Barbara Gertman

Professional Summary

Barbara Gertman is a pioneering geomechanics engineer specializing in underground space utilization through advanced rock-soil mechanics simulations. By integrating computational geotechnics, AI-driven stability analysis, and sustainable subsurface development strategies, Barbara develops predictive models that enable safe and efficient exploitation of urban underground environments—from deep basements and metro tunnels to underground data centers and nuclear waste repositories. Her work bridges the gap between geological complexity and engineering ambition.

Core Innovations & Technical Leadership

1. High-Fidelity Geomechanical Modeling

  • Develops multi-physics simulation frameworks that:

    • Predict time-dependent ground behavior using visco-plastic constitutive models

    • Simulate fracture propagation in jointed rock masses with discrete element methods (DEM)

    • Optimize tunnel boring machine (TBM) performance via real-time soil-abrasion algorithms

2. Risk-Adaptive Underground Planning

  • Designs AI-assisted decision systems for:

    • Settlement forecasting: Neural networks trained on 10,000+ case histories

    • Anomaly detection: Early warning of sinkholes or liquefaction risks

    • Resource mapping: 3D visualization of geotechnical properties using LiDAR and seismic data

3. Sustainable Subsurface Solutions

  • Pioneers green underground technologies including:

    • Thermal-activated retaining walls for geothermal energy harvesting

    • Bio-cemented soils for eco-friendly ground improvement

    • Modular underground structures with carbon-negative materials

Career Milestones

  • Led the geomechanics team for Tokyo's 50-meter-deep "Earthscraper" project, achieving zero settlement incidents

  • Developed the GeoAI Risk Atlas adopted by 15 megacities for underground zoning

  • Patented a self-learning TBM guidance system that reduces excavation delays by 40%

An urban construction site with a large crane and deep excavation. The site is surrounded by buildings and trees, with protective barriers and construction equipment visible.
An urban construction site with a large crane and deep excavation. The site is surrounded by buildings and trees, with protective barriers and construction equipment visible.

TheresearchrequiresGPT-4fine-tuningduetothecomplexityandspecificityof

geotechnicaldata.GPT-4’sadvancedcapabilities,includingitslargerparameterset

andenhancedcontextualunderstanding,areessentialforanalyzingintricate

geomechanicalpatternsandpredictingsoilbehavior.PubliclyavailableGPT-3.5

fine-tuninglackstheprecisionanddepthneededtohandlethenuancedanddynamic

natureofundergroundgeotechnicalchallenges.Fine-tuningGPT-4ensuresthemodelcan

adapttodiversesoilconditions,processlargedatasets,andgenerateactionable

insights,makingitindispensableforthisstudy.

A construction scene near a train platform, featuring workers in orange safety gear operating machinery below a large, reflective grid-like structure.
A construction scene near a train platform, featuring workers in orange safety gear operating machinery below a large, reflective grid-like structure.

Aspartofthesubmission,IrecommendreviewingmypastworkonAIapplicationsin

geotechnicalengineering,particularlymypapertitled“AI-DrivenGeotechnical

Simulation:ACaseStudyofUndergroundStabilityPrediction”.Thisstudyexplored

theuseofAItomodelandpredictsoilbehaviorinundergroundconstruction,focusing

onimprovingsafetyandefficiency.Additionally,myresearchon“EthicalImplications

ofAIinUrbanInfrastructureDevelopment”providesafoundationforunderstanding

thesocietalimpactofAI-drivensolutionsinurbaninnovation.Theseworksdemonstrate

myexpertiseinapplyingAItocomplexgeotechnicalchallengesandhighlightmyability

toconductrigorous,interdisciplinaryresearch.