Renjie Wu

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

Bridge Crush! Infrastructure Sensing and Modeling

Students are having fun (also learning) during the CE170A Infrastructure Sensing and Modeling class, taught by Professor Kenichi Soga, Professor Dimitrios Zekkos, Professor Robert Kayen, Dr. Bingyu Zhao, and Renjie Wu as GSI.  Three aluminum model bridges are designed, built and tested for the class. Various sensing technologies are applied during test: Linear Variable Differential Transformer (LVDT) for displacement measurement, Wireless Tilt Meters for tilting… Read More »Bridge Crush! Infrastructure Sensing and Modeling

Technical e-Forum on Machine Learning and Big Data Analysis on Tunneling and Tunnel Mechanics

Our group participated on Technical e-Forum on Machine Learning and Big Data Analysis on Tunneling and Tunnel Mechanics. This forum was held on Thursday, July 1, 2021, by International Soil Mechanics and Geotechnical Engineering (ISSMGE) Technical Committee 309, China Civil Engineering Society – Engineering Risk and Insurance Research Branch, and Tongji University. The forum comprised of 10 talks from 11 speakers: China (mainland 6, Hongkong… Read More »Technical e-Forum on Machine Learning and Big Data Analysis on Tunneling and Tunnel Mechanics

New report on wildfire evacuations for Paradise and Bolinas, CA

A new technical report is recently completed by the Soga Research Group highlighting the socio-technological challenges faced by California communities in wildfire evacuations. In this interdisciplinary effort, a team formed by researchers in wildfire simulations, communication process modeling, and traffic simulations, worked closely with community partners to identify and reconstruct realistic evacuation scenarios for the two case study areas in Bolinas and Paradise, CA. A… Read More »New report on wildfire evacuations for Paradise and Bolinas, CA

SRG researchers take on working platform design using DFOS

A team from the Soga Research Group led by Ph.D. candidate Peter Hubbard is working with a team from Malcolm Drilling led by Peter Faust to assess the performance of working platforms in San Francisco when subject to large loads from drilling rigs using distributed fiber optic sensors (DFOS). A working platform is a layer of material that is placed on top of the existing… Read More »SRG researchers take on working platform design using DFOS

Best Poster Award- Signals in the Soil Workshop

Ruonan Ou’s work “Soil Fracture Generation Monitoring using Distributed Fiber Optic Sensing (DFOS) Technology”  won the Best Poster Award in the Virtual Signals in the Soil (SitS) Workshop hosted by the National Science Foundation (NSF), the USDA-National Institute of Food and Agriculture (NIFA), and the United Kingdom Research and Innovation (UKRI) councils. Congratulations , Ruonan!  Fig.1   Instrumentation of distributed fiber optic sensors in the soil inside a… Read More »Best Poster Award- Signals in the Soil Workshop

PEER Researcher Meeting

Our group presented our work on the annual Pacific Earthquake Engineering Research Center (PEER) researcher meeting.  Renjie Wu & Bingyu Zhao presented their work:  City-scale multi-infrastructure network resilience simulation tool with collaboration of Charles Wang from SimCenter.  Michael Virtucio & Bingyu Zhao presented their work: Performance Based Economic Loss Assessment Due to a Hypothetical Large Southern California Earthquake Based on the Disruption and Recovery of Port… Read More »PEER Researcher Meeting

Long-term health monitoring of levee cutoff wall under Garden Highway in Sacramento by distributed fiber optic sensing (DFOS) technology

USACE (US Army Corps of Engineers) is currently implementing a levee improvement project along the American River in Natomas, California. The main  measure for the levee is a Slag Cement-Cement-Bentonite (SCCB) cutoff wall with an objective to reduce potential for seepage induced distress such as backward erosion piping (BEP) and slope instability. The levee cutoff wall is constructed by a mixture of cement, bentonite and… Read More »Long-term health monitoring of levee cutoff wall under Garden Highway in Sacramento by distributed fiber optic sensing (DFOS) technology

Publication: AI on NATM Tunneling Process

Our group (Renjie Wu and Yuji Fujita) published a paper Integrating domain knowledge with deep learning models: An interpretable AI system for automatic work progress identification of NATM tunnels on Tunnelling and Underground Space Technology.  Abstract:  Finding a reliable and cost-effective approach to monitor the activities of the New Austrian Tunneling Method (NATM) tunnel construction automatically is a challenging yet important task. This study presents… Read More »Publication: AI on NATM Tunneling Process

Workshop: Recent Advances in Tunneling

Our group participated and presented our work on Workshop: Recent Advances in Tunneling (Tongji- SFB837-UCC- ACTUE-UC Berkeley). Renjie Wu and Yuji Fujita present their work: Integrating domain knowledge with deep learning models: An interpretable AI system for automatic work progress identification of NATM tunnels.  See video below for the presentation:  See our paper for details: https://www.sciencedirect.com/science/article/pii/S0886779820305125?via%3Dihub