基于机器学习的小样本瞬变源早期分类算法  

An Early Classification Algorithm for Small Sample Transient Source Based on Machine Learning

作　　者：李梦慈 刘承志[1,2,3] 吴潮 康喆 邓诗宇[1,4] 李振伟[1,2] Li Mengci;Liu Chengzhi;Wu Chao;Kang Zhe;Deng Shiyu;Li Zhenwei(Changchun Observatory,National Astronomical Observatories,Chinese Academy of Sciences,Changchun 130117,Jilin,China;University of Chinese Academy of Sciences,Beijing 100049,China;Key Laboratory of Space Object&Debris Observation,Purple Mountain Observatory,Chinese Academy of Sciences,Nanjing 210008,Jiangsu,China;National Astronomical Observatories,Chinese Academy of Sciences,Beijing 100101,China)

机构地区：[1]中国科学院国家天文台长春人造卫星观测站,吉林长春130117 [2]中国科学院大学,北京100049 [3]中国科学院紫金山天文台空间目标与碎片观测重点实验室,江苏南京210008 [4]中国科学院国家天文台,北京100101

出　　处：《光学学报》2024年第24期319-328,共10页Acta Optica Sinica

基　　金：国家自然科学基金(U2031129,U1931133,12273080,12203078);吉林省科技发展计划项目(20210101468JC);吉林省院地合作项目(2023SYHZ0027);长春市市院合作项(23SH04);中国科学院A类战略性先导科技专项。

摘　　要：提出一种基于机器学习的小样本瞬变源早期分类算法TXW,可以在训练样本较少的情况下实时、准确地证认出瞬变源的类别。TXW算法是一种改进的小样本度量学习方法,融合了可提取测光数据特征的时间卷积网络和计算类别概率分数的极限梯度提升树,并结合了新的加权算法,可以解决信号源过早消失所导致的噪声被误判为特征的问题。实验结果表明,与其他5种算法相比,TXW算法针对小样本数据集分类的准确度平均提升了4.33百分点,早期结果的精确率召回率曲线精度平均值提升了0.25,接受者操作特性曲线下方面积的宏平均值提升了0.08。同时,TXW算法在精度、鲁棒性、抗噪性上都有较优表现,可实现小样本瞬变源的早期分类,在证认引力波电磁对应体等稀有瞬变源事件中具有应用价值。Objective Transient sources play a crucial role in studying the origins of the universe and physical phenomena in extreme environments.One of the primary objectives of the SVOM mission is to detect target of opportunity(ToO)events,including electromagnetic counterparts of gravitational waves and other types of transients.Given their Rapid decay,millions of transient events are detected by sensors every night.Hence,a Rapid and accurate classification algorithm is essential for confirming their nature early on.Early classification not only aids in subsequent observational followups but also in studying the physical properties and progenitor systems of transients.Currently,early photometric data of transients often consist of incomplete light curves,which poses a challenge for traditional classification algorithms that typically require complete data sets.Existing early classification algorithms rely heavily on large data sets,which may overlook transients with low occurrence rates or those undetected by current methods.Therefore,developing early classification algorithms tailored for small sample transients is necessary to improve detection efficiency.Methods We propose an early classification algorithm for small sample transient sources based on machine learning:temporal convolutional network(TCN)and eXtreme gradient boosting(XGBoost)combined with a weight module(TXW)algorithm.The algorithm utilizes a small sample metric learning method.Firstly,input data is converted into feature vectors,after which similarity scores for all classes are calculated by the classifier.The transient object is classified as the class with the highest score.The TCN module in the TXW algorithm extracts features from the photometric data of transients,while the XGBoost module calculates probability scores for each candidate class of transient objects.We propose a novel weighting algorithm in the weight module to reduce the noise in timeseries photometric data from transient sources.This addresses issues where signal sources disappear pre

关 键 词：瞬变源 分类 测光 小样本 机器学习 

分 类 号：P129[天文地球—天体测量] TP183[天文地球—天文学]