Articles | Volume 11, issue 6
https://doi.org/10.5194/esurf-11-1145-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/esurf-11-1145-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
13 Nov 2023
Research article |
| 13 Nov 2023
| 13 Nov 2023
On the use of convolutional deep learning to predict shoreline change
Eduardo Gomez-de la Peña
CORRESPONDING AUTHOR
School of Environment, The University of Auckland, Tāmaki Makaurau / Auckland, Aotearoa / New Zealand
Giovanni Coco
School of Environment, The University of Auckland, Tāmaki Makaurau / Auckland, Aotearoa / New Zealand
Colin Whittaker
Department of Civil and Environmental Engineering, The University of Auckland, Tāmaki Makaurau / Auckland, Aotearoa / New Zealand
Jennifer Montaño
Auckland Council – Air, Land, and Biodiversity Team, Tāmaki Makaurau / Auckland, Aotearoa / New Zealand
Related authors
No articles found.
Antonis Chatzipavlis, Daniele Trogu, Andrea Ruju, Juan Montes, Antonio Usai, Marco Porta, Giovanni Coco, Sandro De Muro, and Paolo Ciavola
EGUsphere, https://doi.org/10.5194/egusphere-2025-2292, https://doi.org/10.5194/egusphere-2025-2292, 2025
This preprint is open for discussion and under review for Natural Hazards and Earth System Sciences (NHESS).
Short summary
Short summary
This study evaluates the performance of an early warning system for coastal flooding operating at a beach scale. The system is found to effectively capture total water level exceedances based on predefined morphological thresholds and trigger timely warnings, particularly under energetic sea conditions. Its forecasts are found to align well with selected overwash/flood events of varying magnitude and duration, captured by an on-site coastal video monitoring station.
Tate Kimpton, Colin Whittaker, Pablo Higuera, and Liam Wotherspoon
EGUsphere, https://doi.org/10.5194/egusphere-2024-3724, https://doi.org/10.5194/egusphere-2024-3724, 2025
This preprint is open for discussion and under review for Natural Hazards and Earth System Sciences (NHESS).
Short summary
Short summary
This research assesses tsunami exposure across New Zealand using detailed inundation maps for various tsunami scenarios. An efficient and accurate model highlights both urban centres and provincial regions as highly exposed, with significant impacts on buildings, infrastructure, and land. The findings provide critical understanding to help communities and decision-makers better plan for tsunamis, offering valuable insights for improving resilience and protecting assets nationwide.
Wagner L. L. Costa, Karin R. Bryan, and Giovanni Coco
Nat. Hazards Earth Syst. Sci., 23, 3125–3146, https://doi.org/10.5194/nhess-23-3125-2023, https://doi.org/10.5194/nhess-23-3125-2023, 2023
Short summary
Short summary
For predicting flooding events at the coast, topo-bathymetric data are essential. However, elevation data can be unavailable. To tackle this issue, recent efforts have centred on the use of satellite-derived topography (SDT) and bathymetry (SDB). This work is aimed at evaluating their accuracy and use for flooding prediction in enclosed estuaries. Results show that the use of SDT and SDB in numerical modelling can produce similar predictions when compared to the surveyed elevation data.
Charline Dalinghaus, Giovanni Coco, and Pablo Higuera
Nat. Hazards Earth Syst. Sci., 23, 2157–2169, https://doi.org/10.5194/nhess-23-2157-2023, https://doi.org/10.5194/nhess-23-2157-2023, 2023
Short summary
Short summary
Wave setup is a critical component of coastal flooding. Consequently, understanding and being able to predict wave setup is vital to protect coastal resources and the population living near the shore. Here, we applied machine learning to improve the accuracy of present predictors of wave setup. The results show that the new predictors outperform existing formulas demonstrating the capability of machine learning models to provide a physically sound description of wave setup.
Matthew W. Hayward, Emily M. Lane, Colin N. Whittaker, Graham S. Leonard, and William L. Power
Nat. Hazards Earth Syst. Sci., 23, 955–971, https://doi.org/10.5194/nhess-23-955-2023, https://doi.org/10.5194/nhess-23-955-2023, 2023
Short summary
Short summary
In this paper, 20 explosive volcanic eruption scenarios of differing location and magnitude are simulated to investigate tsunami generation in Lake Taupō, New Zealand. A non-hydrostatic multilayer numerical scheme resolves the highly dispersive generated wavefield. Inundation, hydrographic and related hazard outputs are produced, indicating that significant inundation around the lake shore begins above 5 on the volcanic explosivity index.
Matthew W. Hayward, Colin N. Whittaker, Emily M. Lane, William L. Power, Stéphane Popinet, and James D. L. White
Nat. Hazards Earth Syst. Sci., 22, 617–637, https://doi.org/10.5194/nhess-22-617-2022, https://doi.org/10.5194/nhess-22-617-2022, 2022
Short summary
Short summary
Volcanic eruptions can produce tsunamis through multiple mechanisms. We present validation cases for a numerical method used in simulating waves caused by submarine explosions: a laboratory flume experiment and waves generated by explosions at field scale. We then demonstrate the use of the scheme for simulating analogous volcanic eruptions, illustrating the resulting wavefield. We show that this scheme models such dispersive sources more proficiently than standard tsunami models.
Yizhang Wei, Yining Chen, Jufei Qiu, Zeng Zhou, Peng Yao, Qin Jiang, Zheng Gong, Giovanni Coco, Ian Townend, and Changkuan Zhang
Earth Surf. Dynam., 10, 65–80, https://doi.org/10.5194/esurf-10-65-2022, https://doi.org/10.5194/esurf-10-65-2022, 2022
Short summary
Short summary
The barrier tidal basin is increasingly altered by human activity and sea-level rise. These environmental changes probably lead to the emergence or disappearance of islands, yet the effect of rocky islands on the evolution of tidal basins remains poorly investigated. Using numerical experiments, we explore the evolution of tidal basins under varying numbers and locations of islands. This work provides insights for predicting the response of barrier tidal basins in a changing environment.
Giovanni Coco, Daniel Calvete, Francesca Ribas, Huib E. de Swart, and Albert Falqués
Earth Surf. Dynam., 8, 323–334, https://doi.org/10.5194/esurf-8-323-2020, https://doi.org/10.5194/esurf-8-323-2020, 2020
Short summary
Short summary
Sandbars are ubiquitous features of the surf zone. They are rarely straight and often develop crescentic shapes. Double sandbar systems are also common, but the possibility of feedback between inner and outer sandbars has not been fully explored. The presence of double sandbar systems affects wave transformation and can result in a variety of spatial patterns. Here we model the conditions, waves and initial bathymetry that lead to the emergence of different patterns.
Marinella Passarella, Evan B. Goldstein, Sandro De Muro, and Giovanni Coco
Nat. Hazards Earth Syst. Sci., 18, 599–611, https://doi.org/10.5194/nhess-18-599-2018, https://doi.org/10.5194/nhess-18-599-2018, 2018
Sarik Salim, Charitha Pattiaratchi, Rafael Tinoco, Giovanni Coco, Yasha Hetzel, Sarath Wijeratne, and Ravindra Jayaratne
Earth Surf. Dynam., 5, 399–415, https://doi.org/10.5194/esurf-5-399-2017, https://doi.org/10.5194/esurf-5-399-2017, 2017
Short summary
Short summary
The aim of this paper was to verify the existence of a mean critical velocity concept in terms of turbulent bursting phenomena. Laboratory experiments were undertaken in a unidirectional current flume where an acoustic Doppler velocimeter was used. Results in the laboratory conditions both above and below the measured mean critical velocity highlighted the need to re-evaluate the accuracy of a single time-averaged critical velocity for the initiation of sediment entrainment.
