What question did this study set out to answer?

The study aims to compare classical machine-learning classifiers to rule-based definitions for identifying potentially hazardous near-Earth objects.

February 8, 2026Open Access

Near-Earth Object Risk Scoring Using Classical Machine Learning

Key Points

The study aims to compare classical machine-learning classifiers to rule-based definitions for identifying potentially hazardous near-Earth objects.
Utilized publicly available Near-Earth Object data from NASA CNEOS and JPL Small-Body Database
Implemented classical machine-learning classifiers
Focused on interpretability and reproducibility
Assessed the methodology without making predictions about real-world hazards
Classical machine-learning classifiers were evaluated against the standard rule-based approach
Emphasized the importance of interpretability and reproducibility in analysis
No impact prediction or real-world hazard assessment claims were made

Abstract

This work presents a conservative, methodological study comparing classical machine-learning classifiers with the standard rule-based definition of Potentially Hazardous Objects (PHOs) using publicly available Near-Earth Object data from NASA CNEOS and the JPL Small-Body Database. The study emphasizes interpretability, reproducibility, and limited scope, and does not make claims regarding impact prediction or real-world hazard assessment. This preprint is shared to enable early access while awaiting archival posting.

Near-Earth Object Risk Scoring Using Classical Machine Learning

Key Points

Abstract

Cite This Study