Browsing by Author "Ashutosh Kainthola"

Now showing 1 - 20 of 39

3D Stochastic Simulation of Rockfall Mechanism and Mitigation in the Batseri Zone
(Springer Science and Business Media Deutschland GmbH, 2025) Vishnu Himanshu Ratnam Pandey; Ashutosh Kainthola; Vikas Yadav; Jagadish Kundu; Paolo Mazzanti; Ramesh P. Singh; T. N. Singh
On 25 July 2021, a deadly rockfall at Batseri (Himachal Pradesh), India, killed 9 tourists and completely destroyed a crucial Bailey Bridge. The present study primarily focuses into the geomorphological and engineering geological attributes of the Batseri Rockfall dynamics. Extreme weathering phenomenon, adversely orientated joints, and abnormally high precipitation in the valley might have evoked the doomed incident. The work combines field study, structural analysis, and 3D stochastic assessment to ascertain the triggers, and trajectory of the rockfall. Runout distance, bounce height, kinetic energy, and velocity of the falling blocks with varying geometry and sizes have also been calculated. The results have been used to test the efficiency of rockfall barriers with different configurations and combinations to safeguard the affected strategically important road. These results can aid in mitigating the rockfall damage, effectively and economically. The simulation of potential blocks destroying the Bailey Bridge forms an important section of this research, and will assist in identification of suitable locations for new bridge instalment at Baspa River. Moreover, this work is perhaps the first of its kind to undertake the rigid body stochastic analysis for understanding the rockfall mechanism in such a large scale. The results discussed in the paper will be of use to understand similar events across the Himalayan terrains and develop policy for hazard mitigation. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.
Advanced Bivariate Geostatistical Modeling for High-Resolution Landslide Susceptibility Zonation for Effective Risk Management in the Northwestern Himalaya, India
(Springer Science and Business Media Deutschland GmbH, 2025) Imran Khan; Vikas Yadav; Ashutosh Kainthola; Harish Bahuguna; Debi Prasanna Kanungo; Ranjan Kumar Dahal; Shantanu Sarkar; Md Sarfaraz Asgher
Frequent landslides in the northwestern Himalaya India (NHI) region cause significant loss of life and property, making landslide susceptibility zonation (LSZ) crucial for identifying vulnerable areas. This study aims to develop LSZ maps for the NHI using four bivariate geostatistical models: Frequency Ratio (FR), Weight of Evidence (WoE), Information Value (IV), and Yule's Coefficient (Yc). A total of 38,697 landslides, covering 149.50 km2, were analyzed. The data was split into 70% for training and 30% for testing, ensuring robust model validation. Twelve causative factors were considered, including slope angle, slope aspect, slope curvature, relative relief, terrain roughness index, geomorphon, distance to drainage, land use land cover, lithology, distance to fault/thrust, earthquakes, and rainfall. The models identified high to very high susceptibility zones, covering 28.7%, 32.8%, 48.1%, and 48.2% of the region for the Yc, FR, WoE, and IV models, respectively. ROC analysis revealed that the FR model achieved the highest accuracy, with 0.845 (84.5%) for both validation and prediction. The IV model followed with ROC values of 0.833 (83.3%), while the Yc model performed similarly, with values of 0.831 (83.1%). The WoE model exhibited slightly lower accuracy, with ROC values of 0.830 (83.0%) for validation and 0.831 (83.1%) for prediction. Both the WoE and IV models covered over 98% of landslide areas in high and very high susceptibility zones, indicating a tendency to overestimate highly susceptible areas. The study suggests that the FR and Yc models are particularly effective for LSZ and risk assessment. These results provide valuable insights for hazard management, aiding researchers, planners, and policymakers in selecting appropriate models for LSZ and mitigating landslide risks in other vulnerable regions. © King Abdulaziz University and Springer Nature Switzerland AG 2024.