M. Jiménez, S. Castanedo, Z. Zhou, G. Coco, R. Medina, and I. Rodriguez-Iturbe
Adv. Geosci., 39, 69–73, https://doi.org/10.5194/adgeo-39-69-2014, https://doi.org/10.5194/adgeo-39-69-2014, 2014
Z. Zhou, L. Stefanon, M. Olabarrieta, A. D'Alpaos, L. Carniello, and G. Coco
Earth Surf. Dynam., 2, 105–116, https://doi.org/10.5194/esurf-2-105-2014, https://doi.org/10.5194/esurf-2-105-2014, 2014
R. O. Tinoco and G. Coco
Earth Surf. Dynam., 2, 83–96, https://doi.org/10.5194/esurf-2-83-2014, https://doi.org/10.5194/esurf-2-83-2014, 2014
E. B. Goldstein, G. Coco, A. B. Murray, and M. O. Green
Earth Surf. Dynam., 2, 67–82, https://doi.org/10.5194/esurf-2-67-2014, https://doi.org/10.5194/esurf-2-67-2014, 2014
Related subject area
Physical: Geomorphology (including all aspects of fluvial, coastal, aeolian, hillslope and glacial geomorphology)
The glacial paleolandscapes of Southern Africa: the legacy of the Late Paleozoic Ice Age
Multiple equilibrium configurations in river-dominated deltas
Investigating the celerity of propagation for small perturbations and dispersive sediment aggradation under a supercritical flow
Short communication: Multiscale topographic complexity analysis with pyTopoComplexity
Sub-surface processes and heat fluxes at coarse blocky Murtèl rock glacier (Engadine, eastern Swiss Alps): seasonal ice and convective cooling render rock glaciers climate-robust
Influence of alluvial slope on avulsion in river deltas
Surficial sediment remobilization by shear between sediment and water above tsunamigenic megathrust ruptures: experimental study
Curvature-based pebble segmentation for reconstructed surface meshes
Haloturbation in the northern Atacama Desert revealed by a hidden subsurface network of calcium sulfate wedges
An evaluation of flow-routing algorithms for calculating contributing area on regular grids
Geometric constraints on tributary fluvial network junction angles
Effect of grain-sorting waves on alternate bar dynamics: Implications of the breakdown of the hydrograph boundary layer
Automatic detection of floating instream large wood in videos using deep learning
Investigating uncertainty and parameter sensitivity in bedform analysis by using a Monte Carlo approach
Geomorphic imprint of high-mountain floods: insights from the 2022 hydrological extreme across the upper Indus River catchment in the northwestern Himalayas
Short communication: Learning How Landscapes Evolve with Neural Operators
A numerical model for duricrust formation by water table fluctuations
Width evolution of channel belts as a random walk
Evidence of slow millennial cliff retreat rates using cosmogenic nuclides in coastal colluvium
Equilibrium distance from long-range dune interactions
Examination of analytical shear stress predictions for coastal dune evolution
Localised geomorphic response to channel-spanning leaky wooden dams
Post-fire evolution of ravel transport regimes in the Diablo Range, CA
Landscape response to tectonic deformation and cyclic climate change since ca. 800 ka in the southern central Andes
The Aare main overdeepening on the northern margin of the European Alps: basins, riegels, and slot canyons
Surface grain-size mapping of braided channels from SfM photogrammetry
A simple model for faceted topographies at normal faults based on an extended stream-power law
Testing floc settling velocity models in rivers and freshwater wetlands
River suspended-sand flux computation with uncertainty estimation using water samples and high-resolution ADCP measurements
Barchan swarm dynamics from a Two-Flank Agent-Based Model
A landslide runout model for sediment transport, landscape evolution, and hazard assessment applications
Tracking slow-moving landslides with PlanetScope data: new perspectives on the satellite's perspective
Topographic metrics for unveiling fault segmentation and tectono-geomorphic evolution with insights into the impact of inherited topography, Ulsan Fault Zone, South Korea
Biomechanical parameters of marram grass (Calamagrostis arenaria) for advanced modeling of dune vegetation
Acceleration of coastal-retreat rates for high-Arctic rock cliffs on Brøggerhalvøya, Svalbard, over the past decade
The impact of bedrock meander cutoffs on 50 kyr scale incision rates, San Juan River, Utah
Sediment aggradation rates for Himalayan Rivers revealed through SAR remote sensing
Spatiotemporal denudation rates of the Swabian Alb escarpment (Southwest Germany) dominated by base-level lowering and lithology
Use of simple analytical solutions in the calibration of Shallow Water Equations debris flow models
How water, temperature, and seismicity control the preconditioning of massive rock slope failure (Hochvogel)
Large structure simulation for landscape evolution models
Terrace formation linked to outburst floods at the Diexi palaeo-landslide dam, upper Minjiang River, eastern Tibetan Plateau
AI-Based Tracking of Fast-Moving Alpine Landforms Using High Frequency Monoscopic Time-Lapse Imagery
Pliocene shorelines and the epeirogenic motion of continental margins: a target dataset for dynamic topography models
Decadal-scale decay of landslide-derived fluvial suspended sediment after Typhoon Morakot
Role of the forcing sources in morphodynamic modelling of an embayed beach
A machine learning approach to the geomorphometric detection of ribbed moraines in Norway
Stream hydrology controls on ice cliff evolution and survival on debris-covered glaciers
Time-varying drainage basin development and erosion on volcanic edifices
Geomorphic risk maps for river migration using probabilistic modeling – a framework
Pierre Dietrich, François Guillocheau, Guilhem A. Douillet, Neil P. Griffis, Guillaume Baby, Daniel P. Le Héron, Laurie Barrier, Maximilien Mathian, Isabel P. Montañez, Cécile Robin, Thomas Gyomlai, Christoph Kettler, and Axel Hofmann
Earth Surf. Dynam., 13, 495–529, https://doi.org/10.5194/esurf-13-495-2025, https://doi.org/10.5194/esurf-13-495-2025, 2025
Short summary
Short summary
At the evocation of icy landscapes, Africa is not the first place that comes to mind. The modern relief of Southern Africa is generally considered to be a result of uplift and counteracting erosion. We show that some of the modern relief of this region is due to fossil glacial landscapes – striated pavements, valleys, and fjords – tied to an ice age that occurred ca. 300 Myr ago. We focus on how these landscapes have escaped being erased for hundreds of millions of years.
Lorenzo Durante, Nicoletta Tambroni, and Michele Bolla Pittaluga
Earth Surf. Dynam., 13, 455–471, https://doi.org/10.5194/esurf-13-455-2025, https://doi.org/10.5194/esurf-13-455-2025, 2025
Short summary
Short summary
River deltas evolve due to natural forces and human activities, posing challenges for communities relying on stable water flow. This study examines how different flow distributions shape delta channels. Using a new theoretical model, we identify branch length as the key factor influencing stability. Applying this to Italy's Po River Delta, we highlight areas at risk of change, providing insights for better management and planning.
Hasan Eslami, Erfan Poursoleymanzadeh, Mojtaba Hiteh, Keivan Tavakoli, Melika Yavari Nia, Ehsan Zadehali, Reihaneh Zarrabi, and Alessio Radice
Earth Surf. Dynam., 13, 437–454, https://doi.org/10.5194/esurf-13-437-2025, https://doi.org/10.5194/esurf-13-437-2025, 2025
Short summary
Short summary
A channel may be aggraded by overloaded sediment. In this study we realize an aggradation experiment and determine the celerity at which an aggradation wave, due to sediment overloading, migrates. We also investigate the celerity of small perturbations, as quantified by mathematical formulations. The celerities of the two kinds are correlated with each other. However, the celerity of small perturbations is larger than the other one, which is less than a few percent of the water velocity.
Larry Syu-Heng Lai, Adam M. Booth, Alison R. Duvall, and Erich Herzig
Earth Surf. Dynam., 13, 417–435, https://doi.org/10.5194/esurf-13-417-2025, https://doi.org/10.5194/esurf-13-417-2025, 2025
Short summary
Short summary
pyTopoComplexity is an open-source Python tool for multiscale land surface complexity analysis. Applied to a landslide-affected area in Washington, USA, it accurately identified landform features at various scales, enhancing our understanding of landform recovery after disturbances. By integrating with Landlab’s landscape evolution simulations, the software allows researchers to explore how different processes drive the evolution of surface complexity in response to natural forces.
Dominik Amschwand, Jonas Wicky, Martin Scherler, Martin Hoelzle, Bernhard Krummenacher, Anna Haberkorn, Christian Kienholz, and Hansueli Gubler
Earth Surf. Dynam., 13, 365–401, https://doi.org/10.5194/esurf-13-365-2025, https://doi.org/10.5194/esurf-13-365-2025, 2025
Short summary
Short summary
Rock glaciers are comparatively climate-robust permafrost landforms. We estimated the energy budget of the seasonally thawing active layer (AL) of Murtèl rock glacier (Swiss Alps) based on a novel sub-surface sensor array. In the coarse blocky AL, heat is transferred by thermal radiation and air convection. The ground heat flux is largely spent on melting seasonal ice in the AL. Convective cooling and the seasonal ice turnover make rock glaciers climate-robust and shield the permafrost beneath.
