Technology Category
Machine Learning: Multi-class/Multi-label Learning & Extreme ClassificationSearch and Optimization: Mixed Discrete/Continuous SearchNatural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
Improving the discovery of near-Earth objects with machine-learning methods.
🤖 AI Summary
Approximately 50% of candidates in the NASA Near-Earth Object Confirmation Page (NEOCP) are non-near-Earth objects (non-NEOs), leading to significant waste of observational resources.
Method: We propose a hybrid filtering framework integrating digest2 parameter optimization with machine learning. First, we systematically analyze the distribution patterns of 30 digest2 parameters and construct an interpretable parameter filter. Then, we innovatively combine traditional threshold-based screening with ensemble classifiers—including gradient boosting machines and random forests—for high-accuracy initial candidate classification.
Contribution/Results: Our method reduces the non-NEO fraction in NEOCP by over 80%, incurs only a 5.5% loss of true NEO orbital arcs, and achieves a net loss of ~1% and a classification accuracy of 95%. The framework substantially improves NEOCP purity and confirmation efficiency, delivering a reusable, interpretable, and automated solution for efficient target selection in time-domain surveys.
Technology Category
Application Category
📝 Abstract
We present a comprehensive analysis of the digest2 parameters for candidates of the Near-Earth Object Confirmation Page (NEOCP) that were reported between 2019 and 2024. Our study proposes methods for significantly reducing the inclusion of non-NEO objects on the NEOCP. Despite the substantial increase in near-Earth object (NEO) discoveries in recent years, only about half of the NEOCP candidates are ultimately confirmed as NEOs. Therefore, much observing time is spent following up on non-NEOs. Furthermore, approximately 11% of the candidates remain unconfirmed because the follow-up observations are insufficient. These are nearly 600 cases per year. To reduce false positives and minimize wasted resources on non-NEOs, we refine the posting criteria for NEOCP based on a detailed analysis of all digest2 scores. We investigated 30 distinct digest2 parameter categories for candidates that were confirmed as NEOs and non-NEOs. From this analysis, we derived a filtering mechanism based on selected digest2 parameters that were able to exclude 20% of the non-NEOs from the NEOCP while maintaining a minimal loss of true NEOs. We also investigated the application of four machine-learning (ML) techniques, that is, the gradient-boosting machine (GBM), the random forest (RF) classifier, the stochastic gradient descent (SGD) classifier, and neural networks (NN) to classify NEOCP candidates as NEOs or non-NEOs. Based on digest2 parameters as input, our ML models achieved a precision of approximately 95% in distinguishing between NEOs and non-NEOs. Combining the digest2 parameter filter with an ML-based classification model, we demonstrate a significant reduction in non-NEOs on the NEOCP that exceeds 80%, while limiting the loss of NEO discovery tracklets to 5.5%. Importantly, we show that most follow-up tracklets of initially misclassified NEOs are later correctly identified as NEOs. This effectively reduces the net loss of true NEOs to approximately 1%. A greater purity of NEO candidates on the NEOCP would allow follow-up observers to allocate more resources to confirming high-priority objects. This would improve the overall observational efficiency and the confirmation rate of NEO discoveries. We suggest that our methods are used as part of the NEOCP pipeline.
Problem
Research questions and friction points this paper is trying to address.
Reducing false positives in near-Earth object detection
Minimizing wasted resources on non-NEO follow-ups
Improving NEO classification accuracy with machine learning
Innovation
Methods, ideas, or system contributions that make the work stand out.
Machine-learning models classify NEOs with 95% precision
Digest2 parameter filter excludes 20% of non-NEO candidates
Combined approach reduces non-NEOs by over 80%
🔎 Similar Papers
No similar papers found.