Advanced Bivariate Geostatistical Modeling for High-Resolution Landslide Susceptibility Zonation for Effective Risk Management in the Northwestern Himalaya, India
(Springer Science and Business Media Deutschland GmbH, 2024) Imran Khan; Vikas Yadav; Ashutosh Kainthola; Harish Bahuguna; D.P. Kanungo; Ranjan Kumar Dahal; Shantanu Sarkar; Md. Sarfaraz Asgher
Frequent landslides in the northwestern Himalaya India (NHI) region cause significant loss of life and property, making landslide susceptibility zonation (LSZ) crucial for identifying vulnerable areas. This study aims to develop LSZ maps for the NHI using four bivariate geostatistical models: Frequency Ratio (FR), Weight of Evidence (WoE), Information Value (IV), and Yule's Coefficient (Yc). A total of 38,697 landslides, covering 149.50 km2, were analyzed. The data was split into 70% for training and 30% for testing, ensuring robust model validation. Twelve causative factors were considered, including slope angle, slope aspect, slope curvature, relative relief, terrain roughness index, geomorphon, distance to drainage, land use land cover, lithology, distance to fault/thrust, earthquakes, and rainfall. The models identified high to very high susceptibility zones, covering 28.7%, 32.8%, 48.1%, and 48.2% of the region for the Yc, FR, WoE, and IV models, respectively. ROC analysis revealed that the FR model achieved the highest accuracy, with 0.845 (84.5%) for both validation and prediction. The IV model followed with ROC values of 0.833 (83.3%), while the Yc model performed similarly, with values of 0.831 (83.1%). The WoE model exhibited slightly lower accuracy, with ROC values of 0.830 (83.0%) for validation and 0.831 (83.1%) for prediction. Both the WoE and IV models covered over 98% of landslide areas in high and very high susceptibility zones, indicating a tendency to overestimate highly susceptible areas. The study suggests that the FR and Yc models are particularly effective for LSZ and risk assessment. These results provide valuable insights for hazard management, aiding researchers, planners, and policymakers in selecting appropriate models for LSZ and mitigating landslide risks in other vulnerable regions. © King Abdulaziz University and Springer Nature Switzerland AG 2024.
Analysis of Joint Parameters to Understand it’s Effect on Rock Blasting
(Springer Science and Business Media Deutschland GmbH, 2022) Rajesh Silwal; Suman Panthee; Ashutosh Kainthola
Rock mass consists of intact rock material and joints. Different joint parameters like orientation, spacing, persistence, aperture, infilling play important role in tunnel excavation. In drill and blast tunnel excavation, the propagation of blast shock wave differs from one rock mass to another rock mass based on their properties, because of which nature of rock fragmentation differs. All these directly affects the outcome of tunnel blasting. This study establishes the relationship between different joint parameters and excavation volume. In order to do so four different tunnel section of same tunnel alignment, with different joint properties were chosen and then collected data was processed to understand how different joint properties lead to different excavation volume within same tunnel. It was found that when the strike of the joint is parallel to the tunnel axis, the excavation volume obtained from blasting is comparatively higher than that when strike of joint is perpendicular to the tunnel axis, because when joints are parallel to the tunnel axis there is minimum reflection of blast wave from joint plane causing it to travel farther, increasing the fragmentation process. Shape analysis of blast fragments and natural rock block obtained from 3DEC was done in order to find the effect on fragmentation process. It was found that both blast fragments and natural rock block have similar percentage of different shape class proving fragmentation process during blasting of rock mass follows joint pattern, since they are the weak surface in rock mass. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
Assessment of Karmi Landslide Zone, Bageshwar, Uttarakhand, India
(Springer, 2020) V.N. Tiwari; V.H.R. Pandey; Ashutosh Kainthola; P.K. Singh; K.H. Singh; T.N. Singh
Slope instability is a big challenge for the population in mountainous regions. It poses a threat to life, economy, and infrastructure. For the safety of people, various prevention and precautions are taken and hence many scientific studies are going on. In the present study, the stability of the Karmi landslides zone, Bageshwar, Uttarakhand, India is assessed. Karmi village lies quite close to the northern border of India and the excavated roads are the only means of commute. The area lies in a tectonically active lesser Himalayan zone with high relief. Slope geometry was extracted using a total station, and seven different slope geometries were plotted. Soil and rock mass samples were taken and evaluated from various field and laboratory investigations. The direct shear test was performed to assess the friction angle and cohesion of the soil and rock mass. Numerical simulations viz., finite element analysis and probabilistic analysis have been applied on all seven slope sections and found that the mean and median safety factor of all the modeled slopes was 0.78 and 0.81, respectively. The study ascertains that the whole area to be quite vulnerable to failure, especially during rains, since the pore pressure build-up diminishes the shear strength of the slope forming material. Possible mitigation measures have been suggested based on the examined instability of the hill slopes. © 2020, Geological Society of India.
