Journal of South American Earth Sciences最新文献

{"title":"Landslide processes related to recurrent explosive eruptions in the Southern Andes of Chile (39° S)","authors":"Daniel Vásquez-Antipán ,&nbsp;Ivo Fustos-Toribio ,&nbsp;José Riffo-López ,&nbsp;Ana Cortez-Díaz ,&nbsp;Álvaro Bravo ,&nbsp;Pablo Moreno-Yaeger","doi":"10.1016/j.jsames.2025.105469","DOIUrl":"10.1016/j.jsames.2025.105469","url":null,"abstract":"<div><div>Landslides are one of the most hazardous geological processes due to their difficult-to-predict nature and destructive effects, often leading to significant loss of life, infrastructure damage, and environmental disruption. In the Southern Andes of Chile, landslides are particularly frequent and destructive due to a combination of factors, including high seismic activity, steep topography, and the presence of weak, unconsolidated pyroclastic soils. Unfortunately, the geomechanical control of landslide initiation in the Southern Andes is still poorly understood, creating a significant source of uncertainty in developing accurate landslide susceptibility or risk models. This study evaluates the geological and geotechnical factors that control the generation of landslides in pyroclastic soils using in situ data, laboratory analysis and remote sensing approaches. The study area covers the surroundings of the Mocho-Choshuenco Volcanic Complex (MCVC), one of the most explosive volcanoes in the Southern Andes. The results show that the landslides are placed on slopes covered by multiple explosive eruptions that include a period of more than 12 ka. Landslide activity is related to pyroclastic soils with significant weathering and halloysite content. In addition, the geotechnical characteristics show very light soils, with high-water retention capacity, which is vital to induce mechanical instability. The detected deformation may be associated with seasonal precipitation that would increase the pore water pressure and reduce the shear strength of the soil, promoting slow-moving landslides. The geological and geotechnical characteristics of the soils suggests that slow-moving landslides would be extended to a large part of the Southern Andes. Finally, this study contributes to improving hazard assessment to mitigate the impact of landslides on the population, infrastructures and natural resources in the Southern Andes.</div></div>","PeriodicalId":50047,"journal":{"name":"Journal of South American Earth Sciences","volume":"157 ","pages":"Article 105469"},"PeriodicalIF":1.7,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143577556","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated detection of landslide using synergizing dual Graph Convolutional Networks, googlenet, and machine learning techniques","authors":"Anuradha B ,&nbsp;Hadeel Alsolai ,&nbsp;Randa Allafi ,&nbsp;Munya A. Arasi","doi":"10.1016/j.jsames.2025.105457","DOIUrl":"10.1016/j.jsames.2025.105457","url":null,"abstract":"<div><div>This study explores a synergistic approach to automated landslide detection in Centro Fluminense, leveraging advanced deep learning and machine learning frameworks. The proposed methodology integrates dual Graph Convolutional Networks (DGCN) with GoogLeNet to analyze topographic and 175 pre-historic landslide data for precise mapping. A curated dataset of landslide and 195 topographic images underscores the novelty and effectiveness of this approach. The framework employs dual Graph Convolutional Networks to capture spatial dependencies and GoogLeNet to extract deep spatial features effectively. A machine learning model complements these networks to refine predictions through iterative learning processes. The study evaluates network modelling through DGCN and GoogLeNet, focusing on training and validation accuracy. Training datasets demonstrated consistent improvement in classification accuracy, increasing from 66% to 93%, while validation datasets achieved high precision, with values rising from 78% to 99%. The results emphasize the model's robustness and scalability in addressing spatial heterogeneity and complex topographic conditions. Performance metrics were rigorously analyzed, indicating a significant alignment with ground-truth data, as evidenced by a coefficient of determination (R²) of 0.92 and a mean absolute error (MAE) of 4%. The integration of DGCN and GoogLeNet outperformed conventional methods by capturing intricate spatial and contextual features. This comprehensive framework ensures reliable and automated detection, crucial for disaster risk management in regions prone to landslides. In addition to predictive modelling, the study highlights the role of preprocessing techniques, including hillside and LULC analysis, in enhancing detection capabilities. A comparative analysis of models reveals the superiority of the dual network approach over single-framework architectures, particularly in terms of accuracy and adaptability to diverse datasets. This study provides a novel contribution to landslide mapping by combining topographical insights with advanced network architectures. The proposed framework demonstrates the potential for deployment in other regions with similar geological settings, paving the way for improved disaster preparedness and management strategies.