Atul Kumar Patidar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Atul Kumar Patidar has a total of 72 co-authors. Here are the top co-authors by number of shared publications:
- Girish Ch Kothyari
Department of Petroleum Engineering and Earth Science, UPES, Dehradun, India
5 shared publications - Tanupriya Choudhury
School of Computer Sciences, University of Petroleum and Energy Studies (UPES), Dehradun, India
5 shared publications B. Goyal
3 shared publicationsD. M. Maurya
Department of Geology, The Maharaja Sayajirao University of Baroda, Vadodara-390002, India
3 shared publicationsD.M. Maurya
3 shared publications- Jitendra Shital Sangwai
Indian Institute of Technology Madras
3 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Frontiers Media SA in Frontiers in Earth Science
- Vol. 14, 1915184
Comparative analysis of ensemble and linear models for geophysical Delta-T compressional (DTC) well log imputation and reconstruction
Delta-T Compressional (DTC) well logs provide important sonic information for formation evaluation and subsurface characterization, but incomplete or unavailable sonic-log measurements can limit subsequent interpretation. This study evaluates six supervised machine-learning models Multiple Linear Regression, SGD Regressor, K-Nearest Neighbors (KNN), Multi-Layer Perceptron (MLP), Random Forest, and XGBoost for DTC log reconstruction using well-log data from the Taranaki Basin, New Zealand. The dataset was cleaned, depth-aligned, and divided into an 80% training set and a 20% internal test set. Three independent wells were reserved for blind testing. Hyperparameter optimization was performed using randomized search with 2-fold cross-validation for the selected nonlinear models. On the internal test dataset, Random Forest achieved the highest R2 of 0.96, followed by KNN and XGBoost, both with an R2 of 0.93. Independent blind testing showed that model performance varied between wells. SGD achieved an R2 of 0.85 for Trapper-A1, XGBoost achieved 0.71 for Ahuroa South B-1, and MLP achieved 0.81 for Kahili-1C. MLP and XGBoost showed relatively better performance across the independent wells. The predicted DTC profiles reproduced the overall trends of the observed logs, although larger deviations occurred in some depth intervals. An uncertainty analysis based on MLP P5–P95 prediction intervals showed empirical coverage of 33.30%, 25.31%, and 29.32% for the three blind-test wells, indicating that the estimated uncertainty intervals were narrower than the observed prediction variability. The proposed workflow can support DTC reconstruction in wells with incomplete or unavailable sonic-log measurements and may provide useful input for formation evaluation, geomechanical analysis, and hole-cleaning studies. Further validation using additional wells and improved uncertainty-calibration methods is required before broader application.
- 6 November 2026
- Published by Frontiers Media SA in Frontiers in Earth Science
- Vol. 14, 1915184
Open AccessComparative analysis of ensemble and linear models for geophysical Delta-T compressional (DTC) well log imputation and reconstruction
Delta-T Compressional (DTC) well logs provide important sonic information for formation evaluation and subsurface characterization, but incomplete or unavailable sonic-log measurements can limit subsequent interpretation. This study evaluates six supervised machine-learning models Multiple Linear Regression, SGD Regressor, K-Nearest Neighbors (KNN), Multi-Layer Perceptron (MLP), Random Forest, and XGBoost for DTC log reconstruction using well-log data from the Taranaki Basin, New Zealand. The dataset was cleaned, depth-aligned, and divided into an 80% training set and a 20% internal test set. Three independent wells were reserved for blind testing. Hyperparameter optimization was performed using randomized search with 2-fold cross-validation for the selected nonlinear models. On the internal test dataset, Random Forest achieved the highest R2 of 0.96, followed by KNN and XGBoost, both with an R2 of 0.93. Independent blind testing showed that model performance varied between wells. SGD achieved an R2 of 0.85 for Trapper-A1, XGBoost achieved 0.71 for Ahuroa South B-1, and MLP achieved 0.81 for Kahili-1C. MLP and XGBoost showed relatively better performance across the independent wells. The predicted DTC profiles reproduced the overall trends of the observed logs, although larger deviations occurred in some depth intervals. An uncertainty analysis based on MLP P5–P95 prediction intervals showed empirical coverage of 33.30%, 25.31%, and 29.32% for the three blind-test wells, indicating that the estimated uncertainty intervals were narrower than the observed prediction variability. The proposed workflow can support DTC reconstruction in wells with incomplete or unavailable sonic-log measurements and may provide useful input for formation evaluation, geomechanical analysis, and hole-cleaning studies. Further validation using additional wells and improved uncertainty-calibration methods is required before broader application.