Association of landslides with geological structures and rainfall: a case study of two landslides in Sunkuda, Nepal
(Springer Science and Business Media B.V., 2025) Rabin Rimal; Megh Raj Dhital; Moti Lal Rijal; Rajesh Silwal; Vikas Yadav; Md Alquamar Azad; Ashutosh Kainthola
Nepal is home to numerous large landslides. These landslides emanate from both intrinsic and extrinsic factors. Though, prevalent in Himalaya, landslides resulting from underlying geological features are given lesser attention. The present research investigates the evolution and progression of two landslides from Sunkuda region, Western Nepal—and their association with the underlying geological structure. Two landslides, A, and B, from the study area present continuous downslope movement. In order to understand the causal factor, geological, geomorphological, and geophysical survey was conducted in the landslide affected area. Geotechnical attributes were obtained to understand the behaviour of the groundmass. Investigation led to the discovery of a thick band of shear zone nearly 35–40 m on the upper slope and 10–20 m on the lower slope, affecting the stability of the hill slope. Both landslides occur within the crushed zone of the thrust. The research found that the pore water transmitted through the developed shear zone increases the pore pressure and triggers failure. Intense monsoonal rainfall was observed and taken into consideration. Furthermore, the evidence indicates a major role played by the thrust fault behind the genesis and evolution of both landslides. It is also found that anthropogenic activities, gully erosion, and toe-cutting by the stream also had a crucial role in the evolution of landslides. © The Author(s), under exclusive licence to Springer Nature B.V. 2025.
Boundary element coupled structural analysis of Lesser Himalayan railway tunnels: A case study of the Shivpuri–Byasi section, Rishikesh–Karnaprayag BG rail link, Uttarakhand, India
(Springer, 2024) Abhishek Srivastav; Vikas Yadav; Ashutosh Kainthola; Vishnu H R Pandey; Vijay Dangwal; T.N. Singh
A tunnel provides reliable, low-maintenance, and all-weather connectivity in hilly terrains. Rishikesh–Karnaprayag Broad Gauge project is a 125 km long rail link, that includes 35 bridges and 17 tunnels, to connect the tough route of Uttarakhand Chardham sites. This tunnel route passes through the Lower Himalayas of Uttarakhand, India. The present research emphasizes the structural discontinuities’ influence on tunnel stability at different chainages (18570 to 32000) with a 13.4 km long span, having variable overburden and rock mass conditions. The factor of safety is determined using kinematic analysis and numerical simulation based on the boundary element method. The boundary element method examines the excavation problems and captures the interaction of the tunnel structure and surrounding rock mass. Different rock mass classification schemes are also utilized to evaluate the rock mass conditions. Schemes mainly include rock mass rating (RMR), Q-system and Ö-NORM B2203 (NATM class), suggesting that the rock mass quality ranges from poor to fair. The factor of safety for critically unstable wedges without support varies between 0.49 and 0.98, and after applying shotcrete and rock bolting, FOS varies between 0.63 and 3.23. In the present study, the overburden varies between 33 and 590 m. The influence of applied computational support (shotcrete and rock bolting) has been studied with an average value of factor of safety at each 100 m interval. The study outcomes may be significant in supporting estimation during similar rock mass conditions. © Indian Academy of Sciences 2024.