Octria A. Prasojo, Trevor B. Hoey, Amanda Owen, and Richard D. Williams
Earth Surf. Dynam., 13, 349–363, https://doi.org/10.5194/esurf-13-349-2025, https://doi.org/10.5194/esurf-13-349-2025, 2025
Short summary
Short summary
Decades of delta avulsion (i.e. channel abrupt jump) studies have not resolved what the main controls of delta avulsion are. Using a computer model, integrated with field observation, analytical, and laboratory-made deltas, we found that the sediment load, which itself is controlled by the steepness of the river upstream of a delta, controls the timing of avulsion. We can now better understand the main cause of abrupt channel changes in deltas, a finding that aids flood risk management in river deltas.
Chloé Seibert, Cecilia McHugh, Chris Paola, Leonardo Seeber, and James Tucker
Earth Surf. Dynam., 13, 341–348, https://doi.org/10.5194/esurf-13-341-2025, https://doi.org/10.5194/esurf-13-341-2025, 2025
Short summary
Short summary
We propose a new mechanism of co-seismic sediment entrainment induced by shear stress at the sediment–water interface during major subduction earthquakes rupturing to the trench. Physical experiments show that flow velocities consistent with long-period earthquake motions can entrain synthetic marine sediment, and high-frequency vertical shaking can enhance this mobilization. They validate the proposed entrainment mechanism, which opens new avenues for paleoseismology in deep-sea environments.
Aljoscha Rheinwalt, Benjamin Purinton, and Bodo Bookhagen
EGUsphere, https://doi.org/10.5194/egusphere-2025-1110, https://doi.org/10.5194/egusphere-2025-1110, 2025
Short summary
Short summary
Our study presents a computer-based method to detect and measure pebbles in 3D models reconstructed from camera photos. We tested it in a controlled setup and achieved 98 % accuracy in detecting pebbles. Unlike traditional 2D methods, our approach provides full 3D size and orientation data. This improves sediment analysis and riverbed studies by offering more precise measurements. Our work highlights the potential of 3D modeling for studying natural surfaces.
Aline Zinelabedin, Joel Mohren, Maria Wierzbicka-Wieczorek, Tibor Janos Dunai, Stefan Heinze, and Benedikt Ritter
Earth Surf. Dynam., 13, 257–276, https://doi.org/10.5194/esurf-13-257-2025, https://doi.org/10.5194/esurf-13-257-2025, 2025
Short summary
Short summary
In order to interpret the formation processes of subsurface salt wedges and polygonal patterned grounds from the northern Atacama Desert, we present a multi-methodological approach. Due to the high salt content of the wedges, we suggest that their formation is dominated by subsurface salt dynamics requiring moisture. We assume that the climatic conditions during the wedge growth were slightly wetter than today, offering the potential to use the wedges as palaeoclimate archives.
Alexander B. Prescott, Jon D. Pelletier, Satya Chataut, and Sriram Ananthanarayan
Earth Surf. Dynam., 13, 239–256, https://doi.org/10.5194/esurf-13-239-2025, https://doi.org/10.5194/esurf-13-239-2025, 2025
Short summary
Short summary
Many Earth surface processes are controlled by the spatial pattern of surface water flow. We review commonly used methods for predicting such spatial patterns in digital landform models and document the pros and cons of commonly used methods. We propose a new method that is designed to minimize those limitations and show that it works well in a variety of test cases.
Jon D. Pelletier, Robert G. Hayes, Olivia Hoch, Brendan Fenerty, and Luke A. McGuire
Earth Surf. Dynam., 13, 219–238, https://doi.org/10.5194/esurf-13-219-2025, https://doi.org/10.5194/esurf-13-219-2025, 2025
Short summary
Short summary
We demonstrate that landscapes with more planar initial conditions tend to have lower mean junction angles. Geomorphic processes on alluvial piedmonts result in especially planar initial conditions, consistent with a correlation between junction angles and the presence/absence of Late Cenozoic alluvial deposits and the constraint imposed by the intersection of planar approximations to the topography upslope from tributary junctions. We caution against using junction angles to infer paleoclimate.
Soichi Tanabe and Toshiki Iwasaki
EGUsphere, https://doi.org/10.5194/egusphere-2025-103, https://doi.org/10.5194/egusphere-2025-103, 2025
Short summary
Short summary
We try to understand how the sediment supply from the upstream river reach affect the downstream river morphology using a numerical model. If the supplied sediment is composed of variety of size class of particles, a small size bed wave that is composed of mainly fine particles (sorting wave) can propagate to downstream very long distance. However, presence of bars suppresses the effect of sorting wave greatly, and thus the sediment supply has limited role in the downstream river morphology.
Janbert Aarnink, Tom Beucler, Marceline Vuaridel, and Virginia Ruiz-Villanueva
Earth Surf. Dynam., 13, 167–189, https://doi.org/10.5194/esurf-13-167-2025, https://doi.org/10.5194/esurf-13-167-2025, 2025
Short summary
Short summary
This study presents a novel convolutional-neural-network approach for detecting instream large wood in rivers, addressing the need for flexible monitoring methods across diverse data sources. Using a database of 15 228 fully labelled images, the model achieved a weighted mean average precision of 67 %. Fine-tuning parameters and sampling techniques can improve performance by over 10 % in some cases, offering valuable insights into ecosystem management.
Julius Reich and Axel Winterscheid
Earth Surf. Dynam., 13, 191–217, https://doi.org/10.5194/esurf-13-191-2025, https://doi.org/10.5194/esurf-13-191-2025, 2025
Short summary
Short summary
Analyzing the geometry and the dynamics of riverine bedforms (so-called dune tracking) is important for various fields of application and contributes to sound and efficient river and sediment management. We developed a workflow that enables a robust estimation of bedform characteristics and with which comprehensive sensitivity analyses can be carried out. Using a field dataset, we show that the setting of input parameters in bedform analyses can have a significant impact on the results.
Abhishek Kashyap, Kristen L. Cook, and Mukunda Dev Behera
Earth Surf. Dynam., 13, 147–166, https://doi.org/10.5194/esurf-13-147-2025, https://doi.org/10.5194/esurf-13-147-2025, 2025
Short summary
Short summary
Short-lived, high-magnitude flood events across high mountain regions leave substantial geomorphic imprints, which are frequently triggered by excess precipitation, glacial lake outbursts, and natural dam breaches. These catastrophic floods highlight the importance of understanding the complex interaction between climatic, hydrological, and geological forces in bedrock catchments. Extreme floods can have long-term geomorphic consequences on river morphology and fluvial processes.
Gareth G. Roberts
EGUsphere, https://doi.org/10.5194/egusphere-2025-307, https://doi.org/10.5194/egusphere-2025-307, 2025
Short summary
Short summary
The use of new Artificial Intelligence (AI) techniques to learn how landscapes evolve is demonstrated. A few ‘snapshots' of an eroding landscape at different stages of its history provide enough information for AI to ascertain rules governing its evolution. Once the rules are known, predicting landscape evolution is extremely rapid and efficient, providing new tools to understand landscape change.
Caroline Fenske, Jean Braun, François Guillocheau, and Cécile Robin
Earth Surf. Dynam., 13, 119–146, https://doi.org/10.5194/esurf-13-119-2025, https://doi.org/10.5194/esurf-13-119-2025, 2025
Short summary
Short summary
We have developed a new numerical model to represent the formation of duricrusts, which are hard mineral layers found in soils and at the surface of the Earth. We assume that the formation mechanism implies variations in the height of the water table and that the hardening rate is proportional to precipitation. The model allows us to quantify the potential feedbacks they generate on the surface topography and the thickness of the regolith/soil layer.
Jens M. Turowski, Fergus McNab, Aaron Bufe, and Stefanie Tofelde
Earth Surf. Dynam., 13, 97–117, https://doi.org/10.5194/esurf-13-97-2025, https://doi.org/10.5194/esurf-13-97-2025, 2025
Short summary
Short summary
Channel belts comprise the area affected by a river due to lateral migration and floods. As a landform, they affect water resources and flood hazard, and they often host unique ecological communities. We develop a model describing the evolution of channel-belt area over time. The model connects the behaviour of the river to the evolution of the channel belt over a timescale of centuries. A comparison to selected data from experiments and real river systems verifies the random walk approach.
