Earth Surface Processes and Landforms最新文献

{"title":"Improving hydroacoustic methods for monitoring suspended-sand flux and grain size in sediment-laden rivers","authors":"Jessica Marggraf,&nbsp;Jérôme Le Coz,&nbsp;Benoît Camenen,&nbsp;François Lauters,&nbsp;Guillaume Dramais,&nbsp;Gilles Pierrefeu,&nbsp;David J. Topping","doi":"10.1002/esp.6056","DOIUrl":"https://doi.org/10.1002/esp.6056","url":null,"abstract":"<p>Suspended-sand concentration and grain-size data in rivers provide valuable information on the catchment's dynamics for scientists and river managers. Producing continuous measurements of suspended-sand concentrations remains a scientific challenge due to their high spatial and temporal variability. Traditional methods such as sediment-rating curves may be highly uncertain, and optical turbidity is insensitive to coarse particles when there are many fine particles. Surrogate hydroacoustic methods aim to improve sand concentration measurements. These single- or dual-frequency acoustic methods use acoustic attenuation and/or backscatter to estimate fine-sediment (i.e., silt and clay) and/or sand concentration and possibly grain size. New methods have recently been developed and applied in rivers exhibiting a wide range of sediment conditions in North America but not independently tested elsewhere by other researchers. In this article, we apply, adapt and evaluate hydroacoustic methods to continuously estimate suspended-sand concentration and grain size in an Alpine river with high suspended-sediment concentrations. From the example of the River Isère at Grenoble Campus, France, we show that the hydroacoustic methods adapted to local conditions may yield valuable sand concentration estimates consistent with traditional measurements. Compared with prior knowledge, limited additional information on the grain size can be obtained due to high uncertainties. Hydroacoustic concentration estimates are more sensitive to real changes in concentration at the event scale than traditional rating-curve methods that relate concentration to discharge only. These findings open the perspective for facilitated sand concentration monitoring at a higher temporal resolution with decreased field work.</p>","PeriodicalId":11408,"journal":{"name":"Earth Surface Processes and Landforms","volume":"50 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/esp.6056","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143118684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Disintegration characteristics of undisturbed loess in response to train vibration frequency","authors":"Shan Li,&nbsp;Jiading Wang,&nbsp;Dengfei Zhang,&nbsp;Li Wang,&nbsp;Lirong Qi,&nbsp;Tao Xiao,&nbsp;Kai Han,&nbsp;Qinghua Wang","doi":"10.1002/esp.6070","DOIUrl":"https://doi.org/10.1002/esp.6070","url":null,"abstract":"<p>Disintegration fragments the loess body, causing erosion and the emergence of significant geohazards. The impact of vibrations on soil disintegration has been slightly documented; however, the contribution and mechanism of train vibration frequency in the disintegration of undisturbed loess remain unclear. In this study, train vibrations were monitored in situ, and the resulting vibrational parameters were used in loess disintegration tests using a customised vibration-disintegration apparatus. The changes in the meso-parameters of the disintegrated loess and aqueous solutions were quantified, and the microstructural differences in the residual loess after disintegration were compared under non-vibrating and vibrating conditions. The results revealed that train vibrations in the loess progressively diminished with increasing distance from the track, with dominant vibration frequencies ranging from 17 to 49 Hz. Increasing the vibration frequency accelerated loess disintegration and enhanced the dispersion of the disintegrated fragments. Notably, the acceleration effect of disintegration was particularly pronounced in the early stages of increasing vibration frequency, and it tended to plateau above 15 Hz. The relationship between the vibration frequency and disintegration velocity (<i>DV</i>) of loess influenced by the initial water content can be expressed as a power function with variables. Vibrations accelerate loess disintegration primarily attributed to repetitive particle displacement and the vibrations of free water in the pores which lead to frictional damage to the weakly cemented structure and pore expansion. Higher vibration frequencies generate greater inertial forces and facilitate more frequent particle jumps, allowing the loess to reach the disintegration threshold conditions more readily than at lower frequencies. These findings provide theoretical value for the prevention and mitigation of water-induced loess geohazards and land degradation in vibrating environments.