</div></div>","PeriodicalId":50047,"journal":{"name":"Journal of South American Earth Sciences","volume":"157 ","pages":"Article 105457"},"PeriodicalIF":1.7,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143577555","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessing sediment dynamics and erosion-deposition patterns after a dam break: Insights from the Brumadinho tailings dam failure in Brazil","authors":"Caio C.S. Mello ,&nbsp;Julian C. Eleutério","doi":"10.1016/j.jsames.2025.105472","DOIUrl":"10.1016/j.jsames.2025.105472","url":null,"abstract":"<div><div>Dam break events cause disruptive scenarios, leading to the sudden release of large volumes of water and sediment downstream, resulting in significant geomorphic changes in the floodplain. Assessing the consequences of dam break events on floodplain geomorphology, including changes in channel morphology, erosion, and deposition patterns, is an emerging research field, with perspectives of understanding the potential for landform evolution concerning sediment transport and establish benchmarks for future impact assessments and event modeling. The main objective of this research is to quantitatively assess the sediment dynamics following the Brumadinho tailing dam failure, focusing on the released sediment, the bulk retained in the Ferro Carvão stream watershed, and the tailings that reached the Paraopeba River. The methodology involved geospatial evaluation and zonal statistics to calculate bulk volumes, account for uncertainties, and compare the results with available monitoring data. The results highlighted a significant uncertainty regarding the mass sediment discharge hydrograph due to particle's geotechnical properties variability. It was estimated that about half of the sediment volume released from the dam was retained in the event-scale tailing spread area, diverging from other reported values in the literature. Zonal statistics in the floodplain revealed a predominant tendency for deposition over erosion across most of the spread area, especially in downstream areas, attributed to the geomorphological characteristics of the terrain and flow characteristics. However, erosion was more prominent in areas closest to the dam, justified by the flow velocity and stream power in these areas. Additionally, a mass balance indicates that a significant amount of sediment particles is being constantly transported in Paraopeba river, driven mainly by flow regime in rainy periods.</div></div>","PeriodicalId":50047,"journal":{"name":"Journal of South American Earth Sciences","volume":"157 ","pages":"Article 105472"},"PeriodicalIF":1.7,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143628572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Energy balance and evapotranspiration conditioned by deforestation of a seasonally dry tropical forest (Caatinga): A series of four water seasons","authors":"Thieres George Freire da Silva ,&nbsp;Maria Gabriela de Queiroz ,&nbsp;Sérgio Zolnier ,&nbsp;Alexandre Maniçoba da Rosa Ferraz Jardim ,&nbsp;Wilma Roberta dos Santos ,&nbsp;Magna Soelma Beserra de Moura ,&nbsp;Carlos André Alves de Souza ,&nbsp;Antonio José Steidle Neto ,&nbsp;George do Nascimento Araújo Júnior ,&nbsp;Marcelo José da Silva ,&nbsp;Kaique Renan da Silva Salvador ,&nbsp;Elania Freire da Silva ,&nbsp;Luciana Sandra Bastos de Souza","doi":"10.1016/j.jsames.2025.105474","DOIUrl":"10.1016/j.jsames.2025.105474","url":null,"abstract":"<div><div>Changes in land use affect the spatial and temporal variations of surface energy balance components and evapotranspiration in the Caatinga. We aimed to assess the partitioning of energy into latent heat flux (LE) and sensible heat flux (H), as well as actual evapotranspiration (ET), in areas of Caatinga vegetation (CAA) and a deforested area (DEFA) in the Brazilian semi-arid region from 2015 to 2018. Two micrometeorological towers were installed to obtain data during the rainy, dry and transition periods. The energy balance was obtained using the Bowen ratio, based on estimates of daily, monthly and seasonal H and LE fluxes, the latter being used to determine the ET. Higher average values of net radiation (Rn), LE, H and soil heat flux (G) were observed for the CAA landscape, while minimum values were recorded in the DEFA. Mean daily the ET in the CAA and DEFA was 2.19 and 1.97 mm, respectively. Around 23% of the received Rn was used for the LE, 70% for H and 9% for G at the site of the CAA, against 21% of the Rn for LE, 72% for H and 8% for G in the DEFA. Our results further showed that the removal of native vegetation promotes reductions in Rn, air relative humidity, ET and increases the vapour pressure deficit in the DEFA. Greater contributions were observed for H in the dry season, with LE being greater during the rainy season in the Caatinga vegetation area.