Comparative study of predicted and actual rock mass condition in Himalayan railway tunnels
(Elsevier Ltd, 2025) Vikas Yadav; Ashutosh Kainthola
Rishikesh-Karnprayag BG Rail Link project in Uttarakhand Himalaya, presents excavation challenges due to the complex geological setting. This study investigates discrepancies between predicted and actual rock mass conditions, encountered during the excavation of the package-5 tunnel. Despite thorough pre-construction investigation, through bore log data, in-situ tests and geophysical surveys, substantial deviations in rock quality were observed during the construction. Deviation in rock mass conditions force change in support classes, ultimately overrunning the project cost. This study aims to investigate the disparity between the predicted and actual rock mass conditions, with respect to overburden thickness. RMR, Q-System and ÖNORM B 2203, have been utilized to discern the rockmass character. A total of 632 data points were collected in the field. Lithology, presence of shear zones, and overburden thickness have been discussed to understand variance between predicted and actual rockmass condition, during the excavation. Study highlights the presence of shear zones and other uncertainties play a crucial role in discrepancies between predicted and actual conditions. At shallower depths, overestimation of rockmass is identified, with actual RMR values being lesser, along with high deviations. As overburden depth increases, the predicted and actual rockmass distributions become more aligned and fall close to each other. Additionally, four different predictive models—Random Forest (RF), Linear Regression (LR), Support Vector Regression (SVR), and K-Nearest Neighbors (KNN) are also employed in this study to estimate actual rockmass, using predicted rockmass and overburden thickness as features. This research will ultimately aid in better planning and cost management for future Himalayan tunneling projects. © 2025 Elsevier Ltd
Comparative study of the deformation modulus of rock masses—a reply to the comments received from Gokceoglu (2018)
(Springer Verlag, 2018) Suman Panthee; P.K. Singh; Ashutosh Kainthola; Ratan Das; T.N. Singh
Availability of information on the deformation modulus in the initial stages of civil engineering projects related to near-surface or underground excavation is very important for design purposes. However, direct determination of the deformation modulus is a challenging task and a potentially costly one; therefore, several researchers have frequently used indirect methods to assess the deformation modulus. Of the significant number of empirical equations that can be found in literature, most are non-linear, which makes the deformation modulus a parameter that is very sensitive to the quality and types of data used. © 2018, Springer-Verlag GmbH Germany, part of Springer Nature.
Decoding Landslide Susceptibility in Wayanad District of Kerala, India, Using Machine Learning Approach
(Springer Science and Business Media Deutschland GmbH, 2025) Imran Khan; Ashutosh Kainthola; Harish Bahuguna; Vikas Yadav; Vishnu Himanshu Ratnam Pandey; Gaurav Kumar Kushwaha
Landslide Susceptibility Zonation (LSZ) is essential for comprehending and predicting landslide events, especially in areas prone to natural hazards. This study assesses and contrasts the efficacy of two machine learning (ML) algorithm, Random Forest (RF) and Support Vector Machine (SVM), in producing high resolution LSZ maps for the Wayanad area in Kerala, India. The region is significantly susceptible to landslides, as evident by a disastrous occurrence on July 30, 2024, which led to more than 300 deaths and impacted almost 5,000 individuals. LSZ map was created using twelve landslide conditioning factors (LCFs) at a spatial resolution of 12.5 × 12.5 m. The evaluation of multicollinearity confirmed the independence of the explanatory factors. The model training utilized a balanced dataset consisting of 314 landslide and 314 non-landslide sites. The RF model revealed high susceptibility zones including 23.8% of the study region, while the SVM model recognized 19.5%. These zones are primarily located along the southwestern, western, and northwestern boundaries of Wayanad. The predictive capacities of the models, assessed using Receiver Operating Characteristic (ROC) analysis, demonstrated accuracies of 95.8% for RF and 93.5% for SVM, reflecting the strong performance of both techniques. The findings highlight the efficacy of ML algorithm, particularly RF, in LSZ, offering critical insights for hazard mitigation and land-use planning in comparable geologically vulnerable areas. © King Abdulaziz University and Springer Nature Switzerland AG 2025.