</p>","PeriodicalId":11408,"journal":{"name":"Earth Surface Processes and Landforms","volume":"50 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143117743","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hysteretic response of suspended-sediment in wildfire affected watersheds of the Pacific Northwest and Southern Rocky Mountains","authors":"Gregory D. Clark,&nbsp;Sheila F. Murphy,&nbsp;Katherine Skalak,&nbsp;David W. Clow,&nbsp;Garrett Akie,&nbsp;Kurt D. Carpenter,&nbsp;Sean E. Payne,&nbsp;Brian A. Ebel","doi":"10.1002/esp.6067","DOIUrl":"https://doi.org/10.1002/esp.6067","url":null,"abstract":"<p>Wildfires can have a profound impact on hydrosedimentary interactions, or the relationship between sediment and runoff, in forested headwater streams. Quantification of sediment-runoff dynamics at the event scale is integral for understanding source areas and transport of suspended-sediment through a watershed following wildfire. Here we used high-frequency turbidity and stream discharge data, coupled with discrete suspended-sediment measurements, in burned and unburned watersheds in the Southern Rocky Mountains and the western Cascades Range to evaluate the response of fine-grained (clay- and silt-sized particles) suspended-sediment. Hysteresis analysis was conducted on estimated suspended-sediment concentrations (using turbidity as a proxy) and streamflow through measurement of the difference in sediment concentration on the rising and falling limbs of the event hydrograph. All burned watersheds exhibited elevated fine suspended-sediment concentrations relative to concentrations found in pre-fire conditions. Changes to hysteretic response vary and may depend on a watershed's sediment connectivity limitations. Results suggest a watershed's inherent hillslope-to-channel (or lateral) connectivity is the primary factor controlling the relative magnitude of event-driven fine sediment fluxes in watersheds affected by wildfire. While wildfire did promote lateral connectivity through activation of hillslope sources, snowmelt, precipitation characteristics and antecedent conditions were more important drivers of hysteretic response than wildfire. For watersheds influenced by annual snowpack, we identified a predominantly clockwise hysteretic response during snowmelt and counterclockwise events during the late spring and summer months. There were also proportionally more counterclockwise events after wildfire in watersheds with high sediment connectivity. Results suggest contrasting wildfire-related sediment risk potential. Rivers in burned watersheds with high sediment connectivity may pose a higher risk to receiving waterbodies, such as larger tributaries or reservoirs, while rivers with low sediment connectivity may experience long-term sediment-related risk within the watershed above the outlet.</p>","PeriodicalId":11408,"journal":{"name":"Earth Surface Processes and Landforms","volume":"50 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/esp.6067","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143117544","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Gully erosion susceptibility mapping in the Loess Plateau and the Northeast China Mollisol region: Optimal resolution and algorithms, influencing factors and spatial distribution","authors":"Annan Yang,&nbsp;Chunmei Wang,&nbsp;Qinke Yang,&nbsp;Guowei Pang,&nbsp;Yongqing Long,&nbsp;Lei Wang,&nbsp;Richard M. Cruse","doi":"10.1002/esp.6059","DOIUrl":"https://doi.org/10.1002/esp.6059","url":null,"abstract":"<p>Gully erosion susceptibility (GES) mapping is crucial for controlling gully erosion hazards and has become a significant focus of global research and management efforts. Machine learning models have proven effective in this field. However, in areas with different terrain complexity, the model shows significant variation in optimal resolution and algorithms, factor importance and spatial distribution of the model results, which limits their broader application. This study compares GES mapping in two small watersheds: one located in the complex terrain of the Loess Plateau and the other in the relatively flat terrain of the Northeast China Mollisol region. The model predictive accuracy was evaluated using 30% of the datasets that were excluded from model training. The results revealed that: 1) significant differences in optimal resolution of GES mapping in the two regions, which were 1–2.5 m for the Mollisol region, and 2.5–5 m for the Loess Plateau. The extreme boosting tree (XGBoost) algorithm achieved the best simulation results compared to random forest (RF) and gradient boosting decision tree (GBDT) in both regions. 2) Slope gradient and contributing area influenced gully distribution in both watersheds, with land use being critical in the Loess Plateau and distance from streams more important in the Mollisol region. 3) In the Loess Plateau watershed, 25% of the area was highly susceptible to gully erosion, while only 1% of the Mollisol watershed was highly susceptible. This research compared GES mapping in two watersheds with different terrain complexity, which would be beneficial for better use of machine learning in gully research.