Back to feed
arXiv cs.LG
arXiv cs.LG
7/17/2026
Explainable Geospatial AI for Satellite Ground Station Siting Using LiDAR-Derived Terrain Intelligence

Explainable Geospatial AI for Satellite Ground Station Siting Using LiDAR-Derived Terrain Intelligence

Short summary

This paper presents an interpretable ML framework for predicting representative clutter height (RCH) from open geospatial data, trained on LiDAR-derived labels from the USGS 3D Elevation Program. The LightGBM model achieves 1.79m MAE and R²=0.765, reducing error by over 60% versus the ITU baseline. SHAP analysis confirms physical plausibility, identifying tree canopy cover, land-cover semantics, and spectral reflectance as top predictors.

  • •LightGBM model predicts clutter height with 60% lower error than ITU baseline
  • •Trained on LiDAR labels from USGS 3D Elevation Program with global remote sensing features
  • •SHAP analysis validates physical plausibility of influential predictors

Generated with AI, which can make mistakes.

#research-breakthrough#ai-tools#industry-adoption
Read full article at arXiv cs.LG

Is this a good recommendation for you?

Comments

Failed to load comments. Please try again.

Explore more

LunarSite: An end-to-end ML pipeline for lunar south pole landing site selection
Dev.to
Topology-Informed Neural Networks for Flood Detection in Optical and Synthetic Aperture Radar Imagery
arXiv cs.LG
Built Environment Reasoning from Remote Sensing Imagery Using Large Vision--Language Models
arXiv cs.CL
From ML Predictions to Informed Diagnostic Assistance Using the Toulmin Model of Argumentation
arXiv CS.AI