Browsing by Author "Ramesh Murlidhar Bhatawdekar"

Now showing 1 - 7 of 7

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.
Introduction to the Special Issue on Computational Intelligent Systems for Solving Complex Engineering Problems: Principles and Applications
(Tech Science Press, 2024) Danial Jahed Armaghani; Ahmed Salih Mohammed; Ramesh Murlidhar Bhatawdekar; Pouyan Fakharian; Ashutosh Kainthola; Wael Imad Mahmood
[No abstract available]
Machine learning models for prediction of blasting induced ground vibrations in basaltic rocks: a case study from Navi Mumbai Airport quarry, India
(Springer Science and Business Media Deutschland GmbH, 2025) Ramesh Murlidhar Bhatawdekar; T. N. Singh; Prakash Y. Dhekne; Ashutosh Kainthola; Edy Tonnizam Mohamad; Sanjay Purohit; Vishnu Himanshu Ratnam Pandey; Vikas Yadav
Ground vibrations are a deleterious consequence of blasting. Peak particle velocity is used to assess the strength of the ground vibrations, and it usually estimated before the blasting operations. Traditional ground vibration predictors simplify the estimation by considering the maximum charge per delay and the distance from the blast site. Thus, the combined effect of the blast design parameters on the peak particle velocity is disregarded. Artificial intelligence algorithms can be used for the prediction of peak particle velocity considering the collective effects of the blast design parameters. The present research evaluates the different regression algorithms for prediction of the peak particle velocity of blast-induced ground vibrations. Feature used are the ratios of: spacing and burden, stemming and burden, blast hole depth and burden, burden and diameter, charge factor, maximum charge per delay, and the distance of the monitoring station and the target variable is peak particle velocity. A dataset consisting of 418 blasts carried out at the site in Western India. Thereafter, the supervised viz. Extra Tree, Extra Gradient Boost, Random Forest, Light Gradient Boosting Machine, Decision Tree, Support Vector have been adopted to predict the target variable. The results indicate that all the above methods have predicted the peak particle velocity with reasonable accuracy. It further shows that the Extra Tree regressor exhibits highest R2 score of 0.88, for the test set, with a RMSE of.434. The study concludes that tree-based ensemble techniques can be used for reliable prediction when the data set is limited. © Springer Nature Switzerland AG 2025.
Recent Developments in Machine Learning and Flyrock Prediction
(Springer Science and Business Media Deutschland GmbH, 2022) Ramesh Murlidhar Bhatawdekar; Ashutosh Kainthola; V.H.R. Pandey; Singh Trilok Nath; Edy Tonnizam Mohamad
The blasting techniques are employed in mining and underground works to loosen the rock mass and ease the excavation. The blasting practices are economical and swifter in terms of their engineering application, however, they are of major environmental and safety concerns. The major issues related to blasting are flyrock, air over pressure, and ground vibrations etc. The rock fragments of rockmass are thrown outward after blasting, which can be threat to workers and machineries involved in the work, and sometimes nearby human settlements can be its victim. Therefore, an accurate prediction of the flyrock distance is the needed by mining practitioners. Earlier, experts have developed several empirical methods based on certain known parameters to assess flyrock distance. However, with time they become irrelevant and were easily replaced with advanced machine learning algorithm. The present study reviews some of these latest publications (2019–2021) examining flyrocks through artificial intelligent technique. The study incorporates types of machine learning models employed, input parameters used and number of datasets supporting the models. The input parameters were further classified according to rock-mass properties, blast design at site, and explosives responsible for blasting. Moreover, to compare the reliability of the model coefficient of correlation of the testing data of the all the documented model were evaluated. Rock density, rock mass rating and Shmidt hammer rebound number (SHRN) were found to be uncertain parameters. Artificial Neural Network (ANN) and other hybrid models for prediction of flyrock were compared. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
Towards sustainable sand resource management - Best governance practices and alternatives to river sand in India
(Springer, 2025) Ramesh Murlidhar Bhatawdekar; Edy Tonnizam Mohamad; T. N. Singh; Dato Hock Soon Chengong; Ashutosh Kainthola; Manoj Khandelwal; Feten Chihi; Vynotdni Rathinasamy; Clement Kweku Arthur; Anand Ravi Deshpande; Sanjay Nigam; Sangki Kwon; Rahul V. Ralegaonkar; Md Alquamar Azad
[No abstract available]
Unmanned Aerial Vehicles Technology for Slope Hazard Assessment, Monitoring, and Post Failure Management
(Springer International Publishing, 2023) Prakash Biswakarma; Ashutosh Kainthola; Ramesh Murlidhar Bhatawdekar; Varun Joshi; Edy Tonnizam Mohamad
Alleviation of slope failures and landslides demands an in-depth investigation to ascertain the causes, triggers, existing and future instability aspects, along with the design of protection measures. Data collection for these studies usually involves field visits, which can be time-consuming and do not provide real-time data. Alternatively, geomorphic analysis can be carried out using high-resolution satellite images, which are plagued with the issue of resolution. Various methodologies for slope assessment and monitoring were reviewed. Field investigation using geotechnical methods is time-consuming and may not be possible to assess difficult terrain. Even though remote sensing methods are used for slope assessment and monitoring, there is a limitation to acquiring real-time data for a smaller area, which may not be cost-effective. Unmanned Aerial Vehicles (UAV) technology is improving faster and has an advantage over other technology. The present article elaborates on the advantages of using UAV to acquire such critical data. A thorough assessment, based on resolution (temporal and spatial), operation cost, type of data acquired, deployment of operation, and limitations, is presented here. A case towards using UAVs to ascertain the geotechnical data pertaining to the discontinuity distribution and properties has also been discussed. The available literature posits the superiority of UAV-enabled field investigation and data collection. UAVs are especially useful for frontier areas where access can be an issue. UAV also safeguards the people at the site. UAV is also suitable for post-disaster management of landslides. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2023