Deep learning models for large-scale slope instability examination in Western Uttarakhand, India
(Springer Science and Business Media Deutschland GmbH, 2022) Vishnu Himanshu Ratnam Pandey; Ashutosh Kainthola; Vikram Sharma; Abhishek Srivastav; T. Jayal; T.N. Singh
Slope failures are avoidable accidents in most of the scenarios. The eventuality of a failure leads to loss of lives and destruction, especially in hilly areas. Investigation, analysis and prediction of slope failure is a reliable approach to avert such mishaps. Hence, the present research work delves into the prediction of landslides and slope failures through numerical simulation and a deep learning approach. Field attributes and laboratory-tested strength data from Lower Tons Valley, Northern India has been taken as a case study. Initially, a total of 185 slope models were simulated in a finite difference code by varying four slope parameters, namely, slope angle, slope height, cohesion and angle of internal friction. These simulated results were further divided into two parts, one part with 148 datasets for the training of models and other part consisting of 37 datasets for testing of models. Two artificial neural network prediction models, along with a conventional multi-linear regression model was developed and their accuracy was accessed. The developed neural network models superseded the conventional model, in terms of performance and accuracy, as shown by statistical approaches R2 and mean squared error values. Moreover, the neural network model with Adam optimizer achieved higher statistical accuracy than the one with stochastic gradient descent optimizer. However, all these deep learning models demonstrate significant performance, and can be used by geo-engineers for swift prediction of safety factors for excavated slopes in the study area. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.
Discontinuity-Induced Partial Instability in Markundi Hills, Sonbhadra, Uttar Pradesh, India
(Springer Science and Business Media Deutschland GmbH, 2024) Vikas Yadav; Ashutosh Kainthola; Vishnu H. R. Pandey; Gaurav Kushwaha; T.N. Singh
State Highway-05A in Northern India, connects the states of Chhattisgarh, Madhya Pradesh, Uttar Pradesh, and Jharkhand. In Uttar Pradesh, it passes through steep and rugged Markundi Hill, composed of highly jointed sandstone. The current study examines road-cut slopes at six locations to quantify the instability mechanism and slope health. Detailed field and laboratory investigations were combined to ascertain the structural, petrographic, and strength attributes of the rock. Afterwards, data was collated to characterise the rockmass behaviour through widely accepted classification schemes, viz., geological strength index (GSI), Q-slope, rock mass rating (RMR), slope mass rating (SMR), and modified global slope performance index (modified GSPI). The value ranges provided by various empirical classifications are 40–62 (RMR), 39.61–58.46 (SMR) and modified 44.57–52.57 (GSPI). For structural stability, kinematic analysis was conducted. According to RMR, five locations fall in fair and one in poor rockmass classes. SMR suggest all locations are partially stable. Eventually, a novel approach for finding the ratings of GSPI is also introduced in the present work, allowing more comprehensive discontinuity characteristics incorporation. The new approach brings GSPI and SMR to the same scale, making it easy to compare the two. GSPI yields that all the locations have high chances of local bench failures. Compared to other approaches, GSPI predicts a wide range of instabilities and should be used alone or in conjunction with other systems for slope stability assessment. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.
