Search

The eastern Himalayan syntaxis (EHS) region is characterized by steep topography, strong tectonic activity, and strong disaster activity, and the disaster activity has a temporal correlation with the change of seasonal climate factors. Different from other disaster-prone areas, the disasters in the EHS area are more destructive and more susceptible to changes in climate factors. However, previous studies on disaster susceptibility in the region mainly focused on geohazard samples, regional topography, and geological conditions and seldom considered the characteristics of disaster activity and the characteristics of seasonal temperature and rainfall changes, which often led to an underestimation of disaster susceptibility in this region. Therefore, in this study, SBAS-InSAR technology and the GEE (Google Earth Engine) platform were used to identify 317 geological disasters and construct the spatial–temporal motion field and spatial-temporal background information of disasters in the last 5 years. Based on the random forest and optimized evaluation data model, the disaster susceptibility in the EHS area was quantitatively evaluated. The AUC value of the model was 0.89, indicating that the results have high reliability. The results showed that the high-susceptibility areas were mainly distributed in the riverbank and high-altitude areas. The SHAP model revealed that the factors of temperature, precipitation, slope, and elevation in the EHS area had a great negative influence on the disaster. The quantitative results of the influence of seasonal temperature and precipitation on disaster susceptibility showed that the area of susceptibility in summer was significantly higher than that in winter, and the area of high and very high susceptibility increased by about 13%. Finally, the dynamic failure process of typical landslide and glacier disasters in highly susceptible areas was quantitatively predicted, which provides a scientific basis for disaster prevention. [ABSTRACT FROM AUTHOR]

The Wenchuan earthquake strongly disturbed the earth surface and induced sufficient loose debris in the mountain basin, which supplies sufficient solid materials for debris flow initiation. Recently, a catastrophic debris flow was induced by strong rainfall on June 26, 2023 in the Banzi basin. Inconsistent with the first few years of the Wenchuan earthquake, the hillslope landslide sediment supply for debris flow occurrence is limited after 15 years of the Wenchuan earthquake, and the materials supplied for debris flow in the later period are mainly obtained from alluvium deposited along the channel. Simultaneously, this debris flow was triggered by flash flood through strongly erosion channel materials. However, although 15 years have passed since the Wenchuan earthquake, the triggering rainfall conditions have still not returned to pre-earthquake level. This debris flow first initiated in the upper branches of the basin and then gradually transported downstream at an average discharge of 806.99 m3/s, and approximately 82.80 × 104 m3 solid materials were transported out the Banzi basin to form a debris flow fan with length of 120 m and width of 260 m in the Minjiang River, which poses a serious threat to the resettled population and destroy the reconstruction infrastructures. Importantly, there are still sufficient solid materials deposited in the basin, this could result in debris flow activity continuing for an unpredictable time. Therefore, implementation early warning, prevention, and mitigation measures in this basin are still important for debris flow disaster management in the later period of Wenchuan earthquake. [ABSTRACT FROM AUTHOR]

Deformation and failure of the talus slope in the cold region significantly threaten engineered structures. Its driving mechanism of the deformation process is the most challenging issue. In this study, we try to explore these issues using tree ring characteristics. Fifty samples from 21 trees of Pinus densiflora growing on the talus slope in the Huanren area of Northeast China are tested to investigate the characteristics of tree rings and their relation to climate change. The deformation and its driving mechanism of this talus slope are then studied by combining the analysis of tree-ring width and mutation identification with the local meteorological data. The results present that the studied talus slope in Huanren has deformed to varying degrees at least 60 times since 1900. It is reasonable to speculate that the deformation mode of this slope is probably of a long-term and slow type. The local precipitation and seasonal temperature difference are the vital inducing factors of the mutation of tree-ring width and slope deformation. Repeated freezing and thawing are believed to be the driving factors of this talus slope in the cold region. A theoretical model is proposed to capture and predict the deformation of the talus slope. This work presents a new perspective and insight to reveal the deformation and its driving mechanism of similar talus slopes in the cold region. It is of great significance to practical engineering treatment and disaster prevention for this kind of cold region environment. [ABSTRACT FROM AUTHOR]