Rémi Bossis, Vincent Regard, Sébastien Carretier, and Sandrine Choy
Earth Surf. Dynam., 13, 71–79, https://doi.org/10.5194/esurf-13-71-2025, https://doi.org/10.5194/esurf-13-71-2025, 2025
Short summary
Short summary
The erosion of rocky coasts occurs episodically through wave action and landslides, constituting a major natural hazard. Documenting the factors that control the coastal retreat rate over millennia is fundamental to evidencing any change in time. However, the known rates to date are essentially representative of the last few decades. Here, we present a new method using the concentration of an isotope, 10Be, in sediment eroded from the cliff to quantify its retreat rate averaged over millennia.
Jean Vérité, Clément Narteau, Olivier Rozier, Jeanne Alkalla, Laurie Barrier, and Sylvain Courrech du Pont
Earth Surf. Dynam., 13, 23–39, https://doi.org/10.5194/esurf-13-23-2025, https://doi.org/10.5194/esurf-13-23-2025, 2025
Short summary
Short summary
Using a numerical model in 2D, we study how two identical dunes interact with each other when exposed to reversing winds. Depending on the distance between the dunes, they either repel or attract each other until they reach an equilibrium distance, which is controlled by the wind strength, wind reversal frequency, and dune size. This process is controlled by the modification of wind flow over dunes of various shapes, influencing the sediment transport downstream.
Orie Cecil, Nicholas Cohn, Matthew Farthing, Sourav Dutta, and Andrew Trautz
Earth Surf. Dynam., 13, 1–22, https://doi.org/10.5194/esurf-13-1-2025, https://doi.org/10.5194/esurf-13-1-2025, 2025
Short summary
Short summary
Using computational fluid dynamics, we analyze the error trends of an analytical shear stress distribution model used to drive aeolian transport for coastal dunes, which are an important line of defense against storm-related flooding hazards. We find that compared to numerical simulations, the analytical model results in a net overprediction of the landward migration rate. Additionally, two data-driven approaches are proposed for reducing the error while maintaining computational efficiency.
Joshua M. Wolstenholme, Christopher J. Skinner, David J. Milan, Robert E. Thomas, and Daniel R. Parsons
EGUsphere, https://doi.org/10.5194/egusphere-2024-3001, https://doi.org/10.5194/egusphere-2024-3001, 2024
Short summary
Short summary
Leaky wooden dams are a popular form of natural flood management used to slow the flow of water by increasing floodplain connectivity whilst decreasing connectivity along the river profile. By monitoring two leaky wooden dams in North Yorkshire, UK, we present the geomorphological response to their installation, highlighting that the structures significantly increase channel complexity in response to different river flow conditions.
Hayden L. Jacobson, Danica L. Roth, Gabriel Walton, Margaret Zimmer, and Kerri Johnson
Earth Surf. Dynam., 12, 1415–1446, https://doi.org/10.5194/esurf-12-1415-2024, https://doi.org/10.5194/esurf-12-1415-2024, 2024
Short summary
Short summary
Loose grains travel farther after a fire because no vegetation is left to stop them. This matters since loose grains at the base of a slope can turn into a debris flow if it rains. To find if grass growing back after a fire had different impacts on grains of different sizes on slopes of different steepness, we dropped thousands of natural grains and measured how far they went. Large grains went farther 7 months after the fire than 11 months after, and small grain movement didn’t change much.
Elizabeth N. Orr, Taylor F. Schildgen, Stefanie Tofelde, Hella Wittmann, and Ricardo N. Alonso
Earth Surf. Dynam., 12, 1391–1413, https://doi.org/10.5194/esurf-12-1391-2024, https://doi.org/10.5194/esurf-12-1391-2024, 2024
Short summary
Short summary
Fluvial terraces and alluvial fans in the Toro Basin, NW Argentina, record river evolution and global climate cycles over time. Landform dating reveals lower-frequency climate cycles (100 kyr) preserved downstream and higher-frequency cycles (21/40 kyr) upstream, supporting theoretical predications that longer rivers filter out higher-frequency climate signals. This finding improves our understanding of the spatial distribution of sedimentary paleoclimate records within landscapes.
Fritz Schlunegger, Edi Kissling, Dimitri Tibo Bandou, Guilhem Amin Douillet, David Mair, Urs Marti, Regina Reber, Patrick Schläfli, and Michael Alfred Schwenk
Earth Surf. Dynam., 12, 1371–1389, https://doi.org/10.5194/esurf-12-1371-2024, https://doi.org/10.5194/esurf-12-1371-2024, 2024
Short summary
Short summary
Overdeepenings are bedrock depressions filled with sediment. We combine the results of a gravity survey with drilling data to explore the morphology of such a depression beneath the city of Bern. We find that the target overdeepening comprises two basins >200 m deep. They are separated by a bedrock riegel that itself is cut by narrow canyons up to 150 m deep. We postulate that these structures formed underneath a glacier, where erosion by subglacial meltwater caused the formation of the canyons.
Loïs Ribet, Frédéric Liébault, Laurent Borgniet, Michaël Deschâtres, and Gabriel Melun
EGUsphere, https://doi.org/10.5194/egusphere-2024-3697, https://doi.org/10.5194/egusphere-2024-3697, 2024
Short summary
Short summary
This work presents a protocol and a model to get the size of the pebbles in mountain rivers from Unmanned Aerial Vehicle images. A set of 12 rivers located in south-eastern France were photographed to build the model. The results show that the model has little error and should be usable for similar rivers. Grain-size of mountain rivers is an important parameter for environmental diagnostics by mapping the aquatic habitats and for flood management by estimating the pebbles fluxes during floods.
Stefan Hergarten
Earth Surf. Dynam., 12, 1315–1327, https://doi.org/10.5194/esurf-12-1315-2024, https://doi.org/10.5194/esurf-12-1315-2024, 2024
Short summary
Short summary
Faceted topographies are impressive footprints of active tectonics in geomorphology. This paper investigates the evolution of faceted topographies at normal faults and their interaction with a river network theoretically and numerically. As a main result beyond several relations for the geometry of facets, the horizontal displacement associated with normal faults is crucial for the dissection of initially polygonal facets into triangular facets bounded by almost parallel rivers.
Justin A. Nghiem, Gen K. Li, Joshua P. Harringmeyer, Gerard Salter, Cédric G. Fichot, Luca Cortese, and Michael P. Lamb
Earth Surf. Dynam., 12, 1267–1294, https://doi.org/10.5194/esurf-12-1267-2024, https://doi.org/10.5194/esurf-12-1267-2024, 2024
Short summary
Short summary
Fine sediment grains in freshwater can cohere into faster-settling particles called flocs, but floc settling velocity theory has not been fully validated. Combining three data sources in novel ways in the Wax Lake Delta, we verified a semi-empirical model relying on turbulence and geochemical factors. For a physics-based model, we showed that the representative grain diameter within flocs relies on floc structure and that heterogeneous flow paths inside flocs increase floc settling velocity.
Jessica Marggraf, Guillaume Dramais, Jérôme Le Coz, Blaise Calmel, Benoît Camenen, David J. Topping, William Santini, Gilles Pierrefeu, and François Lauters
Earth Surf. Dynam., 12, 1243–1266, https://doi.org/10.5194/esurf-12-1243-2024, https://doi.org/10.5194/esurf-12-1243-2024, 2024
Short summary
Short summary
Suspended-sand fluxes in rivers vary with time and space, complicating their measurement. The proposed method captures the vertical and lateral variations of suspended-sand concentration throughout a river cross-section. It merges water samples taken at various positions throughout the cross-section with high-resolution acoustic velocity measurements. This is the first method that includes a fully applicable uncertainty estimation; it can easily be applied to any other study sites.
Dominic T. Robson and Andreas C. W. Baas
Earth Surf. Dynam., 12, 1205–1226, https://doi.org/10.5194/esurf-12-1205-2024, https://doi.org/10.5194/esurf-12-1205-2024, 2024
Short summary
Short summary
Barchans are fast-moving sand dunes which form large populations (swarms) on Earth and Mars. We show that a small range of model parameters produces swarms in which dune size does not vary downwind – something that is observed in nature but not when using earlier models. We also show how the shape of dunes and the spatial patterns they form are affected by wind direction. This work furthers our understanding of the interplay between environmental drivers, dune interactions, and swarm properties.
Jeffrey Keck, Erkan Istanbulluoglu, Benjamin Campforts, Gregory Tucker, and Alexander Horner-Devine
Earth Surf. Dynam., 12, 1165–1191, https://doi.org/10.5194/esurf-12-1165-2024, https://doi.org/10.5194/esurf-12-1165-2024, 2024
Short summary
Short summary
MassWastingRunout (MWR) is a new landslide runout model designed for sediment transport, landscape evolution, and hazard assessment applications. MWR is written in Python and includes a calibration utility that automatically determines best-fit parameters for a site and empirical probability density functions of each parameter for probabilistic model implementation. MWR and Jupyter Notebook tutorials are available as part of the Landlab package at https://github.com/landlab/landlab.