</div></div>","PeriodicalId":50047,"journal":{"name":"Journal of South American Earth Sciences","volume":"157 ","pages":"Article 105474"},"PeriodicalIF":1.7,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143601308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Present-day foreland development and its relation to plate tectonics in the northern Andes","authors":"Carlos E. Macellari","doi":"10.1016/j.jsames.2025.105465","DOIUrl":"10.1016/j.jsames.2025.105465","url":null,"abstract":"<div><div>Based on analysis of topography through DEM images, geomorphology, river drainage patterns, and surface geology, the foreland basins of northwestern South America are divided into three areas that coincide with segments of boundaries between the South American, Nazca and Caribbean plates. From 2° 30′ to approximately 4°30′ N, is the southern Llanos or Uplifted foreland that is characterized by uplift and a transpressive environment. Major alluvial fans and terraces representing the wedge top depozone are present on the proximal part, and Mio-Pliocene sediments are exposed on the distal part of the foreland. This foreland is the highest (486 m at the mountain front) and has the steeper slope (0.33°) of the northern Andes. Watersheds in this area exhibit low maturity and elevated heat flow is observed. Associated to this foreland is the Cauca or Nazca Segment that has a steeply dipping slab that originates a chain of recent volcanoes to the west.</div><div>The second zone (Main Llanos foreland) is developed north of the Caldas tear zone and extends to the Rio Uribante-Apure. It coincides with a flat slab configuration (Bucaramanga Segment) and is characterized mostly by pure compression. On the foreland this generates deformation of recent terraces and current uplift in the wedge top area that is eroded in several areas. Active sedimentation in an extensive alluvial plain is taking place in the distal foreland. Here the streams are transversal to the Eastern Cordillera, feeding the longitudinal NE-SW trending Meta River. The slope has an average inclination of 0.14°, and an average elevation of 286 m at the mountain front. Watersheds display a high to intermediate maturity, but are less mature to the north, coinciding the Cocuy area of current uplift.</div><div>The northernmost zone, or Barinas Foreland, east of the Venezuelan Andes, aligns with the Caribbean Segment. Major subsidence occurred in the Middle-Upper Miocene mainly in the southern basin, migrating north in the Pliocene-Pleistocene. This resulted in a mature foreland to the south with a low regional slope lacking alluvial fans and wedge top facies. In contrast, the northern area has well-developed alluvial fans, a higher regional slope, and displays current deformation at the mountain front.</div><div>The northern South American Andes illustrates how plate configuration and the associated subduction of oceanic slabs are linked to distinct foreland morphologies. Nevertheless, other factors, such as tectonic inheritance and climatic conditions, play significant roles in determining the final configuration of a specific foreland.</div></div>","PeriodicalId":50047,"journal":{"name":"Journal of South American Earth Sciences","volume":"157 ","pages":"Article 105465"},"PeriodicalIF":1.7,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592545","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"New insights into hydrothermal alteration in the Ag-Pb-Zn Chinchillas deposit, Northwestern Argentina","authors":"Maximiliano Mercado ,&nbsp;D. Beaufort ,&nbsp;P.J. Caffe ,&nbsp;P. Patrier ,&nbsp;M. Franchini ,&nbsp;H. Caranza ,&nbsp;R.I. Zapata","doi":"10.1016/j.jsames.2025.105467","DOIUrl":"10.1016/j.jsames.2025.105467","url":null,"abstract":"<div><div>Hydrothermal alteration and ore deposition at Chinchillas (northern Puna, Argentina) occurred in pyroclastic deposits that fill an explosive diatreme, as well as in monomictic breccias composed of metasedimentary lithoclasts from the basement that bound the diatreme. Highly porous and permeable rocks acted as reservoir for hydrothermal fluids responsible of alteration and mineralization. Sequential mineral associations can be grouped in three pre- and two syn-to post-mineralization stages, which are frequently superimposed in space. The first stage (adularia-rich) is widespread and develops in a context of alkaline solutions, followed by upward circulation of relatively acidic and reducing fluids (second stage) with B availability (tourmaline ± pyrite ± quartz), limited to deep sectors. A third alteration stage is typical of the argillic alteration association and is given by kaolinite replaced by later illite + illite-smectite mixed-layers + quartz ± anatase ± pyrite ± alumino-phosfate-sulfates, which indicates the progressive neutralization of fluids during continuous interaction with rocks. The crystal structure characteristics and zonation of clay minerals with depth suggest temperatures between 200° and 170 °C and a vertical thermal gradient during illitization. These stages seem to have had minor effects on the reservoir quality of the diatreme, as the Ag-Pb-Zn ore + siderite (mineralization stage) was deposited in two relatively large areas of the diatreme, and late siderite (post-mineralization stage) is ubiquitous in both mineralized and barren areas.