In the realm of geotechnical engineering, the integration of data-driven approaches with downhole geophysical logs marks a significant leap forward in subsurface analysis. This innovative methodology harnesses the power of advanced analytics and machine learning to predict geotechnical properties with reliability and efficiency. By interpreting high-resolution geophysical log data, we can gain a deeper understanding of subsurface conditions, leading to more informed decision-making in resource extraction and infrastructure development. This approach not only enhances the precision of geotechnical assessments but also optimises project safety, reduces costs, and supports sustainable engineering practices. As we continue to explore the potential of data-driven geotechnical property prediction, we pave the way for a future where technology and engineering converge to achieve unparalleled insights and advancements in the field.
School
Minerals and Energy Resources Engineering
Research Area
Artificial intelligence | Machine learning | Geotechnics | Downhole geophysical logging | Rock mechanics | Mining | Petroleum
- Research environment
- Expected outcomes
- Supervisory team
- Reference material/links
- Our team consists of experts in geotechnical engineering, subsurface engineering and AI providing a unique environment for growth in subsurface data analytics.
The adoption of data-driven geotechnical property prediction using downhole geophysical logs is expected to yield several key outcomes including more reliable and cost-effective geotechnical investigations. This approach will also improve project safety by mitigating risks, support sustainable engineering practices, and drive innovation in geotechnical methodologies. Ultimately, this integration of advanced data analytics will empower more informed decision-making, and optimising resource management.
- A novel workflow based on physics-informed machine learning to determine the permeability profile of fractured coal seams using downhole geophysical logs
- Effect of spatial variability of downhole geophysical logs on machine learning exercises
- Classification of Rock Joint Profiles Using an Artificial Neural Network-Based Computer Vision Technique
- Machine learning assisted Kriging to capture spatial variability in petrophysical property modelling