Debris flows can develop into mega catastrophes in semi-arid regions when the source materials come from landslides, and both snowmelt and precipitation are involved in increasing water discharge. In such environments, the formation of large-scale debris flows exhibits a distinguishable pattern, in which a multi-fold lower triggering rainfall threshold holds compared to humid regions. Previous research mainly focuses on mechanisms in humid environments or neglects variations across aridity classes. In this study, the formation and evolutionary mechanism of a debris flow occurring in a semi-arid context is investigated via field surveys, granularity measurement, terrain and climate analyses, and snow cover change detection. By examining the July 22, 2021, Xiao Dongsuo debris flow at Amidongsuo Park in the Qilian Ranges on the northeastern margin of the Tibetan Plateau, the mechanism of debris flows in semi-arid regions is revealed. The research finds that the large debris flow, whose course erosion scales up the disaster by 0.12 million m3, is primarily supplied by landslide deposits of 1.16 million m3. The debris flow is empowered by the integrated flow of extreme precipitation and extreme heat-stimulated snowmelt. However, the precipitation required to trigger the debris flow is much lower than that of precipitation-dominated ones and those in humid regions. In semi-arid mountains, prolonged extreme heat tends to increase soil moisture in areas covered by snow or permafrost. This reduces slope stability and induces slope failures, amplifying the disaster magnitude and raising disaster risks through extended deterioration. Hence, this study inspects the failure mechanism associated with debris flows in semi-arid regions for a more comprehensive understanding to constitute viable control plans for analogous disasters. [ABSTRACT FROM AUTHOR]

Typhoons are recurring meteorological phenomena in the southeastern coastal area of China, frequently triggering debris flows and other forms of slope failures that result in significant economic damage and loss of life in densely populated and economically active regions. Accurate prediction of typhoon-triggered debris flows and identification of high-risk zones are imperative for effective risk management. Surprisingly, little attention has been devoted to the construction of physical vulnerability curves in typhoon-affected areas, as a basis for risk assessment. To address this deficiency, this paper presents a quantitative method for developing physical vulnerability curves for buildings by modeling debris flow intensity and building damage characteristics. In this study, we selected the Wangzhuangwu watershed, in Zhejiang Province of China, which was impacted by a debris flow induced by Typhoon Lekima on August 10, 2019. We conducted detailed field surveys after interpreting remote sensing imagery to analyze the geological features and the mechanism of the debris flow and constructed a comprehensive database of building damage characteristics. To model the 2019 debris flow initiation, entrainment, and deposition processes, we applied the Soil Conservation Service-Curve Number (SCS-CN) approach and a two-dimensional debris flow model (FLO-2D). The reconstructed debris flow depth and extent were validated using observed debris flow data. We generated physical vulnerability curves for different types of building structures, taking into account both the degree of building damage and the modeled debris flow intensity, including flow depth and impact pressure. Based on calibrated rheological parameters, we modeled the potential intensity of future debris flows while considering various recurrence frequencies of triggering rainfall events. Subsequently, we calculated the vulnerability index and economic risk associated with buildings for different frequencies of debris flow events, employing diverse vulnerability functions that factored in uncertainty in both intensity indicators and building structures. We observed that the vulnerability function utilizing impact pressure as the intensity indicator tends to be more conservative than the one employing flow depth as a parameter. This comprehensive approach efficiently generated physical vulnerability curves and a debris flow risk map, providing valuable insights for effective disaster prevention in areas prone to debris flows. [ABSTRACT FROM AUTHOR]

The sliding process and characteristics of earthquake-induced landslides are complex, and many factors affect landslide movement. The damage caused by landslides is often closely related to their movement characteristics. Therefore, establishing an efficient and quick analysis model for earthquake-induced landslide movement is very important in considering multiple control factors in the sliding process. Based on the typical characteristics of earthquake-induced landslide movement, considering the influences of earthquake action, friction characteristics of sliding surfaces, topographic relief, and morphological changes in landslide masses, a widely applicable quick analysis model for earthquake-induced landslide movement (ELQA) is constructed based on energy conservation. Compared with the existing landslide movement models, this model can consider multiple control factors and significantly improve the applicability of the model. Through comparisons with theoretical analysis, model tests, and actual landslide (Kolka glacial detrital flow), the movement distance of the landslide front edge obtained by the ELQA model matches well with the comparison results, indicating that the ELQA model can reproduce earthquake-induced landslide movement more accurately and quickly. Based on the ELQA model, the influences of control parameters (terrain sampling point density, time step, calculated point number) and calculation parameters (internal friction angle, slip mass volume, terrain concavity, and convexity characteristics) on the calculation results are studied. The results show that control parameters such as terrain sampling point density, time step, and calculated point number have limited influence on the movement characteristics; as long as appropriate values are selected, the error rate can be controlled within 5%. The calculation parameters have a significant influence on the movement characteristics. For example, the influence of the internal friction angle on the coverage area reaches up to 83.75%. The slip mass volume has an insignificant influence on the maximum movement speed, but it on the coverage area reaches approximately 20%. The influence of the terrain concavity and convexity characteristics on the results is less than 10%. The ELQA model is suitable for in-situ estimation and can provide effective suggestions for disaster prevention and reduction in earthquake-prone areas. [ABSTRACT FROM AUTHOR]

