arXiv subjects

Arash Noshadravan

Publications and source records attributed to Arash Noshadravan.

3 recordsLinked to original sources

arXiv2026

Data-Driven Micromechanical Characterization and Mapping of Shale Rocks Using High Speed Nanoindentation

This study investigates the potential of high-speed nanoindentation in collaboration with data analytics and phase volume fractions to achieve micromechanical characterization of heterogeneous rocks. While micromechanical characterization can be performed using mechanical testing alone, integrating chemical analysis-such as elemental mapping techniques-provides essential phase identification. This enables more accurate interpretation of phase-specific mechanical properties. However, incorporating chemical analysis increases the complexity of the process. Hence, this study proposes data-driven micromechanical characterization and mapping of heterogeneous rocks based primarily on mechanical data and limited dependence on chemical analysis. In this study, Mancos shale rock is analyzed using high-speed nanoindentation to determine the mechanical properties at the microscale. Subsequently, a suite of unsupervised statistical learning techniques, such as Uniform Manifold Approximation and Projection (UMAP) with k-means Clustering, Gaussian Mixture Model (GMM), Dirichlet Process Mixture Model (DPMM), and Density-Based Spatial Clustering of Applications with Noise (DBSCAN), are applied to the nanoindentation data. Additionally, an automated image processing and segmentation technique was developed and tested. The results from each technique have been systematically compared against the conventional chemo-mechanical approach using two metrics: weighted error and spatial error. Based on the results, UMAP with k-means clustering is the most appropriate technique, while DBSCAN, DPMM, and image segmentation techniques are more suitable as secondary approaches. This study demonstrates the capability of high-speed nanoindentation combined with machine learning techniques for micromechanical characterization with reduced analytical complexity and improved workflow efficiency.

cond-mat.mtrl-sci↗

arXiv2025

Reactive Transport Simulation of Silicate-Rich Shale Rocks when Exposed to CO2 Saturated Brine Under High Pressure and High Temperature

This study examines the feasibility of carbon dioxide storage in shale rocks and the reliability of reactive transport models in achieving accurate replication of the chemo-mechanical interactions and transport processes transpiring in these rocks when subjected to CO2 saturated brine. Owing to the heterogeneity of rocks, experimental testing for adequate deductions and findings, could be an expensive and time-intensive process. Therefore, this study proposes utilization of reactive transport modeling to replicate the pore-scale chemo-mechanical reactions and transport processes occurring in silicate-rich shale rocks in the presence of CO2 saturated brine under high pressure and high temperature. For this study, Crunch Tope has been adopted to simulate a one-dimensional reactive transport model of a Permian rock specimen exposed to the acidic brine at a temperature of 100 °C and pressure of 12.40 MPa (1800 psi) for a period of 14 and 28 days. The results demonstrated significant dissolution followed by precipitation of quartz rich phases, precipitation and swelling of clay rich phases, and dissolution of feldspar rich phases closer to the acidic brine-rock interface. Moreover, porosity against reaction depth curve showed nearly 1.00% mineral precipitation occur at 14 and 28 days, which is insufficient to completely fill the pore spaces.

physics.geo-ph↗

arXiv2022

Multi-view deep learning for reliable post-disaster damage classification

This study aims to enable more reliable automated post-disaster building damage classification using artificial intelligence (AI) and multi-view imagery. The current practices and research efforts in adopting AI for post-disaster damage assessment are generally (a) qualitative, lacking refined classification of building damage levels based on standard damage scales, and (b) trained based on aerial or satellite imagery with limited views, which, although indicative, are not completely descriptive of the damage scale. To enable more accurate and reliable automated quantification of damage levels, the present study proposes the use of more comprehensive visual data in the form of multiple ground and aerial views of the buildings. To have such a spatially-aware damage prediction model, a Multi-view Convolution Neural Network (MV-CNN) architecture is used that combines the information from different views of a damaged building. This spatial 3D context damage information will result in more accurate identification of damages and reliable quantification of damage levels. The proposed model is trained and validated on reconnaissance visual dataset containing expert-labeled, geotagged images of the inspected buildings following hurricane Harvey. The developed model demonstrates reasonably good accuracy in predicting the damage levels and can be used to support more informed and reliable AI-assisted disaster management practices.

cs.CV↗