Efficiency of Classification Algorithms for Prediction of Rock Mass ÖNORM B Class in Himalayan Tunnelling
(Springer, 2025) Ashutosh Kainthola; Md Alquamar Azad; Abhishek Srivastav; Vikas Yadav; T. N. Singh; Vijay Dangwal
For underground excavation, accurate assessment of rock mass behaviour is imperative for a robust design of support system. For the ambitious, broad gauge rail link project in Uttarakhand Himalaya, India, apart from Q, and RMR, ÖNORM B system is being used for tunnel support recommendation. However, ÖNORM B system is qualitative in nature, and thus measurement of surrounding rock mass deformation is measured to designate the rock class. This approach is expensive and not often feasible. Therefore, present study attempts, perhaps for the first time, to quantify the prediction of ÖNORM B class of rock mass, using five easy to assess parameters. Two parameters from RMR, two from Q-system, and one common in both were used as inputs. Nine standard machine learning classifiers have been trained on 873 rows of data, and validated on 218 data points. Accuracy, precision, and ROC were evaluated for each classification algorithm. Results are quite promising with highest accuracy and precision in predicting the ÖNORM B class, delivered by Extra Tree, Random Forest, and Decision Tree classifiers. However, the authors recommend Extra Tree classifier since they are the least prone to overfitting and can be generalized. © The Author(s), under exclusive licence to Indian Geotechnical Society 2025.
Empirical and Numerical Evaluation of a Cut Slope Near Rishikesh, India
(Springer Science and Business Media Deutschland GmbH, 2022) V.H.R. Pandey; Ashutosh Kainthola; T.N. Singh
The stability analysis of cut slopes along any transportation corridor is necessary to safeguard people’s and societal interests. The present work presents assessment of a steep rock cut slope near Rishikesh, along a national highway in Uttarakhand, India. The work details empirical and numerical examination of the slope stretching approximately 20 m in length along the road. The field investigation has been undertaken to ascertain discontinuities conditions, their orientations, spacing between them, geological strength index as well as slope geometries. Three joint sets were recorded with spacing of 10–120, 5–45, 6–35 cm respectively, with slope angle of 75° and slope height equal to 65 m. Moreover, the rock samples were taken in laboratory to further discern required geotechnical parameters such as unconfined compressive strength, Young’s modulus, and Poisson’s ratio etc. The empirical and numerical techniques were applied to examine the slope’s health. Q-slope and Slope Mass Rating were the employed empirical method. Besides, the finite element approach was adopted to assess the slope stability numerical. Finally, outcomes of all these scientific assessments were compared with each other and ground reality. The Q-slope values achieved was 1.58 for the concerned slope, while the SMR value was 37. Finite element simulation yielded a safety factor of 1.6 for the dry condition. Furthermore, kinematic analysis of slope shows the possibility of planar and wedge modes of failures. Keeping in view the attained results, the slope should be excavated at an angle of 69°, while also making provisions for drainage of rain water. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
Empirical and numerical hill slope health evaluation at Malling Nala, NH-505, Himachal Pradesh, India
(Springer, 2025) Md Alquamar Azad; Ashutosh Kainthola; Yewuhalashet Fissha; Gaurav Kumar Kushwaha; Vikas Yadav; T. N. Singh
Slope failures and rock mass movements are continuous geomorphic processes, particularly in a dynamically charged terrane like the Himalaya. Thus, failures emanating from weak geology, hydrogeology and anthropogenic disturbances are aplenty. Present research evaluates slope stability in the vicinity of Malling Nala, along NH-505 in Himachal Pradesh, India. For the two most vulnerable sections in the study area, geo-mechanical and structural attributes have initially been ascertained. Field surveys and laboratory tests identified weak and weathered mica schist and gneissic rocks in the study area. Kinematic analysis, Rock Mass Rating (RMR), Geological Strength Index (GSI), Slope Mass Rating (SMR), modified Global Slope Performance Index (mGSPI) led to determination of possible failure mechanism and rock mass behaviour. Finite element analysis provided a comprehensive understanding of slope behaviour under various conditions, highlighting significant shear strain and displacement in both sections. As noticed from the field and classification schemes, planar and localized bench failures were established. Slope section L-1 was found to collapse under saturated water condition, manifesting the influence of snow melt. The findings indicate that both natural and human factors are causing instability. Effective risk management and mitigation strategies are essential to maintain the stability and reliability of this critical frontier region. © The Author(s) 2025.
