Journal Articles
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/19884
Browse
8 results
Search Results
Item Optimizing nailing parameters for hybrid retaining systems using supervised learning regression models(Springer Science and Business Media B.V., 2024) Menon, V.; Kolathayar, S.The work focuses on creating a hybrid retaining wall using geocell, geogrid, and soil-nailing techniques for a road embankment in Mangalore, India. Soil nailing reinforces the soil, geogrids give extra support, and geocell serves as a protective facia against external weathering impacts, decreasing the requirement for conventional shotcreting and lowering the carbon footprint of concrete. This promotes the United Nations’ Sustainable Development Goals (SDGs). The usage of concrete and steel in soil nailing can be minimized using supervised learning regression models (SLRMs), a branch of machine learning (ML). The soil properties in the site were collected by standard penetration tests (SPT). From the limit equilibrium method (LEM) study, 600 iterations are carried out to estimate the factor of safety (FoS), which serves as input training and testing data for the ML model. The surrogate model produces findings for the entire site to identify ideal nail parameters. The random forest (RF) model was found to be useful with a mean square error (MSE) value of 0.009. The finite element method analysis (FEM) yields a modest overestimation of roughly 4.5% while validating the results of the RF model in a typical slope. This study demonstrates the practical application of sustainable methodologies and machine learning to meet crucial development goals, explicitly improving slope stability and road development in the study area through environmentally conscious engineering practices. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.Item Rainfall-Induced Slope Instability in a Tilting Flume: Analysis of Pore Pressure Variations and Surface Crack Percentage(Springer, 2025) Menon, V.; Kolathayar, S.This study investigates the relationship between surface crack development and excess pore water pressure (EPWP) during rainfall-induced debris flow conditions. A custom-designed tilting flume integrated with a rainfall simulator was fabricated to replicate slope failure scenarios. Silty sand was tested under controlled conditions on 45° and 60° slopes with identical rainfall intensities. Surface cracks were quantified using an image processing algorithm to calculate crack percentages, and real-time EPWP measurements were recorded to assess their correlation. The results demonstrate that surface crack formation significantly influences EPWP, suggesting a potential interdependence between these parameters. Furthermore, the study evaluates whether EPWP can serve as an effective threshold parameter for landslide early warning systems (LEWS). These findings contribute to a better understanding of landslide mechanics and provide critical insights for enhancing LEWS design and implementation. © The Author(s), under exclusive licence to Indian Geotechnical Society 2025.Item Slope Stability Analyses and Design for a Telecommunication Tower Site in Kodagu—Limit Equilibrium and Finite Element Approach with Spatial Data Integration(Springer Science and Business Media Deutschland GmbH, 2025) Menon, V.; Anjana, S.; Kolathayar, S.This paper examines slope stability issues at the All-India Radio Telecommunication tower site in Kodagu, Coorg, Karnataka, India, where the hillock on which the tower stands has shown signs of instability after the monsoon of 2022. This study proposes reclamation strategies to mitigate future landslips in the region. A spatial analysis utilizing open-source Digital Elevation Models and Scoop3D software was performed to identify critical locations prone to landslips. The designs were assessed using the Limit Equilibrium method (LEM) and Finite Element method (FEM). Both static and pseudo-static conditions were considered in the analyses, with and without reinforcement, using the Limit Equilibrium Method and Finite Element Method. The proposed design aligns with the United Nations Sustainable Development Goals (SDGs) 9 and 11, demonstrating a significant increase in the Factor of Safety by more than 10%. The study recommends a geocell-based hybrid retaining system as a comprehensive solution to enhance slope stability and protect the site from future landslips. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.Item Landslides and debris flow triggered by the July 2024 extreme rainstorm in the Chooralmala watershed in Wayanad, India(Springer Science and Business Media Deutschland GmbH, 2025) Kolathayar, S.; Menon, V.; Kundu, P.[No abstract available]Item Analysis and Design of a Hybrid Reinforced Earth Retention System for Sustainable Slope Protection: A Case Study Using Limit Equilibrium and Finite Element Methods(Springer, 2025) Menon, V.; Kolathayar, S.This study proposes an innovative hybrid earth retention system to stabilize slopes for a road-widening project in Dakshina Kannada, Karnataka, India. The system combines soil nailing, geogrid reinforcement, geocell walls, and biotechnical stabilization—popular geotechnical techniques aligned with sustainable development goals. These methods were engineered synergistically to address the site-specific challenges of restoring a slope that experienced five major collapses during heavy rains, enabling both highway expansion and slope protection without disrupting traffic flow. Soil samples were collected, and laboratory tests were conducted to evaluate the engineering properties of the site soil. Boreholes were drilled at strategic locations and Standard Penetration Tests were performed. The analysis and design of the retention system employed both the Limit Equilibrium Method (LEM) and the Finite Element Method (FEM), utilizing GEO5 and OptumG2 software, respectively. A comparative analysis of these methods is presented, along with a non-linear regression model to establish correlations for soil nail