- 25 July 2026
- Published by Springer Nature
- p. 149-159
Status of CCUS Project Viability for Mumbai Offshore and Cambay Basins, Western India
- 25 July 2026
- Published by Springer Nature
- p. 149-159
Status of CCUS Project Viability for Mumbai Offshore and Cambay Basins, Western India
- 23 June 2026
- Published by Wiley in Geological Journal
Comparative Assessment of Land Stability Analysis of Towns of the Kumaun Himalaya, Uttarakhand
The rapid urbanization across the Kumaun Himalaya has made it gradually necessary to evaluate land stability, as unstable land can significantly increase the risks of disasters. The present study conducts a comparative analysis of the three rapidly growing towns of Kumaun Himalaya, namely Almora, Haldwani, and Nainital, using a comparative geospatial framework that applies the Analytical Hierarchy Process (AHP) and Shannon Entropy (SE) approach. Thirteen conditioning factors influencing land stability were considered to delineate stability zones. The final stability maps divide the area into five stability classes. The stability assessment of Haldwani town using the AHP technique reveals that nearly 42% of its area lies in the very low to moderate stability zone. Likewise, for Almora town, it shows about 60% of the area that comes under very low to moderate stable zones. Similarly, for Nainital town, it shows about 62% of its area lies in very low to moderate stable zones. On the contrary, the stability analysis results of the SE technique reveal that Almora falls under 50% of the total area in very low to moderate stability zones. Haldwani town highlights ~47% of the area lies in very low to moderate stability zones. Nainital town demonstrates about 53% of the area in very low to moderate stability classes. The AHP and SE models were validated using Receiver Operating Characteristic (ROC) curve, which yielded Area Under Curve (AUC) values of 0.879 for Haldwani, 0.763 for Nainital, and 0.794 for Almora for the SE model, and 0.948 for Haldwani, 0.742 for Almora, and 0.769 for Nainital for the AHP model. The comparison of AHP and SE results enhances reliability, offering valuable guidance for sustainable urban development and hazard mitigation in the Himalayan region.
- 23 June 2026
- Published by Wiley in Geological Journal
Comparative Assessment of Land Stability Analysis of Towns of the Kumaun Himalaya, Uttarakhand
The rapid urbanization across the Kumaun Himalaya has made it gradually necessary to evaluate land stability, as unstable land can significantly increase the risks of disasters. The present study conducts a comparative analysis of the three rapidly growing towns of Kumaun Himalaya, namely Almora, Haldwani, and Nainital, using a comparative geospatial framework that applies the Analytical Hierarchy Process (AHP) and Shannon Entropy (SE) approach. Thirteen conditioning factors influencing land stability were considered to delineate stability zones. The final stability maps divide the area into five stability classes. The stability assessment of Haldwani town using the AHP technique reveals that nearly 42% of its area lies in the very low to moderate stability zone. Likewise, for Almora town, it shows about 60% of the area that comes under very low to moderate stable zones. Similarly, for Nainital town, it shows about 62% of its area lies in very low to moderate stable zones. On the contrary, the stability analysis results of the SE technique reveal that Almora falls under 50% of the total area in very low to moderate stability zones. Haldwani town highlights ~47% of the area lies in very low to moderate stability zones. Nainital town demonstrates about 53% of the area in very low to moderate stability classes. The AHP and SE models were validated using Receiver Operating Characteristic (ROC) curve, which yielded Area Under Curve (AUC) values of 0.879 for Haldwani, 0.763 for Nainital, and 0.794 for Almora for the SE model, and 0.948 for Haldwani, 0.742 for Almora, and 0.769 for Nainital for the AHP model. The comparison of AHP and SE results enhances reliability, offering valuable guidance for sustainable urban development and hazard mitigation in the Himalayan region.
- 11 June 2026
- Published by IOP Publishing in Engineering Research Express
- Vol. 8 (12)
Highway Expansion and Landslide Susceptibility in the Lesser Himalaya: Geospatial Modelling and Structural Analysis Along the Chamba–Sainj Corridor
Landslides pose significant challenges to infrastructure development in mountainous regions, particularly along highways constructed in geologically fragile and tectonically sensitive terrains. This study examines the effect of road widening on the landslide susceptibility in the Chamba-Sainj corridor (NH-94 and NH-108) in Uttarkashi and Tehri districts, Uttarakhand. It can be observed from this study that the widening of highways plays a major role in changing the pattern of landslide susceptibility, especially in zones where slope failures are kinematically controlled due to the presence of structurally complicated areas. A temporal landslide inventory for 2012-2022 years was made in the buffer of the highway at 500 meters. Fourteen causative factors have been selected for making Landslide Susceptibility Zonation (LSZ) maps based on three bivariate models viz Frequency Ratio (FR), Information Value (IV) and Shannon Entropy (SE). The models' effectiveness was measured through the value of Area Under the Curve (AUC) that was more than 90% in case of the pre-expansion and 85% for the post-expansion, showing that models performed well. Although slope stability showed improvement after expansion, HS and VHS zones were highly concentrated in some critical sections. In the SE model, there was an increase of 6.21% in the VHS class mainly due to unstable slope cutting, poor drainage, and slope toe cutting. Kinematic Analysis was done at 16 SMR values were notably lower at active failure sites, confirming the structural control on slope instability. This study highlights the significance of combining susceptibility models with outcrop-scale structural analysis to support sustainable infrastructure development and reduce geohazard risks in the Himalayan region.