Ariane Mueting and Bodo Bookhagen
Earth Surf. Dynam., 12, 1121–1143, https://doi.org/10.5194/esurf-12-1121-2024, https://doi.org/10.5194/esurf-12-1121-2024, 2024
Short summary
Short summary
This study investigates the use of optical PlanetScope data for offset tracking of the Earth's surface movement. We found that co-registration accuracy is locally degraded when outdated elevation models are used for orthorectification. To mitigate this bias, we propose to only correlate scenes acquired from common perspectives or base orthorectification on more up-to-date elevation models generated from PlanetScope data alone. This enables a more detailed analysis of landslide dynamics.
Cho-Hee Lee, Yeong Bae Seong, John Weber, Sangmin Ha, Dong-Eun Kim, and Byung Yong Yu
Earth Surf. Dynam., 12, 1091–1120, https://doi.org/10.5194/esurf-12-1091-2024, https://doi.org/10.5194/esurf-12-1091-2024, 2024
Short summary
Short summary
Topographic metrics were used to understand changes due to tectonic activity. We evaluated the relative tectonic activity along the Ulsan Fault Zone (UFZ), one of the most active fault zones in South Korea. We divided the UFZ into five segments, based on the spatial variation in activity. We modeled the landscape evolution of the study area and interpreted tectono-geomorphic history during which the northern part of the UFZ experienced asymmetric uplift, while the southern part did not.
Viktoria Kosmalla, Oliver Lojek, Jana Carus, Kara Keimer, Lukas Ahrenbeck, Björn Mehrtens, David Schürenkamp, Boris Schröder, and Nils Goseberg
EGUsphere, https://doi.org/10.5194/egusphere-2024-2688, https://doi.org/10.5194/egusphere-2024-2688, 2024
Short summary
Short summary
This study analysed seasonal biomechanical traits of marram grass at two coastal dune sites using monthly field and lab data acquired 2022. Differences in density, leaf length, and flower stems were observed, which are unaffected by wind and deemed transferable. These findings enable surrogate model development for numerical and physical experiments alike, where live vegetation is impractical. Results address the knowledge gap how dune stability and erosion resistance are affected by vegetation.
Juditha Aga, Livia Piermattei, Luc Girod, Kristoffer Aalstad, Trond Eiken, Andreas Kääb, and Sebastian Westermann
Earth Surf. Dynam., 12, 1049–1070, https://doi.org/10.5194/esurf-12-1049-2024, https://doi.org/10.5194/esurf-12-1049-2024, 2024
Short summary
Short summary
Coastal rock cliffs on Svalbard are considered to be fairly stable; however, long-term trends in coastal-retreat rates remain unknown. This study examines changes in the coastline position along Brøggerhalvøya, Svalbard, using aerial images from 1970, 1990, 2010, and 2021. Our analysis shows that coastal-retreat rates accelerate during the period 2010–2021, which coincides with increasing storminess and retreating sea ice.
Aaron T. Steelquist, Gustav B. Seixas, Mary L. Gillam, Sourav Saha, Seulgi Moon, and George E. Hilley
Earth Surf. Dynam., 12, 1071–1089, https://doi.org/10.5194/esurf-12-1071-2024, https://doi.org/10.5194/esurf-12-1071-2024, 2024
Short summary
Short summary
The rates at which rivers erode their bed can be used to interpret the geologic history of a region. However, these rates depend significantly on the time window over which you measure. We use multiple dating methods to determine an incision rate for the San Juan River and compare it to regional rates with longer timescales. We demonstrate how specific geologic events, such as cutoffs of bedrock meander bends, are likely to preserve material we can date but also bias the rates we measure.
Jingqiu Huang and Hugh D. Sinclair
EGUsphere, https://doi.org/10.5194/egusphere-2024-2600, https://doi.org/10.5194/egusphere-2024-2600, 2024
Short summary
Short summary
This study uses radar technology to track tiny changes in riverbeds elevation in Himalayan Rivers as they flow onto the Gangetic Plains. By analyzing data from 2016 to 2021, we found that sediment builds up in seasonally dry (ephemeral) rivers during monsoon seasons, while the surrounding floodplains is sinking. This research is important for understanding how these elevation changes affect flood risks in rapidly growing communities in Nepal and India. Our findings can improve flood management.
Mirjam Schaller, Daniel Peifer, Alexander B. Neely, Thomas Bernard, Christoph Glotzbach, Alexander R. Beer, and Todd A. Ehlers
EGUsphere, https://doi.org/10.5194/egusphere-2024-2729, https://doi.org/10.5194/egusphere-2024-2729, 2024
Short summary
Short summary
This study reports chemical weathering, physical erosion, and total denudation rates from river load data in the Swabian Alb, Southwest Germany. Tributaries to the Neckar River draining to the North show higher rates than tributaries draining to the South into the Danube River causing a retreat of the Swabian Alb escarpment. Observations are discussed in the light of lithology, climate, and topography. The data are further compared to other rates over space and time as well as to global data.
Riccardo Bonomelli, Marco Pilotti, and Gabriele Farina
EGUsphere, https://doi.org/10.5194/egusphere-2024-2267, https://doi.org/10.5194/egusphere-2024-2267, 2024
Short summary
Short summary
Debris flows are fundamental components of the hazard in mountain regions and numerical models must be used for the related risk computation. Most existing commercial software strongly conceptualizes the main characteristics of the flow, leading to an inevitable calibration process, that is time-consuming and difficult to accomplish. This contribution offers some physically based solutions to confine the calibration process and to better understand the implications of the selected choice.
Johannes Leinauer, Michael Dietze, Sibylle Knapp, Riccardo Scandroglio, Maximilian Jokel, and Michael Krautblatter
Earth Surf. Dynam., 12, 1027–1048, https://doi.org/10.5194/esurf-12-1027-2024, https://doi.org/10.5194/esurf-12-1027-2024, 2024
Short summary
Short summary
Massive rock slope failures are a significant alpine hazard and change the Earth's surface. Therefore, we must understand what controls the preparation of such events. By correlating 4 years of slope displacements with meteorological and seismic data, we found that water from rain and snowmelt is the most important driver. Our approach is applicable to similar sites and indicates where future climatic changes, e.g. in rain intensity and frequency, may alter the preparation of slope failure.
Julien Coatléven and Benoit Chauveau
Earth Surf. Dynam., 12, 995–1026, https://doi.org/10.5194/esurf-12-995-2024, https://doi.org/10.5194/esurf-12-995-2024, 2024
Short summary
Short summary
The aim of this paper is to explain how to incorporate classical water flow routines into landscape evolution models while keeping numerical errors under control. The key idea is to adapt filtering strategies to eliminate anomalous numerical errors and mesh dependencies, as confirmed by convergence tests with analytic solutions. The emergence of complex geomorphic structures is now driven exclusively by nonlinear heterogeneous physical processes rather than by random numerical artifacts.
Jingjuan Li, John D. Jansen, Xuanmei Fan, Zhiyong Ding, Shugang Kang, and Marco Lovati
Earth Surf. Dynam., 12, 953–971, https://doi.org/10.5194/esurf-12-953-2024, https://doi.org/10.5194/esurf-12-953-2024, 2024
Short summary
Short summary
In this study, we investigated the geomorphology, sedimentology, and chronology of Tuanjie (seven terraces) and Taiping (three terraces) terraces in Diexi, eastern Tibetan Plateau. Results highlight that two damming and three outburst events occurred in the area during the late Pleistocene, and the outburst floods have been a major factor in the formation of tectonically active mountainous river terraces. Tectonic activity and climatic changes play a minor role.
Hanne Hendrickx, Xabier Blanch, Melanie Elias, Reynald Delaloye, and Anette Eltner
EGUsphere, https://doi.org/10.5194/egusphere-2024-2570, https://doi.org/10.5194/egusphere-2024-2570, 2024
Short summary
Short summary
This study introduces a novel AI-based method to track and analyse the movement of rock glaciers and landslides, key indicators of permafrost dynamics in high mountain regions. Using time-lapse images, our approach provides detailed velocity data, revealing patterns that traditional methods miss. This cost-effective tool enhances our ability to monitor geohazards, offering insights into climate change impacts on permafrost and improving safety in alpine areas.
