Key Takeaways

  • Photogrammetric structural mapping extracts discontinuity orientation, spacing and trace length from pit-wall imagery. It is the established standard, via Maptek’s I-Site Studio/PointStudio and the CSIRO-developed Sirovision system.
  • Automated discontinuity-detection algorithms are increasingly built into these platforms, reducing manual digitizing of joint sets from point clouds.
  • This is a commercial, deployed capability. The AI and automation layer is still emerging on top of an already mature photogrammetry foundation.

TL;DR

AI-assisted structural mapping starts with a pit-wall point cloud from a laser scan or drone photogrammetry, built in Maptek PointStudio or CSIRO’s Sirovision. Automated discontinuity-detection algorithms then extract joint orientation, spacing and trace length. An engineer reviews the candidate joint sets instead of hand-digitizing every structure.

What Is Structural Mapping?

Joints, faults, bedding and other discontinuities cut through every rock mass. These planes of weakness control how a pit wall or underground opening behaves. Structural mapping records their orientation, spacing and persistence across an exposed face.

Traditionally, geologists mapped structures with a tape and compass along a scanline. That is slow, and it puts people close to steep, unstable walls. However, the data is essential. Engineers group discontinuities into joint sets and plot them on stereonets. They then test whether blocks could slide or topple out of the wall.

How Do I Apply AI to Structural Mapping?

Photogrammetry has transformed this work over the last decade, and it is the foundation any AI layer sits on. The workflow has three stages.

Capturing the wall as a point cloud

Maptek’s PointStudio (formerly I-Site Studio) turns terrestrial laser scans and drone photogrammetry into point clouds. It then provides geotechnical tools for plane fitting, discontinuity set analysis and slope evaluation directly from that data. You no longer need a manual tape-and-compass scanline survey. The same capture methods overlap with drone survey and 3D terrain modelling.

Using Sirovision for bench-scale mapping

Consultancies like SRK widely deploy CSIRO’s Sirovision system. It does the equivalent for bench-scale kinematic analysis. It captures 3D location, orientation, trace length and fracture spacing from stereo photogrammetric pairs. As a result, a team can map a whole bench face from a safe distance.

Automating structural mapping with detection algorithms

The emerging piece is automated discontinuity detection. Traditionally, a geotechnical engineer manually clicks and fits planes to visible joint traces in the point cloud. Newer algorithms increasingly automate that extraction. They flag candidate discontinuity sets for review instead of requiring fully manual digitizing. For spacing specifically, see fracture spacing AI.

What to Expect From AI Structural Mapping

This is a genuine productivity gain layered on mature photogrammetric hardware and software. You are not waiting for the core technology to mature. Instead, you adopt the automation features as they roll out in tool updates.

Expect to review the output. Automated detection can miss joints parallel to the camera view, or split one structure into several planes. Therefore, keep an engineer in the loop to accept, merge or reject candidate sets. The mapped joint sets then feed bench slope design, where they drive the kinematic checks on each wall.

FAQs

What is structural mapping in mining?

Structural mapping records the orientation, spacing and persistence of joints, faults and other discontinuities in exposed rock. Geotechnical engineers use it to understand how the rock mass may fail. It is a core input to slope and excavation design.

How does AI help structural mapping?

AI and automated algorithms detect discontinuities in point clouds and fit planes to them automatically. They group results into candidate joint sets for an engineer to review. As a result, mapping a wall takes far less manual digitizing.

What software is used for photogrammetric mapping?

Maptek PointStudio (formerly I-Site Studio) and CSIRO’s Sirovision are the established tools. Both build 3D models from laser scans or photographs and measure discontinuities from them. Automated detection features increasingly ship with these platforms.

Is automated joint detection reliable?

It is reliable as a first pass, not as a final answer. The photogrammetry itself is mature, but automated detection still needs human review. Engineers should check joint sets against field observations and drillhole data.

Try It With Geocluster

Connecting mapped structures to your block model and slope-design inputs means a newly mapped joint set can update downstream geotechnical models. That integration work is what Geocluster is built to support. Read how the Geocluster Research Harness works to see where it fits.