Landslides are a severe geohazard around the world. When moving soil masses discharge into a large water body, a tsunami can be generated and exacerbate the devastating effects of the landslide as well as extend the affected area. In this study, based on on-site geological investigation and monitoring, a numerical depth-averaged, two-phase model is established for a hypothetical tsunami in the Suofengying reservoir induced by the potential Bianjiazhai landslide in China which has been previously identified as critical. The analysis of the simulation results shows that the maximum wave amplitude measured at gauge point closest to the landslide is 31 m, and the tsunami reaches the reservoir's dam about 66 s after the landslide initiation. The inundation map provides potential risk areas that could be affected if a landslide occurs with the anticipated characteristics. Under similar conditions, the research results will help guide reservoir operation and landslide-tsunami disaster prevention. Simultaneously, examining the sequence of events in the tsunami disaster chain facilitates the analysis of the fundamental physics governing the propagation of tsunamis within reservoirs. This analysis contributes to the prediction and prevention of landslide-induced tsunami disasters occurring along reservoir banks. [ABSTRACT FROM AUTHOR]

Comprehensive identification of geological hazard risks remains one of the most important tasks in disaster prevention and mitigation. Currently, remote sensing combined with deep learning methods can gradually achieve the recognition of geological hazard risks. However, landslide images taken by satellites, with complex backgrounds and varying scales, particularly small-scale landslide images, are prone to false detections and omissions. The fundamental reason is that the existing models cannot effectively extract the detailed features of landslide images in multi-scale complex backgrounds. To address these challenges, we selected Luding County, Sichuan Province, China, as the study area and created an open and accurate landslide dataset. Geological hazard research experts interpreted and annotated the samples, which contained 230 landslide images with corresponding labels and geographical coordinates for each landslide. We propose a novel deep learning method for landslide identification, which combines YOLO + U-Net. The specific recognition process is as follows: Firstly, the landslide images to be measured are input into the improved YOLOv4 model for the target detection task, and the landslide detection frames are output to find the approximate location of the landslide using the frames. Then, we put forward an innovative method to expand the landslide detection box, so that it retains certain contextual semantic information, except for the detection box, other backgrounds are filled with black, which can shield a part of irrelevant complex background interference, conducive to further recognition. Finally, the improved U-Net semantic segmentation model is used to perform the semantic segmentation task inside the detection frame, and the accurate landslide boundary segmentation results are obtained. In the experiments, we thoroughly discussed and compared four methods: U-Net, improved U-Net, PSP-Net, and YOLO + U-Net. YOLO + U-Net showed a 20.6% improvement in mean IoU for small-scale landslides compared to U-Net, and a 2.08% improvement for landslides in complex backgrounds, with an average improvement of 9.91%. These results indicate that YOLO + U-Net can effectively extract detailed features of landslide images at different scales, improve the ability to recognize landslides in complex backgrounds, and effectively reduce the problem of false detection and omission of landslide image identification. [ABSTRACT FROM AUTHOR]

In July 2023, Himachal Pradesh, India experienced heavy rainfall that led to numerous landslides and significant damage. The affected districts of Shimla, Kullu, and Mandi were the hardest hit, with 223 fatalities, 1300 road closures, and extensive property damage. Factors contributing to the landslides included the intense rainfall, the area's geology and topography, and human activities such as unplanned construction and deforestation. The damage assessment is still ongoing, but initial reports indicate thousands of landslides, loss of life, injuries, and destruction of homes. Further investigations are needed to understand the slope characteristics and develop effective emergency plans to mitigate future impacts. [Extracted from the article]