Andrew Hollyday, Maureen E. Raymo, Jacqueline Austermann, Fred Richards, Mark Hoggard, and Alessio Rovere
Earth Surf. Dynam., 12, 883–905, https://doi.org/10.5194/esurf-12-883-2024, https://doi.org/10.5194/esurf-12-883-2024, 2024
Short summary
Short summary
Sea level was significantly higher during the Pliocene epoch, around 3 million years ago. The present-day elevations of shorelines that formed in the past provide a data constraint on the extent of ice sheet melt and the global sea level response under warm Pliocene conditions. In this study, we identify 10 escarpments that formed from wave-cut erosion during Pliocene times and compare their elevations with model predictions of solid Earth deformation processes to estimate past sea level.
Gregory A. Ruetenik, Ken L. Ferrier, and Odin Marc
Earth Surf. Dynam., 12, 863–881, https://doi.org/10.5194/esurf-12-863-2024, https://doi.org/10.5194/esurf-12-863-2024, 2024
Short summary
Short summary
Fluvial sediment fluxes increased dramatically in Taiwan during Typhoon Morakot in 2009, which produced some of the heaviest landsliding on record. We analyzed fluvial discharge and suspended sediment concentration data at 87 gauging stations across Taiwan to quantify fluvial sediment responses since Morakot. In basins heavily impacted by landsliding, rating curve coefficients sharply increased during Morakot and then declined exponentially with a characteristic decay time of <10 years.
Nil Carrion-Bertran, Albert Falqués, Francesca Ribas, Daniel Calvete, Rinse de Swart, Ruth Durán, Candela Marco-Peretó, Marta Marcos, Angel Amores, Tim Toomey, Àngels Fernández-Mora, and Jorge Guillén
Earth Surf. Dynam., 12, 819–839, https://doi.org/10.5194/esurf-12-819-2024, https://doi.org/10.5194/esurf-12-819-2024, 2024
Short summary
Short summary
The sensitivity to the wave and sea-level forcing sources in predicting a 6-month embayed beach evolution is assessed using two different morphodynamic models. After a successful model calibration using in situ data, other sources are applied. The wave source choice is critical: hindcast data provide wrong results due to an angle bias, whilst the correct dynamics are recovered with the wave conditions from an offshore buoy. The use of different sea-level sources gives no significant differences.
Thomas J. Barnes, Thomas V. Schuler, Simon Filhol, and Karianne S. Lilleøren
Earth Surf. Dynam., 12, 801–818, https://doi.org/10.5194/esurf-12-801-2024, https://doi.org/10.5194/esurf-12-801-2024, 2024
Short summary
Short summary
In this paper, we use machine learning to automatically outline landforms based on their characteristics. We test several methods to identify the most accurate and then proceed to develop the most accurate to improve its accuracy further. We manage to outline landforms with 65 %–75 % accuracy, at a resolution of 10 m, thanks to high-quality/high-resolution elevation data. We find that it is possible to run this method at a country scale to quickly produce landform inventories for future studies.
Eric Petersen, Regine Hock, and Michael G. Loso
Earth Surf. Dynam., 12, 727–745, https://doi.org/10.5194/esurf-12-727-2024, https://doi.org/10.5194/esurf-12-727-2024, 2024
Short summary
Short summary
Ice cliffs are melt hot spots that increase melt rates on debris-covered glaciers which otherwise see a reduction in melt rates. In this study, we show how surface runoff streams contribute to the generation, evolution, and survival of ice cliffs by carving into the glacier and transporting rocky debris. On Kennicott Glacier, Alaska, 33 % of ice cliffs are actively influenced by streams, while nearly half are within 10 m of streams.
Daniel O'Hara, Liran Goren, Roos M. J. van Wees, Benjamin Campforts, Pablo Grosse, Pierre Lahitte, Gabor Kereszturi, and Matthieu Kervyn
Earth Surf. Dynam., 12, 709–726, https://doi.org/10.5194/esurf-12-709-2024, https://doi.org/10.5194/esurf-12-709-2024, 2024
Short summary
Short summary
Understanding how volcanic edifices develop drainage basins remains unexplored in landscape evolution. Using digital evolution models of volcanoes with varying ages, we quantify the geometries of their edifices and associated drainage basins through time. We find that these metrics correlate with edifice age and are thus useful indicators of a volcano’s history. We then develop a generalized model for how volcano basins develop and compare our results to basin evolution in other settings.
Brayden Noh, Omar Wani, Kieran B. J. Dunne, and Michael P. Lamb
Earth Surf. Dynam., 12, 691–708, https://doi.org/10.5194/esurf-12-691-2024, https://doi.org/10.5194/esurf-12-691-2024, 2024
Short summary
Short summary
In this paper, we propose a framework for generating risk maps that provide the probabilities of erosion due to river migration. This framework uses concepts from probability theory to learn the river migration model's parameter values from satellite data while taking into account parameter uncertainty. Our analysis shows that such geomorphic risk estimation is more reliable than models that do not explicitly consider various sources of variability and uncertainty.
Cited articles
Antolínez, J. A., Méndez, F. J., Anderson, D., Ruggiero, P., and Kaminsky, G. M.: Predicting climate-driven coastlines with a simple and efficient multiscale model, J. Geophys. Res.-Earth, 124, 1596–1624, https://doi.org/10.1029/2018JF004790, 2019. a
Biondi, D., Freni, G., Iacobellis, V., Mascaro, G., and Montanari, A.: Validation of hydrological models: Conceptual basis, methodological approaches and a proposal for a code of practice, Phys. Chem. Earth Pt. a/b/c, 42–44, 70–76, https://doi.org/10.1016/j.pce.2011.07.037, 2012. a
Blossier, B., Bryan, K. R., Daly, C. J., and Winter, C.: Shore and bar cross-shore migration, rotation, and breathing processes at an embayed beach, J. Geophys. Res.-Earth, 122, 1745–1770, https://doi.org/10.1002/2017JF004227, 2017. a, b
Booij, N., Ris, R. C., and Holthuijsen, L. H.: A third-generation wave model for coastal regions. 1. Model description and validation, J. Geophys. Res., 104, 7649–7666, https://doi.org/10.1029/98JC02622, 1999. a
Buscombe, D. and Goldstein, E. B.: A reproducible and reusable pipeline for segmentation of geoscientific imagery, Earth Space Sci., 9, e2022EA002332, https://doi.org/10.1029/2022EA002332, 2022. a
Buscombe, D., Wernette, P., Fitzpatrick, S., Favela, J., Goldstein, E. B., and Enwright, N. M.: A 1.2 Billion Pixel Human-Labeled Dataset for Data-Driven Classification of Coastal Environments, Sci. Data, 10, 46, https://doi.org/10.1038/s41597-023-01929-2, 2023. a
Cagigal, L., Rueda, A., Anderson, D., Ruggiero, P., Merrifield, M. A., Montaño, J., Coco, G., and Méndez, F. J.: A multivariate, stochastic, climate-based wave emulator for shoreline change modelling, Ocean Model., 154, 101695, https://doi.org/10.1016/j.ocemod.2020.101695, 2020. a
Calkoen, F., Luijendijk, A., Rivero, C. R., Kras, E., and Baart, F.: Traditional vs. machine-learning methods for forecasting sandy shoreline evolution using historic satellite-derived shorelines, Remote Sens., 13, 934, https://doi.org/10.3390/rs13050934, 2021. a
Camus, P., Losada, I., Izaguirre, C., Espejo, A., Menéndez, M., and Pérez, J.: Statistical wave climate projections for coastal impact assessments, Earth's Future, 5, 918–933, https://doi.org/10.1002/2017EF000609, 2017. a
Castelle, B. and Harley, M.: Extreme events: Impact and recovery, in: Sandy Beach Morphodynamics, Elsevier, 533–556, https://doi.org/10.1016/B978-0-08-102927-5.00022-9, 2020. a
