Capture got fast. Turning what comes back into linework, breaklines, surfaces and classified deliverables did not, and that step is where production capacity actually gets spent.Two talks on closing that gap. The first covers how two engineering firms rebuilt their extraction workflow around machine learning for survey and design deliverables, including how operators stay in control of the output and what it took to scale the approach across project types. The second looks at AI classification for drone lidar, covering ground, vegetation and utility feature detection, and why point density, trajectory accuracy and collection method still determine how well any of it works. Both are clear that automation does not rescue bad data.
This session will include the following presentations:
Reinventing Survey and Design Workflows for Machine Learning
Presented by Russell Hall, Langan Engineering and Environmental Services, Alex Baikovitz, Mach9, and Eddie Fossler, Olsson
Reality capture has improved remarkably. Turning point clouds into linework, breaklines, surfaces, and engineering-ready deliverables remains a key bottleneck and constrains production output. Machine learning is rewiring that production layer: teams at Olsson and Langan are implementing AI-enabled extraction and workflows to scale production and shorten delivery timelines.The session covers requirements, the end-to-end production workflow, and key technical and organizational considerations, along with lessons and guidance for AEC firms delivering survey and topographic projects.
AI Meets Drone Lidar: Faster Classification from Lidar Data
This presentation will focus on how geospatial professionals can use better Lidar data and new AI classification tools to move faster from raw point clouds to clean, usable deliverables.
As Lidar projects continue to get larger and more complex, one of the biggest challenges is still the time it takes to classify, clean up, and prepare point cloud data for final delivery. This session will look at how high-quality data from Lidar systems, combined with AI-assisted processing, can help reduce manual work, improve consistency, and speed up everyday production workflows.
A major part of the presentation will highlight new AI classification tools: AI Ground, AI Ground+, AI Forestry, and AI Utilities. These tools are designed to help users automate some of the most time-consuming parts of point cloud processing, including ground classification, improved ground modeling in tough terrain, vegetation and forestry analysis, and utility feature detection.
The goal is to show practical, real-world workflows, not just talk about AI as a buzzword. We’ll look at how AI classification can support applications such as corridor mapping, site assessment, infrastructure inspection, forestry projects, utility mapping, and survey-ready deliverables.
This presentation will also cover why the quality of the Lidar data still matters. Point density, trajectory accuracy, sensor selection, and collection methods all play a big role in how well classification works. When you start with better data, AI tools can do a better job helping teams create accurate deliverables faster.