Engineering geological characteristics and failure mechanics of Jure rock avalanche, Nepal
(Springer Science and Business Media Deutschland GmbH, 2023) Suman Panthee; Suman Dulal; Vishnu Himanshu Ratnam Pandey; Vikas Yadav; Prakash Kumar Singh; Ashutosh Kainthola
Introduction: The rock avalanches are a frequent and disruptive phenomenon in the Himalayas and other mountain chains. To minimize future losses, it is essential to investigate the engineering geological causative factors and mechanism of these mass wasting events. Study area: The present work is aimed at assessing the failure mechanism of the disastrous 2014 Jure rock avalanche along Araniko Highway, Northern Nepal. The event had blocked the Sunkoshi River and blocked an economically significant route to China. Geotechnical properties and analysis: Initially, rockmass characterization and intact strength attribute were determined for the site to classify the failure zone. The parameters measured and obtained from the field and laboratory were integrated into the analytical models to obtain a conclusive interpretation of the failure mechanism. Structural, kinematic, and key block theory analyses have been carried out for decipher the evolution of the failure zone. Results and discussion: Rock mass was found to be of fair quality, however, the structural instabilities and the presence of water has led to a progressive failure. Movement of the key block and subsequent sliding of wedges and foot failure appears to be a possible failure mechanism. Conclusion: The present research explores the contributory engineering geological aspects of the Jure rock avalanche. The investigation results can be used to tackle similar large scale rock avalanches in similar geological terrains and thus minimizing the losses. © 2023, The Author(s).
Ensemble Algorithms for Prediction of Ripping Production in Sedimentary Rocks
(Springer, 2025) Edy Tonnizam Mohamad; Ramesh Murlidhar Bhatawdekar; Vishnu Himanshu Ratnam Pandey; Ashutosh Kainthola
In the earlier stages of mine planning, geo-engineers and planners need a reliable estimation of ripper production. For weak and fractured rocks, definitive geotechnical information has the potential to yield an estimate of the mine site rippability. These parameters usually have some hidden pattern relating them with ripper production for machine being employed. Today, in the era of advanced computing and artificial intelligence, decoding these hidden patterns through machine learning techniques have become a viable option. Therefore, in the present research the rippability estimation was accomplished through several ensemble machine learning techniques based on the five laboratory tested data. Ensemble models like Extra Tree, Gradient Boosting, Histogram Gradient Boosting, AdaBoost, Bagging, and Voting have been developed in the present work. The five geotechnical attributes viz., uniaxial compressive strength, Brazilian tensile strength, slake durability index, point load index, & P-wave velocity have been used as feature variables. The influence on rock mass weathering grade on ripper production has also been investigated in the present research. Additionally, a linear regression model was developed to compare the accuracy of the advanced artificial intelligence models with it. The statistical means to compare the prediction accuracy of the presently developed algorithms are the R2 and mean absolute error (MAE). The Extra Tree regressor beats all other models and achieved a highest R2 and least MAE value among all other algorithms. Comparatively, linear model had displayed statistically impoverished performance in the present research work. © The Institution of Engineers (India) 2025.