Castelle, B., Dodet, G., Masselink, G., and Scott, T.: A new climate index controlling winter wave activity along the Atlantic coast of Europe: The West Europe Pressure Anomaly, Geophys. Res. Lett., 44, 1384–1392, https://doi.org/10.1002/2016GL072379, 2017. a, b
Cooper, J. and McKenna, J.: Social justice in coastal erosion management: The temporal and spatial dimensions, Geoforum, 39, 294–306, https://doi.org/10.1016/j.geoforum.2007.06.007, 2008. a
Davidson, M. and Turner, I.: A behavioral template beach profile model for predicting seasonal to interannual shoreline evolution, J. Geophys. Res.-Earth, 114, F01020, https://doi.org/10.1029/2007JF000888, 2009. a
Duveiller, G., Fasbender, D., and Meroni, M.: Revisiting the concept of a symmetric index of agreement for continuous datasets, Sci. Rep., 6, 1–14, https://doi.org/10.1038/srep19401, 2016. a, b, c, d
Ellenson, A. N., Simmons, J. A., Wilson, G. W., Hesser, T. J., and Splinter, K. D.: Beach State Recognition Using Argus Imagery and Convolutional Neural Networks, Remote Sens., 12, 3953, https://doi.org/10.3390/rs12233953, 2020. a
Elsayed, S. M. and Oumeraci, H.: Effect of beach slope and grain-stabilization on coastal sediment transport: An attempt to overcome the erosion overestimation by XBeach, Coas. Eng., 121, 179–196, https://doi.org/10.1016/j.coastaleng.2016.12.009, 2017. a
Gers, F. A., Schmidhuber, J., and Cummins, F.: Learning to forget: Continual prediction with LSTM, Neural Comput., 12, 2451–2471, https://doi.org/10.1162/089976600300015015, 2000. a
Goldstein, E. B., Coco, G., and Plant, N. G.: A review of machine learning applications to coastal sediment transport and morphodynamics, Earth-Sci. Rev., 194, 97–108, https://doi.org/10.1016/j.earscirev.2019.04.022, 2019. a, b, c
Gomez-de la Pena, E.: eduardogomezdelapena/DL_shoreline_prediction: Code release with paper publication (Version 1), Zenodo [code and data set], https://doi.org/10.5281/zenodo.10088350, 2023. a
Goodfellow, I., Bengio, Y., and Courville, A.: Deep Learning, MIT Press, https://doi.org/10.1007/s10710-017-9314-z, 2016. a
Guedes, R. M. C., Bryan, K. R., Coco, G., and Holman, R. A.: The effects of tides on swash statistics on an intermediate beach, J. Geophys. Res.-Oceans, 116, C04008, https://doi.org/10.1029/2010JC006660, 2011. a
Gupta, M., Kodamana, H., and Sandeep, S.: Prediction of ENSO Beyond Spring Predictability Barrier Using Deep Convolutional LSTM Networks, IEEE Geosci. Remote Sens. Lett., 19, 1–5, https://doi.org/10.1109/LGRS.2020.3032353, 2022. a
Harley, M. D., Turner, I. L., Short, A. D., and Ranasinghe, R.: Interannual variability and controls of the Sydney wave climate, Int. J. Climatol., 30, 1322–1335, https://doi.org/10.1002/joc.1962, 2010. a
Hinton, G., Deng, L., Yu, D., Dahl, G. E., Mohamed, A.-r., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., and Sainath, T. N.: Deep neural networks for acoustic modelling in speech recognition: The shared views of four research groups, IEEE Sig. Process. Mag., 29, 82–97, https://doi.org/10.1109/MSP.2012.2205597, 2012a. a
Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R. R.: Improving neural networks by preventing co-adaptation of feature detectors, arXiv [preprint], https://doi.org/10.48550/arXiv.1207.0580, 2012b. a
Hochreiter, S. and Schmidhuber, J.: Long Short-Term Memory, Neural Comput., 9, 1735–1780, https://doi.org/10.1162/neco.1997.9.8.1735, 1997. a
Ibaceta, R., Splinter, K. D., Harley, M. D., and Turner, I. L.: Improving multi-decadal coastal shoreline change predictions by including model parameter non-stationarity, Front. Mar. Sci., 9, 1012041, https://doi.org/10.3389/fmars.2022.1012041, 2022. a
Ismail Fawaz, H., Forestier, G., Weber, J., Idoumghar, L., and Muller, P.-A.: Deep learning for time series classification: a review, Data Min. Knowl. Discov., 33, 917–963, https://doi.org/10.1007/s10618-019-00619-1, 2019. a
Jaramillo, C., Jara, M. S., González, M., and Medina, R.: A shoreline evolution model considering the temporal variability of the beach profile sediment volume (sediment gain/loss), Coast. Eng., 156, 103612, https://doi.org/10.1016/j.coastaleng.2019.103612, 2020. a
Jaramillo, C., González, M., Medina, R., and Turki, I.: An equilibrium-based shoreline rotation model, Coast. Eng., 163, 103789, https://doi.org/10.1016/j.coastaleng.2020.103789, 2021. a
Kobayashi, N., Buck, . M., Payo, . A., and Johnson, B. D.: Berm and Dune Erosion during a Storm, J. Waterway Port Coast. Ocean Eng., 135, 1–10, https://doi.org/0.1061/(ASCE)0733-950X(2009)135:1(1), 2009. a
Kratzert, F., Klotz, D., Brenner, C., Schulz, K., and Herrnegger, M.: Rainfall–runoff modelling using long short-term memory (LSTM) networks, Hydrol. Earth Syst. Sci., 22, 6005–6022, https://doi.org/10.5194/hess-22-6005-2018, 2018. a
Krizhevsky, A., Sutskever, I., and Hinton, G. E.: Imagenet classification with deep convolutional neural networks, Adv. Neural Inform. Process. Syst., 25, 1097–1105, https://doi.org/10.1145/3065386, 2012. a, b
Larochelle, H., Bengio, Y., Louradour, J., and Lamblin, P.: Exploring strategies for training deep neural networks, J. Mach. Learn. Res., 10, 1–40, 2009. a
LeCun, Y., Boser, B., Denker, J., Henderson, D., Howard, R., Hubbard, W., and Jackel, L.: Handwritten digit recognition with a back-propagation network, Adv. Neural Inform. Process. Syst., 2, 396–404, 1989. a
LeCun, Y., Bengio, Y., and Hinton, G.: Deep learning, Nature, 521, 436–444, https://doi.org/10.1038/nature14539, 2015. a, b
Lees, T., Reece, S., Kratzert, F., Klotz, D., Gauch, M., De Bruijn, J., Kumar Sahu, R., Greve, P., Slater, L., and Dadson, S. J.: Hydrological concept formation inside long short-term memory (LSTM) networks, Hydrol. Earth Syst. Sci., 26, 3079–3101, https://doi.org/10.5194/hess-26-3079-2022, 2022. a
Lim, C., Kim, T.-K., and Lee, J.-L.: Evolution model of shoreline position on sandy, wave-dominated beaches, Geomorphology, 415, 108409, https://doi.org/10.1016/j.geomorph.2022.108409, 2022. a
Lu, W.-S., Tseng, C.-H., Hsiao, S.-C., Chiang, W.-S., and Hu, K.-C.: Future Projection for Wave Climate around Taiwan Using Weather-Type Statistical Downscaling Method, J. Mar. Sci. Eng., 10, 1823, https://doi.org/10.3390/jmse10121823, 2022. a
Luijendijk, A., Hagenaars, G., Ranasinghe, R., Baart, F., Donchyts, G., and Aarninkhof, S.: The state of the world's beaches, Sci. Rep., 8, 1–11, https://doi.org/10.1038/s41598-018-24630-6, 2018. a
Luijendijk, A., de Schipper, M., and Ranasinghe, R.: Morphodynamic acceleration techniques for multi-timescale predictions of complex sandy interventions, J. Mar. Sci. Eng., 7, 78, https://doi.org/10.3390/jmse7030078, 2019. a
McCall, R. T., De Vries, J. V. T., Plant, N., Van Dongeren, A., Roelvink, J., Thompson, D., and Reniers, A.: Two-dimensional time dependent hurricane overwash and erosion modelling at Santa Rosa Island, Coast. Eng., 57, 668–683, https://doi.org/10.1016/j.coastaleng.2010.02.006, 2010. a
McCarroll, R. J., Masselink, G., Valiente, N. G., Scott, T., Wiggins, M., Kirby, J.-A., and Davidson, M.: A rules-based shoreface translation and sediment budgeting tool for estimating coastal change: ShoreTrans, Mar. Geol., 435, 106466, https://doi.org/10.1016/j.margeo.2021.106466, 2021. a
Mentaschi, L., Vousdoukas, M. I., Pekel, J.-F., Voukouvalas, E., and Feyen, L.: Global long-term observations of coastal erosion and accretion, Sci. Rep., 8, 1–11, https://doi.org/10.1038/s41598-018-30904-w, 2018. a