</div></div>","PeriodicalId":50047,"journal":{"name":"Journal of South American Earth Sciences","volume":"157 ","pages":"Article 105467"},"PeriodicalIF":1.7,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621128","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Land use and land cover analysis with special reference to mangrove dynamics for sustainable use in the Rosario River sub-basin, Pixvae, Panama","authors":"Jaime Rivera-Solís ,&nbsp;Adolfo Quesada-Román ,&nbsp;Rosa G. Castillero","doi":"10.1016/j.jsames.2025.105464","DOIUrl":"10.1016/j.jsames.2025.105464","url":null,"abstract":"<div><div>Effective land use planning necessitates integrating environmental parameters to assess spatial patterns and ecosystem conditions, particularly in vulnerable coastal regions. Mangrove ecosystems provide critical ecological services, yet they face increasing threats from anthropogenic pressures. This study combines remote sensing and field-based structural analysis to classify land cover and assess mangrove conditions in Ensenada de Rosario in Panama, supporting environmental planning. Using high-resolution PlanetScope satellite imagery within the ArcGIS Pro environment, we applied spectral analysis through the Normalized Difference Vegetation Index (NDVI) to classify land cover into five spectral classes and quantify four primary land use categories. Field validation in July 2023 involved four 10 × 10 m quadrants spaced 50 m apart, where mangrove species were identified, and structural parameters—including diameter at breast height (DBH), tree height, volume, basal area (BA), and density—were measured. Results indicate that the mangrove is a fringe type dominated by Rhizophora mangle, covering 24.7% of the sub-basin, while the anthroponatural landscape accounts for 3.2%. Structural analysis revealed an average DBH of 14.3 ± 2.6 cm, mean tree height of 6.8 ± 1.4 m, and basal area of 18.5 ± 3.2 m²/ha, indicating moderate forest development. Model uncertainties were estimated at ±5% for NDVI classification and ±10% for structural parameter measurements. These findings underscore the value of integrating remote sensing and field verification for land use classification and mangrove conservation, providing a methodological framework for balancing development with ecological sustainability in coastal environments.</div></div>","PeriodicalId":50047,"journal":{"name":"Journal of South American Earth Sciences","volume":"157 ","pages":"Article 105464"},"PeriodicalIF":1.7,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143611551","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A simple method to discriminate non-seismic pulses and long-period noise in broadband seismic records and its application to centroid moment tensor inversion of earthquakes in Colombia","authors":"Viviana Dionicio ,&nbsp;Hiroyuki Kumagai ,&nbsp;Juan Carlos Bermudez ,&nbsp;Esteban Poveda ,&nbsp;Faustino Blanco ,&nbsp;Masahiro Yoshimoto ,&nbsp;Maeda Yuta ,&nbsp;Orlando Chamorro ,&nbsp;Patricia Pedraza ,&nbsp;Indira Molina","doi":"10.1016/j.jsames.2025.105466","DOIUrl":"10.1016/j.jsames.2025.105466","url":null,"abstract":"<div><div>Non-seismic pulses and long-period noise are artifacts produced by broadband seismometers and degrade centroid moment tensor (CMT) solutions of earthquakes estimated from waveform inversion. In addition to the source amplitude ratio proposed by a previous study, we found that kurtosis is useful for discriminating artifacts from seismic signals. For 157 tectonic earthquakes with moment magnitudes of 4.6–7.5 in and around Colombia in 2014–2022, we manually selected waveforms from the Colombian broadband seismic network and estimated CMT solutions by waveform inversion in a long-period (50−200 s) band. We found that 98% of the selected waveforms had kurtosis values and signal-to-noise ratios larger than 2.5 and 3, respectively, and 92% had source amplitude ratios smaller than 11. We used these values as thresholds and automatically selected waveforms using the three parameters for the 157 earthquakes. Their CMT solutions showed a clear improvement compared to those estimated without any selection. They were better than those estimated with the previous method using only the source amplitude and the signal-to-noise ratios. The proposed parameters were implemented to obtain real-time automatic solutions that were similar to corresponding manual CMT solutions, and 87% of them were estimated within 20 min. Our simple method based on the statistical parameters applied to automatic CMT inversion contributes to improved earthquake monitoring and tsunami warnings in Colombina.