- 11 June 2026
- Published by IOP Publishing in Engineering Research Express
- Vol. 8 (12)
Highway Expansion and Landslide Susceptibility in the Lesser Himalaya: Geospatial Modelling and Structural Analysis Along the Chamba–Sainj Corridor
Landslides pose significant challenges to infrastructure development in mountainous regions, particularly along highways constructed in geologically fragile and tectonically sensitive terrains. This study examines the effect of road widening on the landslide susceptibility in the Chamba-Sainj corridor (NH-94 and NH-108) in Uttarkashi and Tehri districts, Uttarakhand. It can be observed from this study that the widening of highways plays a major role in changing the pattern of landslide susceptibility, especially in zones where slope failures are kinematically controlled due to the presence of structurally complicated areas. A temporal landslide inventory for 2012-2022 years was made in the buffer of the highway at 500 meters. Fourteen causative factors have been selected for making Landslide Susceptibility Zonation (LSZ) maps based on three bivariate models viz Frequency Ratio (FR), Information Value (IV) and Shannon Entropy (SE). The models' effectiveness was measured through the value of Area Under the Curve (AUC) that was more than 90% in case of the pre-expansion and 85% for the post-expansion, showing that models performed well. Although slope stability showed improvement after expansion, HS and VHS zones were highly concentrated in some critical sections. In the SE model, there was an increase of 6.21% in the VHS class mainly due to unstable slope cutting, poor drainage, and slope toe cutting. Kinematic Analysis was done at 16 SMR values were notably lower at active failure sites, confirming the structural control on slope instability. This study highlights the significance of combining susceptibility models with outcrop-scale structural analysis to support sustainable infrastructure development and reduce geohazard risks in the Himalayan region.
- 27 March 2026
- Published by Springer Nature in Journal of Mountain Science
- Vol. 23 (3) , 1079-1104
Assessing neotectonic deformation and terrain evolution through geospatial morphometric techniques across the MBT zone, NW Himalaya
- 27 March 2026
- Published by Springer Nature in Journal of Mountain Science
- Vol. 23 (3) , 1079-1104
Assessing neotectonic deformation and terrain evolution through geospatial morphometric techniques across the MBT zone, NW Himalaya
- 20 January 2026
- Published by Springer Nature in Spatial Information Research
- Vol. 34 (1) , 11
Geohazard dynamics in Kumaon and Garhwal regions of Uttarakhand Himalayas: a critical review of trends and socio-environmental impacts
- 20 January 2026
- Published by Springer Nature in Spatial Information Research
- Vol. 34 (1) , 11
Geohazard dynamics in Kumaon and Garhwal regions of Uttarakhand Himalayas: a critical review of trends and socio-environmental impacts
- 5 September 2025
- Published by Springer Nature in Pure and Applied Geophysics
- Vol. 182 (10) , 4113-4135
ML-Based Geophysical Well Log Prediction for Subsurface Energy Applications: A Stratified Analysis of Feature Sets and Model Performance
- 5 September 2025
- Published by Springer Nature in Pure and Applied Geophysics
- Vol. 182 (10) , 4113-4135
ML-Based Geophysical Well Log Prediction for Subsurface Energy Applications: A Stratified Analysis of Feature Sets and Model Performance
- 29 July 2025
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 51 (11) , 14115-14135
Tectono-Geomorphic Analysis and Landscape Evolution of Transient Ladhiya River Basin of Uttarakhand Himalaya
- 29 July 2025
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 51 (11) , 14115-14135
Tectono-Geomorphic Analysis and Landscape Evolution of Transient Ladhiya River Basin of Uttarakhand Himalaya
- 13 November 2024
- Published by Springer Nature in Journal of Mountain Science
- Vol. 21 (11) , 3720-3738
Extraction of tectonic imprints using geospatial techniques: Evidence from Mandakini River basin, Uttarakhand, India
- 13 November 2024
- Published by Springer Nature in Journal of Mountain Science
- Vol. 21 (11) , 3720-3738
Extraction of tectonic imprints using geospatial techniques: Evidence from Mandakini River basin, Uttarakhand, India