This study proposes an innovative approach to develop a regional-scale landslide forecasting model based on rainfall thresholds optimized for operational early warning. In particular, it addresses two main issues that usually hinder the operational implementation of this kind of models: (i) the excessive number of false alarms, resulting in civil protection system activation without any real need, and (ii) the validation procedure, usually performed over periods too short to guarantee model reliability. To overcome these limitations, several techniques for reducing the number of false alarms were applied in this study, and a multiple validation phase was conducted using data from different sources. An intensity-duration threshold system for each of the five alert zones composing the Liguria region (Italy) was identified using a semiautomatic procedure called MaCumBA, considering three levels of criticality: low, moderate, and high. The thresholds were developed using a landslide inventory collected from online newspapers by a data mining technique called SECaGN. This method was chosen to account for only those events that echo on the Internet and therefore impact society, ignoring landslides occurred in remote areas, not of interest for civil protection intervention, which would adversely affect the model performance because they would result in false alarms. A calibration phase was performed to minimize the impact of false alarms, allowing at least one false alarm per year over the moderate criticality level. In addition, an innovative approach to include antecedent rainfall as the third dimension of the intensity-duration thresholds was applied, generating a consistent reduction in false alarms. The results were validated through an independent landslide inventory and were compared with (i) the alert issued by the regional civil protection agency to observe the improvements achieved with the proposed model and to evaluate to what extent the proposed model is consistent with the assessments of the civil protection and (ii) a dataset of the national states of emergency to verify the suitability of the developed thresholds for alerting citizens. The thresholds obtained showed high predictive capabilities, confirming their suitability for implementation in an operational landslide early warning system. [ABSTRACT FROM AUTHOR]

This article provides an overview of a snow avalanche that took place in Tibet on January 17, 2023. The avalanche occurred unexpectedly near the Duoxiongla Tunnel on the Pai-Mo highway, burying approximately 7 km of the road and causing a three-day blockage. The avalanche was particularly significant due to its magnitude and impact, which were unprecedented in the region. The causes of the avalanche included heavy snowfall, temperature fluctuations, snow and ice melt, and strong winds. The article emphasizes the importance of prioritizing measures to prevent and mitigate avalanches on roads in the future. It also highlights the need for enhanced monitoring and early warning systems, the establishment of refuge points in secure areas, and the improvement of scientific knowledge and awareness regarding snow avalanche prevention. [Extracted from the article]

Rockfalls are ubiquitous products of landscape evolution in steep mountainous terrains. Among other effects, they pose a significant concern to the management of transportation corridors located on valley floors. Here, we describe the field application of a ground-based Doppler radar that performs real-time, long-range, wide-area detection and tracking of rockfalls and related slope hazards. We deployed the instrument at the Ruinon landslide, where accelerated deformation of upper chaotic debris has for several months promoted secondary mass wasting processes of extremely rapid velocity. In particular, large rolling boulders had the potential to propagate beyond the toe of the landslide and impact a road that connects important localities in the Italian Alps interiors. The Doppler radar was programmed to actuate a pair of traffic lights so that a predefined exclusion zone could instantly be enforced for approaching vehicles upon initial movement detection. We discuss the setup of the alarm system, the main observations collected during the monitoring campaign, and how this technique may enhance safety in areas critically exposed to rockfalls as well as our understanding of rockfall dynamics in general. [ABSTRACT FROM AUTHOR]

The occurrence of landslides is not uncommon in the Western Ghats of Maharashtra, India. However, during the last week of July 2021, an unprecedented number of landslides due to heavy rainfall were reported in this region. To determine the cause of the large-scale landsliding, we mapped an event-based landslide inventory using high-resolution satellite imagery and identified 5012 landslides. We analysed rainfall data for the 2005–2021 period to identify the anomaly in rainfall quantity and its distribution which triggered such large number of landslides, particularly in 2021, even though heavy annual monsoonal rainfall is observed every year in this region. It is observed that the quantity of rainfall in 2021 is much lesser than that seen in most of the previous years. Analysis of antecedent rainfall for time-stamped landslides, such as Jui (2005), Malin (2014) and Taliye (2021), shows that two-day antecedent rainfall is the primary trigger of landslides in the region. An in-depth comparison of rainfall variability for all the years which recorded more rainfall than 2021 shows that the amount of two-day consecutive rainfall is significantly higher in 2021, although the cumulative seasonal rainfall is less than in preceding years. Further, this anomalously high rainfall was concentrated around the 600 m – 900 m elevation range. The probable consequence of such spatiotemporally localised heavy rainfall over higher elevations was rapid soil saturation triggering a large number of landslides in 2021. In times when the effect of climate change is visible in the form of weather extremes, the present study may aid in preparedness for response to such disasters. [ABSTRACT FROM AUTHOR]