</p>","PeriodicalId":11408,"journal":{"name":"Earth Surface Processes and Landforms","volume":"50 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143117714","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Tectonic implications of raised Quaternary relative sea-level indicators along the NE border of the Campania Plain (southern Italy)","authors":"Ciro Cerrone,&nbsp;Marco Meschis,&nbsp;Alessandra Ascione,&nbsp;Michele Soligo,&nbsp;Paola Tuccimei,&nbsp;Jennifer Robertson,&nbsp;Gerald P. Roberts","doi":"10.1002/esp.6066","DOIUrl":"https://doi.org/10.1002/esp.6066","url":null,"abstract":"<p>Tectonically raised paleoshorelines have been recently identified along the southern fault scarps of the Mt. Fellino and Roccarainola horst blocks, which are part of the northeastern border of the Campania Plain coastal basin (southern Apennines, Italy). Such horst blocks are bounded to the south by the Polvica Fault, a roughly E-W trending normal fault. The sequence of uplifted paleoshorelines has been studied in detail by integrating geomorphological, structural and stratigraphical analyses to assess the Quaternary uplift of the Mt. Fellino and Roccarainola horst blocks. Yet, the staircase of paleoshorelines is still not chronologically well constrained.</p><p>Aimed at constraining the uplift history of Mt. Fellino and Roccarainola horst blocks and the rate of activity of the Polvica fault, in this study, we integrate former knowledge on paleoshorelines with a geomorphological analysis to map erosional terraces, that we interpret as remnants of shore platforms. We apply the synchronous correlation method, driven by new and a former ²³⁰Th/²³⁴U dating of calcite veins cutting marine sands, to infer the age of the paleoshorelines and terraces. Based on the synchronous correlation, the mapped paleoshorelines and terraces are correlated with sea-level peaks of the late Early to Late Pleistocene. In particular, the paleoshorelines along the Mt. Fellino ridge are correlated with the Marine Isotope Stage (MIS) 7e and 9c or 11, while the oldest terrace is correlated with the sea-level peak of 980 ka. Using inferred paleoshorelines ages, we estimate the uplift rate of the Polvica Fault footwall. The uplift rate varies from c. 0.2 mm/yr close to the western fault tip up to c. 0.5–0.6 mm/yr in the East, in the Roccarainola block. We combine surface evidence with subsurface data from a shallow well to constrain the vertical throw of the Polvica Fault. A mean fault throw rate of c. 0.4 mm/yr in the last c. 1 Ma is estimated for the central part of the PF. Assuming that the Polvica Fault is still active, we estimate the maximum expected earthquake by means of empirical relationship and obtain a Mw ~ 6.2 value and recurrence interval value of c. 1,200 yr. Historical seismicity activity of the PF has not been acknowledged to date. However, our results raise the crucial question of an in-depth assessment of the seismic hazard for the densely populated Campania Plain.</p>","PeriodicalId":11408,"journal":{"name":"Earth Surface Processes and Landforms","volume":"50 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/esp.6066","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143117712","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Early Pleistocene initiation of Simav Graben: Implications for widespread extension and landscape change in West Anatolia","authors":"Faruk Ocakoğlu,&nbsp;Muammer Tün,&nbsp;Eren Şahiner","doi":"10.1002/esp.6060","DOIUrl":"https://doi.org/10.1002/esp.6060","url":null,"abstract":"<p>The prevailing model of west Anatolian extension posits that the westward extrusion of Anatolia, driven by the Northern and Eastern Anatolian transform faults and slab rollback across the Hellenic Trench, governs ongoing extension from Gökova Graben to the Eskişehir Graben in Western Anatolia. However, data gaps and conflicting datasets constrain our understanding of the most recent phase of extension and the underlying geodynamic processes. To address these uncertainties, we investigated the sediment thickness and chronology of the Simav Graben (NW Anatolia) using microtremor surveys, radiocarbon dating and optically stimulated luminescence (OSL) dating from drill cores. Additionally, we examined the geomorphological characteristics of the graben and identified knickpoints along select rivers. Our findings indicate that the Simav Graben is an early Pleistocene (~1.1 Ma) structure with a maximum sediment thickness of approximately 540 m, accompanied by 900 m of maximum vertical displacement along the main bounding fault. Based on alluvial terraces, we infer an uplift rate of 1.1–1.3 mm/year for the last 85 ka, with an average long-term uplift rate of 0.8 mm/year over the graben's lifespan. Our morphological analysis reveals a series of knickpoints unrelated to lithology, beginning at 1300 m and descending to 800 m on hillslopes inclined toward the Sea of Marmara. The synchronous initiation of the Southern Splay of the Northern Anatolian Fault in the Marmara region and the Simav Graben suggests a causal relationship. We propose that the formation of the Northern Anatolian Fault in southern Marmara during the early Pleistocene triggered widespread extension in western Anatolia. Consequently, the north-flowing river networks, except for those associated with the Simav Graben, experienced regional incision.