SPOCK 2.0:行星轨道构型稳定性分类器(Stability of Planetary Orbital Configurations Klassifier)中 FeatureClassifier 的更新
SPOCK 2.0: Update to the FeatureClassifier in the Stability of Planetary Orbital Configurations Klassifier
AI总结:
本文通过引入系统特定积分时间尺度作为新特征,并清理原始训练数据集中的重复和误分类样本,改进了 SPOCK 包中 FeatureClassifier 的轨道稳定性预测性能,使其 AUC 提升至 0.950,并发布了新模型与清理后的数据集。
摘要:
行星轨道构型稳定性分类器(SPOCK)包汇集了用于预测紧凑型行星系统稳定性及碰撞演化的机器学习模型。本文探讨了 SPOCK 的二进制稳定性分类器(FeatureClassifier)的改进,该分类器通过对系统的短时 N-body 积分收集数据来预测轨道稳定性。我们发现,通过使用系统特定的时间尺度(而非固定的 $10^4$ 轨道)进行积分,并将该时间尺度作为附加特征,我们将模型的 AUC 指标从 0.943 适度提升至 0.950(完美模型的 AUC=1)。此外,我们发现 SPOCK 原始训练数据集中约 10% 的 N-body 积分被意外重复,且不到 1% 的积分在实际上导致行星被抛射出系统时被错误分类为稳定。我们提供了一个包含 100,000+ 次独特积分的清理后数据集,发布了新训练的稳定性分类模型,并对 API 进行了微调。
英文摘要:
The Stability of Planetary Orbital Configurations Klassifier (SPOCK) package collects machine learning models for predicting the stability and collisional evolution of compact planetary systems. In this paper we explore improvements to SPOCK's binary stability classifier (FeatureClassifier), which predicts orbital stability by collecting data over a short N-body integration of a system. We find that by using a system-specific timescale (rather than a fixed $10^4$ orbits) for the integration, and by using this timescale as an additional feature, we modestly improve the model's AUC metric from 0.943 to 0.950 (AUC=1 for a perfect model). We additionally discovered that $\approx 10\%$ of N-body integrations in SPOCK's original training dataset were duplicated by accident, and that $<1\%$ were misclassified as stable when they in fact led to ejections. We provide a cleaned dataset of 100,000+ unique integrations, release a newly trained stability classification model, and make minor updates to the API.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。