On April 18, 2023, a rockslide occurred in Torkham town in Pakistan, near the border with Afghanistan. The rockslide buried trucks and people, resulting in seven deaths and many injuries. The area is prone to natural disasters such as earthquakes, landslides, and floods. The rockslide was triggered by heavy rainfall and may have been exacerbated by slope cutting for road widening. The authors recommend slope stabilization measures, such as drainage systems, vegetation planting, retaining walls, and rockfall barriers, to prevent future disasters. [Extracted from the article]

Landslides often occur in V-shaped valleys exhibiting strong river incisions and large elevation differences between the riverbed and surrounding mountains. This study expounded upon the topographical and flow conditions of typical landslide dam sites through field investigations and data collection and established a small-scale physical model for experimental research. The formation conditions of landslide dams, an important part of the long-term management of such events, were studied. Simultaneously, the experiments verified a series of engineering measures proposed based on calculus theory and implementation principles according to their experimental disposal effects to mitigate short-term flood risks. Results showed that the dam formation is mainly related to topographic characteristics, upstream flow, and dam compositions. Specifically, steep V-shaped valleys should be considered when establishing physical models as they provide great conditions for landslide mass blocking the river completely. In addition, for earth dams, the effects of the position and direction of excavated diversion channels were compared; it showed that when there are multiple passes on the dam crest, priority should be given to lateral excavation of channels from the pass to restrict the lateral development process. The dam-break flow direction should better be orthogonal rather than be parallel to the river bend, which can reduce peak flow discharge by natural energy dissipation. For earth and rockfill dams with wide particle distributions, piles and flexible nets were instead utilized to coarsen the dam breach and reduce peak flow discharge. Finally, applicable values and research significance were summarized based on the obtained results. This research enriches studies of mountain disaster management and provides guidance for on-site emergency response. [ABSTRACT FROM AUTHOR]

Landslide deformation monitoring is an important method for proactive disaster prevention. Acoustic emission (AE) equipment, comprising active waveguides (i.e., a steel tube with granular internal/external backfill), has become an optional monitoring technology for subsurface deformation in landslides. It is also challenging to develop novel AE monitoring equipment that can optimise technological applications and data interpretation. In this study, we developed an equipment named "AE array" with a newly designed assembly and a standardised structure, from which we developed a complete AE monitoring system. We then conducted an experimental investigation of the AE array using speed-controlled compression to explore the acoustic properties in response to deformation. The AE array was also used in the field to demonstrate its practical use and performance for landslide monitoring at a loess slope. The deformation–AE relationship was obtained and compared using data from the compression experiment and the field site. The AE array collectively monitored AE and an inclinometer within a borehole, which has practical applications and data validation advantages. A strong linear correlation was obtained between the cumulative displacement and AE data, independent of the length of the AE array. The complexity and variability of the field-based deformation–AE relationship have implications for potentially improving the performance of the AE array. Machine learning models should be considered to automatically quantify the dynamic deformation–AE relationship, which can provide a basis for landslide early warning systems. [ABSTRACT FROM AUTHOR]

This study investigates the sediment dynamics resulting from the extreme Storm Alex in October 2020 in the Roya Valley and its tributaries in the Alpes-Maritimes region, France. The storm, triggered by a low-pressure system, led to unprecedented rainfall, causing extensive flooding and erosion in the region. Despite limited pre-flood data, the study employs aerial and satellite imagery, digital elevation models, and field surveys to quantify sediment mobilization and its effects on the Viévola alluvial fan in the Roya Valley. The Roya Valley’s complex geomorphology, characterized by steep gradients, gullies, and torrential streams, played a significant role in sediment transport. The study reveals that the Dente and Rabay torrents were major sediment contributors, with gullies in these areas producing substantial erosion. Bank erosion in the Dente valley was particularly prominent, attributed to geological factors and glacial deposits. The analysis, relying on topographical comparisons and digital data, assesses sediment volumes eroded and deposited during the event. Despite challenges in data quality, the study offers valuable insights into sediment dynamics during extreme hydro-sedimentary events. The Viévola catchment area is a focal point, emphasizing the importance of scree and fluvio-glacial deposits as primary sources of sediment. The findings emphasize the need for improved pre-event data and monitoring in mountainous regions susceptible to extreme events. The study’s methodology, despite limitations, contributes to a better understanding of geomorphic responses to extreme events. Expanding similar studies to cover a wider range of catchment areas and incorporating field data offers potential for enhanced hazard assessment and management strategies. The research underscores the critical role of sediment transport in shaping landscapes and impacting human infrastructure during extreme flood events. [ABSTRACT FROM AUTHOR]

