57–107). Elsevier. https://doi.org/10.1016/bs.agph.2020.08.003

Salisbury, J. B., Haddad, D. E., Rockwell, T., Arrowsmith, J. R., Madugo, C., Zielke, O., & Scharer, K. (2015). Validation of Meter-Scale Surface Faulting Offset Measurements from High-Resolution Topographic Data. Geosphere, 11(6), 1884–1901. https://doi.org/10.1130/GES01197.1

Salomon, G. W., New, T., Muir, R. A., Whitehead, B., Scheiber-Enslin, S., Smit, J., Stevens, V., Kahle, B., Kahle, R., Eckardt, F. D., & Alastair Sloan, R. (2021). Geomorphological and Geophysical Analyses of the Hebron Fault, SW Namibia: Implications for Stable Continental Region Seismic Hazard. Geophysical Journal International, 229(1), 235–254. https://doi.org/10.1093/gji/ggab466

Sare, R., Hilley, G. E., & DeLong, S. B. (2019). Regional-Scale Detection of Fault Scarps and Other Tectonic Landforms: Examples From Northern California. Journal of Geophysical Research: Solid Earth, 124(1), 1016–1035. https://doi.org/10.1029/2018JB016886

Schlagenhauf, A., Manighetti, I., Malavieille, J., & Dominguez, S. (2008). Incremental Growth of Normal Faults: Insights from a Laser-Equipped Analog Experiment. Earth and Planetary Science Letters, 273(3–4), 299–311. https://doi.org/10.1016/j.epsl.2008.06.042

Scott, C., Adam, R., Arrowsmith, R., Madugo, C., Powell, J., Ford, J., Gray, B., Koehler, R., Thompson, S., Sarmiento, A., Dawson, T., Kottke, A., Young, E., Williams, A., Kozaci, O., Oskin, M., Burgette, R., Streig, A., Seitz, G., … Ingersoll, S. (2023). Evaluating How Well Active Fault Mapping Predicts Earthquake Surface-Rupture Locations. Geosphere, 19(4), 1128–1156. https://doi.org/10.1130/GES02611.1

Scott, C., Bello, S., & Ferrarini, F. (2020). Matlab Algorithm for Systematic Vertical Separation Measurements of Tectonic Fault Scarps. Zenodo. https://doi.org/10.5281/zenodo.4247586

Scott, C. P., Giampietro, T., Brigham, C., Leclerc, F., Manighetti, I., Arrowsmith, J. R., Laó-Dávila, D. A., & Mattéo, L. (2022). Semiautomatic Algorithm to Map Tectonic Faults and Measure Scarp Height from Topography Applied to the Volcanic Tablelands and the Hurricane Fault, Western US. Lithosphere, 2021(Special 2), 9031662. https://doi.org/10.2113/2021/9031662

Shridhar, K., Laumann, F., & Liwicki, M. (2019a). A Comprehensive Guide to Bayesian Convolutional Neural Network with Variational Inference. ArXiv:1901.02731 [Cs, Stat].

Shridhar, K., Laumann, F., & Liwicki, M. (2019b). Uncertainty Estimations by Softplus Normalization in Bayesian Convolutional Neural Networks with Variational Inference. ArXiv:1806.05978 [Cs, Stat].

Smith, T. R., & Bretherton, F. P. (1972). Stability and the Conservation of Mass in Drainage Basin Evolution. Water Resources Research, 8(6), 1506–1529. https://doi.org/10.1029/WR008i006p01506

Stewart, N., Gaudemer, Y., Manighetti, I., Serreau, L., Vincendeau, A., Dominguez, S., Mattéo, L., & Malavieille, J. (2018). “3D_Fault_Offsets,” a Matlab Code to Automatically Measure Lateral and Vertical Fault Offsets in Topographic Data: Application to San Andreas, Owens Valley, and Hope Faults. Journal of Geophysical Research: Solid Earth, 123(1), 815–835. https://doi.org/10.1002/2017JB014863

Tucker, G. E., Hobley, D. E. J., McCoy, S. W., & Struble, W. T. (2020). Modeling the Shape and Evolution of Normal-Fault Facets. Journal of Geophysical Research: Earth Surface, 125(3), e2019JF005305. https://doi.org/10.1029/2019JF005305

Vega-Ramírez, L. A., Spelz, R. M., Negrete-Aranda, R., Neumann, F., Caress, D. W., Clague, D. A., Paduan, J. B., Contreras, J., & Peña-Dominguez, J. G. (2021). A New Method for Fault-Scarp Detection Using Linear Discriminant Analysis in High-Resolution Bathymetry Data From the Alarcón Rise and Pescadero Basin. Tectonics, 40(12), e2021TC006925. https://doi.org/10.1029/2021TC006925

Wallace, R. E. (1977). Profiles and Ages of Young Fault Scarps, North-Central Nevada. GSA Bulletin, 88(9), 1267–1281. https://doi.org/10.1130/0016-7606(1977)88<1267:PAAOYF>2.0.CO;2

Wells, D. L., & Coppersmith, K. J. (1994). New Empirical Relationships among Magnitude, Rupture Length, Rupture Width, Rupture Area, and Surface Displacement. Bulletin of the Seismological Society of America, 84(4), 974–1002.

Wolfe, F. D., Stahl, T. A., Villamor, P., & Lukovic, B. (2020). Short Communication: A Semiautomated Method for Bulk Fault Slip Analysis from Topographic Scarp Profiles. Earth Surface Dynamics, 8(1), 211–219. https://doi.org/10.5194/esurf-8-211-2020

Zhang, P., Slemmons, D. B., & Mao, F. (1991). Geometric Pattern, Rupture Termination and Fault Segmentation of the Dixie Valley—Pleasant Valley Active Normal Fault System, Nevada, U.S.A. Journal of Structural Geology, 13(2), 165–176. https://doi.org/10.1016/0191-8141(91)90064-P

Zielke, O., Klinger, Y., & Arrowsmith, J. R. (2015). Fault Slip and Earthquake Recurrence along Strike-Slip Faults — Contributions of High-Resolution Geomorphic Data. Tectonophysics, 638, 43–62. https://doi.org/10.1016/j.tecto.2014.11.004

Downloads

Published

2025-07-16

How to Cite

Pousse-Beltran, L., Lallemand, T., Audin, L., Lacan, P., Nunez-Meneses, A. D., & Giffard-Roisin, S. (2025). ScarpLearn: an automatic scarp height measurement of normal fault scarps using convolutional neural networks. Seismica, 4(2). https://doi.org/10.26443/seismica.v4i2.1387

Issue

Section

Articles

Funding data