</div></div>","PeriodicalId":50047,"journal":{"name":"Journal of South American Earth Sciences","volume":"157 ","pages":"Article 105466"},"PeriodicalIF":1.7,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143561989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Petrogenesis, magmatic evolution of the Morro de São João Alkaline Massif, southeastern Brazil, and implications for the evolution of the South American Platform","authors":"Mariana Bessa Fagundes ,&nbsp;Anderson Costa dos Santos ,&nbsp;Mauro Geraldes ,&nbsp;Sérgio de Castro Valente ,&nbsp;Gabriela Rodrigues Caitano ,&nbsp;Eduardo Reis Viana Rocha-Júnior","doi":"10.1016/j.jsames.2025.105456","DOIUrl":"10.1016/j.jsames.2025.105456","url":null,"abstract":"<div><div>The Morro de São João Alkaline Massif, Meso-Cenozoic, is an alkaline intrusion of approximately 10 km², located within the Poços de Caldas – Cabo Frio Alkaline Alignment. The massif consists of metaluminous rocks, ultrabasic to intermediate, potassic to ultrapotassic, SiO₂-undersaturated, and occasionally intersected by hypabyssal rocks, associated or not with pseudoleucite. The rocks of the massif are olivine-free and rich in nepheline, alkali-feldspar, and titanium- and calcium-bearing minerals. The (Dy/Yb)_N <em>vs.</em> (La/Yb)_N ratios suggest that the partial melting responsible for generating the massif occurred at approximately 1% of a garnet-bearing spinel peridotite. Meanwhile, isotopic ratios indicate that this source results from a mixture of up to 71.95 % of the EM I end-member, with influences from DMM, HIMU, and carbonatite. The magmatic evolution of the massif was not driven exclusively by fractional crystallization; the observed mineralogical and lithological diversity reflects complex processes of crustal assimilation and magma mixing. Evidence of these processes is provided by high ratios of ⁸⁷Sr/⁸⁶Sr, Ba/Sr and Rb/Sr, as well as low ratios of P₂O₅/K₂O, in addition to distinctive mineral textures such as compositional zoning in garnet and clinopyroxene crystals, poikilitic textures in amphiboles, and geochemical modeling of trace elements suggesting that the nepheline-monzosyenite, a hybrid member of the massif, contains up to 32% mafic contribution from malignite.</div></div>","PeriodicalId":50047,"journal":{"name":"Journal of South American Earth Sciences","volume":"156 ","pages":"Article 105456"},"PeriodicalIF":1.7,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143529296","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrating geospatial techniques and machine learning for assessing soil erosion and associated geomorphic risks","authors":"Priyadharshini V.M. ,&nbsp;Ghadah Aldehim ,&nbsp;Noha Negm ,&nbsp;S. Subathradevi","doi":"10.1016/j.jsames.2025.105463","DOIUrl":"10.1016/j.jsames.2025.105463","url":null,"abstract":"<div><div>Soil erosion is a critical environmental issue that threatens sustainability, agriculture, and infrastructure, necessitating a precise evaluation of geomorphic risks. This study employs an integrated approach combining geospatial techniques and machine learning models to assess soil erosion exposure in the Colima area. A comprehensive dataset of geospatial parameters, including inclination angle, land use/land cover (LULC), topographic wetness index (TWI), geological formation, proximity to roads and waterbodies, terrain elevation, aspect, sunlight exposure (HillShade), soil classification, vegetation index (NDVI), terrain ruggedness index (TRI), and sediment transport index (STI), was utilized to capture the spatial variability influencing erosion processes. Machine learning models—CatBoost, AdaBoost, Convolutional Neural Networks (CNN), and Stacking—were evaluated for their predictive performance using sensitivity, specificity, specificity, F1 score, recall, and precision metrics. Among these models, CNN achieved the highest accuracy, with sensitivity, specificity, F1 score, recall, and precision values of 0.84, 0.92, 0.90, 0.84, and 0.93, respectively. The CNN model's ability to capture complex spatial relationships and patterns in the dataset underscores its suitability for erosion risk assessment. The findings indicate that terrain elevation, LULC, and NDVI are key determinants of soil erosion susceptibility. High-risk areas were associated with steep slopes, sparse vegetation cover, and proximity to waterbodies. Canoas, Camoltan De Miraflores, Chandiablo, and Jalipa have been identified as areas facing significant soil erosion risks. These regions exhibit steep slopes, sparse vegetation cover, and proximity to water bodies, making them highly susceptible to erosion. The study's findings provide valuable insights for implementing targeted erosion control measures and sustainable land management strategies in these vulnerable areas. The study provides an efficient framework for identifying erosion-prone zones and prioritizing mitigation measures, contributing to sustainable land management strategies. By leveraging advanced machine learning techniques and geospatial analysis, this research advances the predictive modelling of geomorphic risks and aids in the development of targeted erosion control interventions.</div></div>","PeriodicalId":50047,"journal":{"name":"Journal of South American Earth Sciences","volume":"156 ","pages":"Article 105463"},"PeriodicalIF":1.7,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143551627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}