</p>","PeriodicalId":11408,"journal":{"name":"Earth Surface Processes and Landforms","volume":"50 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143117713","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Glacier thickness modelling and monitoring with geophysical data constraints: A case study on the Indren Glacier (NW Italy)","authors":"Valeria Strallo,&nbsp;Chiara Colombero,&nbsp;Fabrizio Troilo,&nbsp;Luca Mondardini,&nbsp;Alberto Godio","doi":"10.1002/esp.6068","DOIUrl":"https://doi.org/10.1002/esp.6068","url":null,"abstract":"<p>The ongoing global temperature increase has accelerated the mass loss of glaciers worldwide, with Italian alpine glaciers being particularly vulnerable due to their small size, complex geometries and exposition that implies a fast reaction to thermal and hydrological modifications. In such a frame, the Indren Glacier (Aosta Valley, north-western Italian Alps) provides a valid test site to check the thickness evolution over the last two decades (1999–2020), through an integrated approach combining historical data, on-site geophysical measurements, remote sensing surveys, modelling and temperature analysis. Using a 2018 helicopter-based photogrammetric survey and Ground Penetrating Radar (GPR) survey campaigns of 2020, we obtained new input data and constraints to build up an updated thickness model for the whole glacier through the Glacier Thickness Estimation algorithm (GlaTE). Ice thickness is indeed a key parameter to estimate the ice volume and use it as further input in evolutionary models forecasting future scenarios. As a part of this integrated approach, we also analysed remote sensing and temperature data, finding a major modification in the glacier conditions over the last decade. Further comparing these results with previous studies, we identified a significant decrease in ice thickness, and we confirmed the presence of an over-deepening in the glacier central widest part. This integrated methodology enhances our understanding of glacier dynamics and improves predictions of future changes, offering crucial insights for managing water resources and mitigating natural hazards in the alpine region.</p>","PeriodicalId":11408,"journal":{"name":"Earth Surface Processes and Landforms","volume":"50 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/esp.6068","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143117715","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reliability analysis and design of soil slopes considering spatial variability under rainfall infiltration","authors":"Wen-Qing Zhu,&nbsp;Shuang-Lin Zhao,&nbsp;Han Han,&nbsp;Lei-Lei Liu,&nbsp;Wen-Gang Zhang,&nbsp;Shao-He Zhang,&nbsp;Yung-Ming Cheng","doi":"10.1002/esp.6057","DOIUrl":"https://doi.org/10.1002/esp.6057","url":null,"abstract":"<p>Slope reliability analysis is a critical aspect of geotechnical engineering, particularly under conditions of rainfall infiltration, where the spatial variability of soil parameters can significantly affect the reliability of slopes. Traditional methods like Monte Carlo simulation are often computationally intensive, severely challenging the design of cutting slopes considering the spatial variability of multiple soil parameters. To address this challenge, this study proposes a convolutional neural network (CNN)-based surrogate model to efficiently assess the reliability of unsaturated soil slopes. The CNN model is trained to establish an implicit relationship between the random field inputs of soil parameters and the corresponding slope stability outcomes, enabling rapid calculation of the probability of failure (<i>P</i>_<i>f</i>) under varying conditions. The results indicate that as rainfall intensity increases, the <i>P</i>_<i>f</i> rises. For the same slope cutting distance, a greater slope cutting angle leads to a higher <i>P</i>_<i>f</i>. Similarly, for the same slope cutting angle, increasing the slope cutting distance results in a higher <i>P</i>_<i>f</i>; and the impact of slope cutting distance on slope reliability is more significant than that of slope cutting angle. Additionally, for various rainfall conditions and slope cutting scenarios, the CNN-based surrogate model is integrated into the full probability reliability design method, and a design response surface is used to establish the relationship between design variables and reliability responses. It is found that the proposed approach can efficiently evaluate the reliability of all design schemes. A strategy for determining the optimal slope cutting scheme is finally provided as practical guidance to meet the target reliability.