Miller, J. K. and Dean, R. G.: A simple new shoreline change model, Coast. Eng., 51, 531–556, https://doi.org/10.1016/j.coastaleng.2004.05.006, 2004. a
Murray, A. B.: Which Models Are Good (Enough), and When?, in: Treatise on Geomorphology, vol. 2, Elsevier Inc., 50–58, https://doi.org/10.1016/B978-0-12-374739-6.00027-0, 2013. a
Pape, L., Ruessink, B. G., Wiering, M. A., and Turner, I. L.: Recurrent neural network modelling of nearshore sandbar behavior, Neural Networks, 20, 509–518, https://doi.org/10.1016/j.neunet.2007.04.007, 2007. a
Pape, L., Kuriyama, Y., and Ruessink, B.: Models and scales for cross-shore sandbar migration, J. Geophys. Res.-Earth, 115, F03043, https://doi.org/10.1029/2009JF001644, 2010. a, b, c
Pérez, J., Méndez, F. J., Menéndez, M., and Losada, I. J.: ESTELA: a method for evaluating the source and travel time of the wave energy reaching a local area, Ocean Dynam., 64, 1181–1191, https://doi.org/10.1007/s10236-014-0740-7, 2014. a
Rampal, N., Shand, T., Wooler, A., and Rautenbach, C.: Interpretable Deep Learning Applied to Rip Current Detection and Localization, Remote Sens., 14, 6048, https://doi.org/10.3390/rs14236048, 2022. a
Ranasinghe, R.: Assessing climate change impacts on open sandy coasts: A review, Earth-Sci. Rev., 160, 320–332, https://doi.org/10.1016/j.earscirev.2016.07.011, 2016. a
Ranasinghe, R.: On the need for a new generation of coastal change models for the 21st century, Sci. Rep., 10, 2010, https://doi.org/10.1038/s41598-020-58376-x, 2020. a
Reichstein, M., Camps-Valls, G., Stevens, B., Jung, M., Denzler, J., and Carvalhais, N.: Deep learning and process understanding for data-driven Earth system science, Nature, 566, 195–204, https://doi.org/10.1038/s41586-019-0912-1, 2019. a, b, c, d
Robinet, A., Castelle, B., Idier, D., Le Cozannet, G., Déqué, M., and Charles, E.: Statistical modelling of interannual shoreline change driven by North Atlantic climate variability spanning 2000–2014 in the Bay of Biscay, Geo-Mar. Lett., 36, 479–490, https://doi.org/10.1007/s00367-016-0460-8, 2016. a
Roelvink, D., Reniers, A., van Dongeren, A., van Thiel de Vries, J., McCall, R., and Lescinski, J.: Modelling storm impacts on beaches, dunes and barrier islands, Coast. Eng., 56, 1133–1152, https://doi.org/10.1016/j.coastaleng.2009.08.006, 2009. a
Serafin, K. A. and Ruggiero, P.: Simulating extreme total water levels using a time-dependent, extreme value approach, J. Geophys. Res.-Oceans, 119, 6305–6329, https://doi.org/10.1002/2014JC010093, 2014. a
Sherwood, C. R., Van Dongeren, A., Doyle, J., Hegermiller, C. A., Hsu, T.-J., Kalra, T. S., Olabarrieta, M., Penko, A. M., Rafati, Y., and Roelvink, D.: modelling the morphodynamics of coastal responses to extreme events: what shape are we in?, Annu. Rev. Mar. Sci., 14, 457–492, https://doi.org/10.1146/annurev-marine-032221-090215, 2022. a
Shi, X., Chen, Z., Wang, H., Yeung, D.-Y., Wong, W.-K., and Woo, W.-C.: Convolutional LSTM network: A machine learning approach for precipitation nowcasting, in: Advances in Neural Information Processing Systems, vol. 28, edited by: Cortes, C., Lawrence, N., Lee, D., Sugiyama, M., and Garnett, R., Curran Associates, Inc., ISBN 9781510825024, 2015. a
Silva, A., Klein, A., Fetter-Filho, A., Hein, C. J., Méndez, F., Broggio, M., and Dalinghaus, C.: Climate-induced variability in South Atlantic wave direction over the past three millennia, Sci. Rep., 10, 18553, https://doi.org/10.1038/s41598-020-75265-5, 2020. a
Sit, M., Demiray, B. Z., Xiang, Z., Ewing, G. J., Sermet, Y., and Demir, I.: A comprehensive review of deep learning applications in hydrology and water resources, Water Sci. Technol., 82, 2635–2670, https://doi.org/10.2166/wst.2020.369, 2020. a
Splinter, K. D., Turner, I. L., Davidson, M. A., Barnard, P., Castelle, B., and Oltman-Shay, J.: A generalized equilibrium model for predicting daily to interannual shoreline response, J. Geophys. Res.-Earth, 119, 1936–1958, https://doi.org/10.1002/2014JF003106, 2014. a
Taylor, K. E.: Summarizing multiple aspects of model performance in a single diagram, J. Geophys. Res.-Atmos., 106, 7183–7192, https://doi.org/10.1029/2000JD900719, 2001. a, b
Toimil, A., Losada, I. J., Camus, P., and Díaz-Simal, P.: Managing coastal erosion under climate change at the regional scale, Coast. Eng., 128, 106–122, https://doi.org/10.1016/j.coastaleng.2017.08.004, 2017. a
Van, S. P., Le, H. M., Thanh, D. V., Dang, T. D., Loc, H. H., and Anh, D. T.: Deep learning convolutional neural network in rainfall–runoff modelling, J. Hydroinform., 22, 541–561, https://doi.org/10.2166/hydro.2020.095, 2020. a
Vitousek, S., Barnard, P. L., Limber, P., Erikson, L., and Cole, B.: A model integrating longshore and cross-shore processes for predicting long-term shoreline response to climate change, J. Geophys. Res.-Earth, 122, 782–806, https://doi.org/10.1002/2016JF004065, 2017. a, b, c
Vitousek, S., Cagigal, L., Montaño, J., Rueda, A., Mendez, F., Coco, G., and Barnard, P. L.: The application of ensemble wave forcing to quantify uncertainty of shoreline change predictions, J. Geophys. Res.-Earth, 126, e2019JF005506, https://doi.org/10.1029/2019JF005506, 2021. a
Vos, K., Harley, M. D., Turner, I. L., and Splinter, K. D.: Pacific shoreline erosion and accretion patterns controlled by El Niño/Southern Oscillation, Nat. Geosci., 16, 140–146, https://doi.org/10.1038/s41561-022-01117-8, 2023. a, b
Wang, N., Chen, Q., and Chen, Z.: Reconstruction of nearshore wave fields based on physics-informed neural networks, Coast. Eng., 176, 104167, https://doi.org/10.1016/j.coastaleng.2022.104167, 2022. a
Wright, L. D. and Short, A. D.: Morphodynamic variability of surf zones and beaches: a synthesis, Mar. Geol., 56, 93–118, https://doi.org/10.1016/0025-3227(84)90008-2, 1984. a
Xu, T., Coco, G., and Neale, M.: A predictive model of recreational water quality based on adaptive synthetic sampling algorithms and machine learning, Water Res., 177, 115788, https://doi.org/10.1016/j.watres.2020.115788, 2020. a
Yan, B., Zhang, Q.-H., and Wai, O. W.: Prediction of sand ripple geometry under waves using an artificial neural network, Comput. Geosci., 34, 1655–1664, https://doi.org/10.1016/j.cageo.2008.03.002, 2008. a
Yates, M. L., Guza, R. T., and O'reilly, W. C.: Equilibrium shoreline response: Observations and modelling, J. Geophys. Res, 114, 9014, https://doi.org/10.1029/2009JC005359, 2009. a, b
Yoon, H.-D., Cox, D. T., and Kim, M.: Prediction of time-dependent sediment suspension in the surf zone using artificial neural network, Coast. Eng., 71, 78–86, https://doi.org/10.1016/j.coastaleng.2012.08.005, 2013. a
Zhang, K., Geng, X., and Yan, X.-H.: Prediction of 3-D Ocean Temperature by Multilayer Convolutional LSTM, IEEE Geosci. Remote Sens. Lett., 17, 1303–1307, https://doi.org/10.1109/LGRS.2019.2947170, 2020. a
Short summary
Predicting how shorelines change over time is a major challenge in coastal research. We here have turned to deep learning (DL), a data-driven modelling approach, to predict the movement of shorelines using observations from a camera system in New Zealand. The DL models here implemented succeeded in capturing the variability and distribution of the observed shoreline data. Overall, these findings indicate that DL has the potential to enhance the accuracy of current shoreline change predictions.
Predicting how shorelines change over time is a major challenge in coastal research. We here...