Evaluation of Machine Learning Models for Ore Grade Estimation
(Springer Science and Business Media Deutschland GmbH, 2022) Gaurav Jain; Pranjal Pathak; Ramesh Murlidhar Bhatawdekar; Ashutosh Kainthola; Abhishek Srivastav
Geostatistics has been widely used for qualitative estimation of ore deposits for many decades. However, ore quality does not vary uniformly in three dimensions which results in a poor quality estimation with the conventional geostatistical methods. Also, the time required for processing geostatistical data can be substantially high. On the other hand, with the advancement in computational processing power and development of advanced algorithms on artificial intelligence (AI) and machine learning (ML), the requirements of an accurate ore grade estimation in reasonable computation time can be fulfilled. In this paper, the applicability of various machine learning techniques like artificial neural network (ANN), extreme learning machine (ELM), gradient boosted decision trees (GBDT), random forests (RF), support vector regression (SVR) have been discussed for ore grade estimation of different mineral deposits like iron, gold and copper. This study also cross-examines the results of ordinary kriging (OK) and inverse distance weighted (IDW) techniques for qualitative estimation. Correspondingly, statistical parameters such as coefficient of determination (R2) and root mean squared error (RMSE) have also been taken into account for a better understanding of the models. Nowadays, AI/ML techniques are extensively used in multiple fields worldwide, including the mining sector, due to their fast and efficient prediction capability. The investigation of these models highlights the importance of accuracy in predicting the quality of the ore as the latter greatly impacts the economic feasibility of mineral deposits. This study forms a ground for developing new advanced intelligent approaches for improving the accuracy of ore grade estimation for mineral deposits. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
Field data driven rockfall hazard and risk assessment along Sangla-Chitkul road, Himachal Pradesh, India
(Springer Science and Business Media Deutschland GmbH, 2025) Vishnu Himanshu Ratnam Pandey; Gaurav Kumar Kushwaha; Ashutosh Kainthola; Vikas Yadav; T. N. Singh; Abhi S. Krishna
This study addresses the issue of rockfall hazard in Baspa Valley, Himachal Pradesh, India. Proven empirical rockfall hazard rating systems were interpolated in the GIS-environment to analyse the contingent risk to the population. Initially, field data were ascertained from precarious rockfall locations along the 23 km long Sangla-Chitkul road. This was followed by a kinematic analysis to identify potential structural failure modes, revealing that each studied slope section could undergo one or a combination of failures. Rockfall Hazard Rating System (RHRS) parameters were formulated and interpolated for the entire area using the inverse-distance weighting (IDW) technique. Resulting hazard map, overlaid with population data, classified rockfall risk into five categories: very high (14.7%), high (28.8%), moderate (23.2%), low (18.6%), and very low (14.7%). A similar assessment using the Missouri Rockfall Hazard Rating System (MORFH-RS) showed the following rockfall risk distribution: very high (11%), high (21%), moderate (21%), low (21%), and very low (11%). Additionally, MORFH-RS indicated that around 90% of the area lies in high-risk and high-consequence zone, with high consequences for all locations. Two-dimensional stochastic simulations were conducted to understand rockfall dynamics at all studied locations, revealing that most sites exhibit kinetic energy exceeding 500 kJ, with five locations surpassing 1000 kJ. This indicates a high potential for significant damage across a large area of the valley, based on runout-distance data. Additionally, these findings were correlated with geotechnical characterization using Global Slope Performance Index (GSPI), identifying the potential for four distinct failure types in the valley. © The Author(s) 2025.
Geotechnical and micro-structural characteristics of phyllite derived soil; implications for slope stability, Lesser Himalaya, Uttarakhand, India
(Elsevier B.V., 2021) T. Ansari; Ashutosh Kainthola; K.H. Singh; T.N. Singh; M. Sazid
Collapses of hill slopes along critical roadways are of dire consequence. Large literature is available on the stability assessment of hill slopes composed of rock and soils; however, a lacuna exists when it comes to geotechnical appraisal and instability aspects of slopes composed of in-situ saprolitic soils. The present study examines the physical, micro-structural and geotechnical characteristics of soil derived phyllite, and its ensuing influence on the instability of hill slopes at certain sections along National Highway-7, Uttarakhand, India. Four distinct locations along the highway were selected for the study. After field survey, the laboratory investigation was carried out to ascertain the geotechnical, chemical and mirco-structural parameters of the representative phyllitic soil samples. Eventually, stability analysis was carried out using Limit Equilibrium Method, Finite Element Method, and Finite Difference method, for the four locations. The analysis for location 2 & 4 showed them to be in a critical - unstable state, whereas, location 1 & 3 demonstrated stability in the present state. Compared to other techniques, FDM analysis results were in close congruence with the ground truth. The present study also sheds significant insight into the composition and deformation behaviour of the soils derived from the weathering of phyllite. The research may have enormous ramifications for the future assessment of similar soils and their possible use as admixtures in construction industry. © 2020 Elsevier B.V.