The Soga Research Group carries out research in the field of geotechnical and infrastructure engineering. We are interested in developing new monitoring technologies, which allow gaining insight into the behavior of infrastructure, detecting anomalies, and providing data for performance analyses. On top of that, we are also conducting research on city-scale modeling and simulations to evaluate the value of sensing for better management of infrastructure during operation as well as for better response during and after natural disasters such as earthquakes and wildfires. Our research groups are divided into four sub-categories as follows.

City-scale Modeling

In the city-scale modeling group, we develop scientific simulation models to capture the behaviors of infrastructures and integrate them into a “system of systems” model to obtain insights. Please click on the images below to learn more about ongoing works Wildfire Pipeline Earthquake Traffic System of Systems

Computational Geomechanics

The group conducts research in the field of computational geomechanics utilizing a variety of methods that include the Material point method (MPM), Finite element method (FEM), and Lattice element method (LEM). The group applies these methods to both research and consulting applications which include, but are not limited to landslides, slope failures, tunneling, soil-pipeline interactions, geothermal energy, and deep borehole drilling. Please click on the… Read More »Computational Geomechanics

Shallow Geothermal Energy

Shallow geothermal energy is an emerging renewable green energy that can provide heating and cooling for buildings in a safe, non-emitting, and affordable way thus reducing the dependence on natural gas. Soga research group is exploring the potential of shallow geothermal energy through in-situ geothermal investigation, city-scale geothermal simulation and optimization, and development of advanced energy delivery system.  Geothermal Investigation at Berkeley Campus Geothermal Energy… Read More »Shallow Geothermal Energy

Machine Learning for Construction and Infrastructure

The group conducts research on utilizing and developing data analytics techniques to better understand and solve complex problems in underground construction and infrastructure. Please click on the images below to learn more about ongoing works Automated NATM work progress identification Measuring tunnel lining deformation with computer vision techniques Modeling EPBM excavation processes using Bayesian Networks   Prediction and control of TBM trajectory Supervised and unsupervised… Read More »Machine Learning for Construction and Infrastructure

Sensing Technology

The sensor technologies and methodologies are developed to transform the future of infrastructure and geomechanics through smart information. The data gathered permits an assessment of the behavior of the infrastructure in its environment and allows performance analyses. The group develops, tests, and delivers new robust, resilient, and adaptable technologies, such as distributed fiber optic sensors (DFOS), wireless sensor network (WSN), energy harvesting, and computer vision. … Read More »Sensing Technology