Current Research Students
-
Danrong Zhang, Ph.D. Candidate, CSE, Georgia Tech
-
Jiaojun Liu, Ph.D. Candidate, CEE, Georgia Tech
-
Karie Yamamoto, Ph.D. Candidate, CEE, Georgia Tech
Research Areas
Characterizing the Pore Space Architecture of Particulate Materials
The location and geometry of elements inside the 3D pore space of particulate material microstructure holds physical significance in various engineering applications. For example, flow and deformation analysis in materials, tissue repair, petroleum extraction, subsurface modifications in soil, mechanics of porous metals, and so on.
I work on developing robust and operator-independent algorithms to segment the continuous 3D pore space of particulate microstructures into an interconnected network of bulky pore bodies and narrow pore throats based on the overall geometry.
After the discretization, various properties of pore space features can be quantified and applied to the study of the performance and behavior of materials under external loading conditions.
More information about this research can found in this article.
Physics Informed Deep learning workflow for Rapid and Comprehensive Characterization of Geomaterials
The rapid accumulation of data and dramatic advances in computational techniques are transforming how engineering problems are being solved. The accurate and precise computation of complex microstructural properties is computationally expensive since it requires a high-resolution input. Conversely, to obtain properties of materials at field-scale, systems comprising 10’s of millions of particles are required to fully capture the multi-scale variability of the strata.
In this light, I work on developing deep learning techniques based workflow to predict a myriad of microstructural properties of 3D images, ranging from properties of individual microstructural elements like pore bodies, throats, particles, and contacts, to collective properties like tortuosity, connectivity, and orientation anisotropy of elements
Micro-to-Macro Analysis of Shear-Induced Deformation of Granular Materials
The macroscopic behavior of granular materials stem from a heterogeneous interplay of microstructural responses and is influenced by micro-mechanical descriptions of particles, their interconnected network of contacts, and associated pore bodies and throats.
This work explores the role of micro-mechanical properties in providing insights into the deformation characteristics of sheared granular sands from the perspective of pore space, which has been overlooked for a long time as compared to particle and contact measurements.
More information about this research can found in this article.
Analyzing the complex micromechanics of bio-cemented soils
Bio-cementation improves the mechanical behavior of the subsurface by integrating bacterial metabolic activity in soil structure to induce the formation of calcite. The spatial location and distribution of the calcite bonds have a huge effect on the macroscopic improvement in the behavior of the cemented material.
​
This work explores the role of 3D micro-mechanical characterizations of cemented soil microstructures to gain insights into the factors affecting improvement in macro response to learning ways to engineer the treatment methods for better results.
Some details about the ongoing work on this topic can be found here.
Artificial Intelligence based natural disasters-induced damage assessment and prediction
Real-time damage assessment after a natural disaster event is critical to efficient disaster reconnaissance activities, that otherwise rely on cumbersome and time-consuming field surveys. This work relies on AI techniques applied to surrogate data from satellites and other sources that can correlate to disaster-induced damage. With sufficient multi-sourced data available, early identification of disaster-prone regions can be attempted.
Geospatial and site characterization data describing subsurface conditions of a disaster-struck region can be collected from post-disaster studies, governmental bodies, emergency responders, loss adjusters, and social media channels.