<aside>

Pipeline overview:

1. Install deps — pip install --user laspy csf (sklearn + numpy already available)
2. Download the 13 .las files from rclone into /scratch/jw8868/lidar_tmp/
3. Merge all files into one combined point cloud with laspy
4. Z-axis cleanup — estimate ground plane using a grid-based percentile approach, then remove points >1m above or below it
5. CSF filter — classify ground vs off-ground, discard off-ground points
6. K-means clustering — run sklearn KMeans on the remaining ground points (K=5)
7. Save output — write the final clustered LAS file to /scratch/jw8868/ (or home) </aside>