</p>","PeriodicalId":11408,"journal":{"name":"Earth Surface Processes and Landforms","volume":"50 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143121048","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Antidune simulations using continuum-based models","authors":"Cristián Escauriaza,&nbsp;Megan Williams","doi":"10.1002/esp.6058","DOIUrl":"https://doi.org/10.1002/esp.6058","url":null,"abstract":"<p>The interactions of supercritical flows with sand or gravel beds in river channels or tidal inlets lead to the formation of antidunes. These bedforms are generally identified as nearly periodic sedimentary patterns of symmetrical shape that are in phase with the surface waves in the flow and have important effects on flow resistance and bedload transport. In addition, they play a fundamental role on morphodynamical processes in estuarine systems, on the scour around hydraulic infrastructure, and their bed signature can help to interpret paleofloods from sedimentary records. Despite the importance and ubiquity of antidunes in environmental flows, very few numerical simulations have captured their dynamics. In this work, we develop a model that couples the shallow-water and Exner equations in two-dimensions (2D) and demonstrate that a higher-level theory can reproduce the experimental antidune results of Pascal et al. (2021), independent of interactions at the particle scale. The flows are characterised by Froude numbers between 1.31 and 1.45, sediment diameters of <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msub>\u0000 <mrow>\u0000 <mi>d</mi>\u0000 </mrow>\u0000 <mrow>\u0000 <mn>50</mn>\u0000 </mrow>\u0000 </msub>\u0000 <mo>=</mo>\u0000 <mn>2.9</mn>\u0000 </mrow>\u0000 <annotation>$$ {d}_{50}=2.9 $$</annotation>\u0000 </semantics></math> mm and with 3° mean bed slopes. Using this information, we aim to identify the minimum requirements for a numerical model to capture in detail the migration of these bedforms. We use spectral analysis and compute statistics of bed elevation to determine the relevant temporal and spatial scales associated to the antidune propagation. The results of the model yield new insights on the mechanisms of bedform migration, providing tools to improve their description and assess the morphodynamic feedbacks.</p>","PeriodicalId":11408,"journal":{"name":"Earth Surface Processes and Landforms","volume":"50 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2024-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143120736","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine learning for surficial geologic mapping","authors":"Sarah E. Johnson,&nbsp;William C. Haneberg","doi":"10.1002/esp.6032","DOIUrl":"https://doi.org/10.1002/esp.6032","url":null,"abstract":"<p>Surficial geologic maps contribute to decisions regarding natural hazard mitigation, land-use planning and infrastructure development. However, geologic maps may not adequately convey the uncertainty inherent in the information shown. In this study, we use machine learning and lidar elevation data to produce surficial geologic maps for parts of two quadrangles in Kentucky. We measured the performance of eight supervised machine learning methods by comparing the overall accuracy and F1 scores for each geologic unit. Surficial geologic units include residuum, colluvium, alluvial and lacustrine terraces, high-level alluvial deposits and modern alluvium. The importance of 41 moving-window geomorphic variables, including slope, roughness, residual topography, curvature, topographic wetness index, vertical distance to channel network and topographic flatness, was reduced to 12 variables by ranking the importance of each variable. The gradient-boosted trees model produced the classifier with the greatest overall accuracy, producing maps with overall accuracies of 87.4% to 90.7% in areas of simple geology and 80.7% to 81.6% in areas with more complex geology. The model produced high F1 scores of up to 96.2% for colluvium but was not as good at distinguishing between units found in the same geomorphic position, such as high-level alluvium and residuum, both of which are found on ridgelines. Probability values for each geologic unit at each cell are conveyed using gradations of colour and eliminate the need for drawn boundaries between units. Machine learning may be used to create accurate surficial geologic maps in areas of simple geology; in more complex areas, highlight that additional information obtained in the field is necessary to distinguish between units.</p>","PeriodicalId":11408,"journal":{"name":"Earth Surface Processes and Landforms","volume":"50 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2024-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143119532","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}