parameters derived from LEM analyses. The study demonstrates the successful integration of geocell walls with soil nailing and geogrid reinforcement to support an unprotected embankment. The findings include the site reconnaissance report, reclamation strategies, and a detailed discussion of LEM and FEM analysis results, establishing the robustness and sustainability of the proposed hybrid retention system. © The Institution of Engineers (India) 2025.Item Empirical and machine learning-based approaches to identify rainfall thresholds for landslide prediction: a case study of Kerala, India(Springer Nature, 2025) Menon, V.; Kolathayar, S.Kerala, a state in India, experiences one of the highest incidences of rainfall-induced landslides. Historical data has been collected and analyzed to devise thresholds for the early detection of landslides. Two empirical approaches based on the relationships between rainfall intensity and duration, as well as cumulative rainfall and duration, have been utilized to identify early warning thresholds for landslides. Five machine learning-based approaches were employed to determine these thresholds. Among the classifiers tested, the K-Nearest Neighbour (KNN) classifier with K=5 demonstrated the highest prediction accuracy compared to other methods in the study.; For the safe and resilient development of cities, disaster risk reduction plays a crucial role, aligning with sustainable development goal 11 of the United Nations. Supporting this objective, the present study developed a machine learning (ML) classifier-based threshold model to determine rainfall thresholds for predicting impending landslides in Kerala, India, using historical data. Using a dataset of 64 rainfall-induced landslide events recorded since the year 2000, rainfall data were collected up to 15 days prior to each landslide to support empirical analysis of intensity-duration and event rainfall-duration thresholds. In cases where exact rainfall durations were unavailable, classification machine learning (ML) models, including K-nearest neighbours (KNN), random forest (RF), gradient boosting machine (GBM), support vector machine (SVM), and logistic regression, were used to determine threshold reliability. Among these, the KNN model with 5 Neighbours achieved the highest performance, with an ROC-AUC of 0.9 and an accuracy of 82%. This model, saved as a pickle file, serves as a core filter in the development of a landslide early warning system. This paper presents the model development and performance comparisons, contributing to a practical, community-centred solution for landslide disaster resilience in Kerala. © The Author(s) 2025.; © The Author(s) 2025.Item The Shirur landslide of July 2024 triggered by intense rainfall and unchecked development(KeAi Communications Co., 2025) Kundu, P.; Menon, V.; Kolathayar, S.; Umesht, P.On the morning of July 16, 2024, a significant landslide occurred in Shirur of Uttara Kannada district, Karnataka, India. The landslide claimed seven lives, leaving one person missing and severely disrupting the transport network by blocking National Highway 66. The displaced debris travelled 180m across the highway and into the Gangavali River, causing a significant splash and damaging structures on the opposite bank. The event, characterised by a rotational slip, was triggered by a combination of anthropogenic activities and intense rainfall. The construction of National Highway 66, which involved the removal of the slope's toe without adequate protection for the excavation, significantly destabilised the area. On 15th July, the rain gauge in Ankola recorded rainfall of 260 ?mm. The accumulated rainfall calculated for Shirur using Inverse Distance Weightage (IDW) for the storm period of 4 days was 198 ?mm, which increased the pore water pressure within the soil, weakening its shear strength and leading to slope failure. This incident underscores the need for further analysis and the implementation of appropriate mitigation measures, as the region remains at risk for future landslides. The Shirur landslide serves as a critical reminder of the dynamic nature of such disasters, particularly when human activities exacerbate natural hazards. © 2025 The AuthorsItem Debris flow in c-? soil: experimental analyses of pore pressure variations, crack percentage, digital image correlation (DIC) and particle image velocimetry (PIV)(Springer, 2025) Menon, V.; Kolathayar, S.Debris flow is the aftermath of soil losing its strength due to an increase in moisture content, which is initiated by Rainfall. This study investigates rainfall-induced debris flow in c-? soil predominantly found in the Western Ghats, India. The experimental setup utilised the tilting flume technique to simulate a 45-degree slope, replicating field conditions in terms of field density and natural moisture content. Excess pore water pressure (EPWP) variations were monitored during simulated rainfall events with an intensity of 30 mm/h. The findings indicate that the decrease in EPWP observed during the experiments Following a peak value and coincides with the initiation of soil movement, which occurs after the formation of shear cracks on the soil surface. To substantiate these observations, a masking algorithm based on OpenCV was employed to analyse fluctuations in crack percentage. Particle image velocimetry (PIV) and Digital Image Correlation (DIC) quantified particle velocity-displacement dynamics using high-definition camera imagery over time, which validated the initiation of landslides. It was observed that the rapid decline in EPWP serves as a critical precursor to potential landslide occurrences, underscoring the pivotal role of these metrics in early landslide prediction and risk assessment. This research contributes valuable insights into understanding landslide mechanics under controlled laboratory conditions, with implications for early landslide detection and hazard mitigation strategies in landslide-prone regions. © Indian Academy of Sciences 2025.