Landslides represent a major global natural disaster, often leading to severe consequences, including substantial loss of life and property. However, research on the spatiotemporal distribution characteristics of fatal landslide events across different climate regions and their association with precipitation remains limited. In this study, we compiled a database of non-seismic fatal landslides in China from 2010 to 2022 to examine their spatiotemporal distribution and relationship with precipitation. From 2010 to 2022, China experienced a total of 710 fatal landslide events, causing 5158 fatalities. The data revealed a declining trend in both the number of fatal landslides and associated fatalities, with the number of fatal landslides demonstrating a recurring cycle of 3–4 years marked by continuous decreases within each cycle. The initial year of a new cycle witnessed a significant increase in the number of fatal landslides, suggesting a periodic occurrence, which is related to El Niño. The central subtropical humid region recorded the highest number of fatal landslide events, attributed to its highest annual precipitation. The trend in fatal landslides closely corresponded with variations in precipitation, increasing in spring and summer and decreasing in autumn and winter. The cumulative frequency distributions of fatal landslides and fatalities followed a power-law distribution, with a sharp decline observed when exceeding a certain value, indicating a deflection effect. Despite the low population density, the plateau climate region has the highest risk of life loss among all climate regions. Understanding the spatial distribution of non-seismic fatal landslides can significantly aid in formulating more effective disaster prevention and mitigation policies. [ABSTRACT FROM AUTHOR]

Landslides, as a common natural disaster, pose a significant threat to human society and the natural environment, including loss of life, economic damage, and environmental destruction. Effective landslide early warning is key to reducing these negative impacts. However, current warning methods face two major challenges: one is the reliance on static threshold judgments, which not only easily leads to false and missed alarms but also cannot adapt to complex and changing natural conditions. The second is the lack of ground data support in areas with complex terrain, which greatly limits the application range and accuracy of traditional warning methods. To overcome these challenges, this study designed an efficient processing system for Interferometric Synthetic Aperture Radar (InSAR) based on the (Artificial Intelligence) AI Earth Cloud platform, integrated with the Comprehensive Standardized Deformation Index (CSDI) approach, to provide an early warning analysis for the Zhenxiong landslide in Yunnan Province, China on January 22, 2024. Utilizing the cloud platform for rapid generation of deformation rates and selection of characteristic deformation points to reflect landslide trends, and applying the CSDI method for time-displacement curve analysis, enabled a fast and accurate landslide early warning. The research results show that the method proposed in this study can effectively warn of landslide events, significantly improving the accuracy and practicality of the warning. By combining InSAR technology with the CSDI model, this study not only addresses the challenges faced by traditional methods but also provides new insights and solutions in the field of landslide early warning, demonstrating the great potential of technological innovation in natural disaster management. [ABSTRACT FROM AUTHOR]

Landslide disasters are one of the frequently occurring geological hazards, posing a significant threat to human life and property safety. Swift and accurate identification of landslide areas is crucial for disaster prevention and mitigation. Current object detection algorithms have limitations in the localization and recognition of landslide areas. To address this issue, this paper proposes a cross-spatial network based on efficient multi-scale attention (EMA-Net) landslide recognition model. The proposed EMA-Net model incorporates the efficient multi-scale attention (EMA) for cross space learning, enhancing the model’s focus on landslide areas. Additionally, by employing convolution with absolute positioning (CoordConv), the positional information of features is retained to enhance the capability of multiscale feature extraction. The utilization of the SCYLLA-IoU (SIoU )loss function enhances regression learning ability for model prediction borders, thereby improving the efficiency and accuracy of the model. To assess its performance, EMA-Net is evaluated against other models, including Yolov5-\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$-$$\end{document}5.0, Yolov5-\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$-$$\end{document}6.1, Yolov7, and Faster-R-CNN. The evaluation demonstrates that the proposed EMA-Net achieves a precision of 0.980, recall of 0.982, and mAP of 0.717, exhibiting clear improvement over the compared networks. Furthermore, through visualized analysis, the proposed network is capable of effectively identifying landslides within a smaller range. Comparative analysis of the aforementioned experiments validates the superiority of the proposed network. [ABSTRACT FROM AUTHOR]