多任务学习(Multi-task Learning,MTL)就是把多个问题一起进行分析、计算,以发掘不同问题之间的相关性,提高分析结果的精度,该类方法已被广泛地应用于机器学习、模式识别、计算机视觉等领域.使用多任务学习方案研究了恒星大气物理参数中表面温度(Teff)、表面重力加速度(lgg)、化学丰度([Fe/H])的估计问题.首先使用多任务Sparse Group Lasso算法提取对3个大气物理参数均有预测能力的光谱特征;然后使用支持向量机估计恒星大气物理参数.该方案在Sloan实测恒星光谱和理论光谱上均做了测试.在实测光谱上的平均绝对误差分别为:0.0064(lg(Teff/K)),0.1622(Ig(9/(cm·S^-2))),0.1221dex([Fe/H]).在由Kurucz的New Opacity Distribution Function(NEWODF)模型得到的理论光谱上也做了同样的特征提取和恒星大气物理参数估计测试,相应的平均绝对误差分别为:0.0006(lg(Teff/K))),0.0098(lg(g/(cm·S^-2))),0.0082dex([Fe/H]).通过与文献中的同类研究比较表明,多任务Sparse Group Lasso特征提取与支持向量机回归(support vector machine regression,SVR)两者结合的方案有较高的恒星大气物理参量估计精度.
The multi-task learning puts the multiple tasks together to analyse and calculate for discovering the correlation between them, which can improve the accuracy of analysis results. This kind of methods have been widely studied in machine learning, pattern recognition, computer vision, and other related fields. This paper investigates the application of multi-task learning in estimating the effective temperature (TEN), surface gravity (lg g), and chemical abundance ([Fe/H]). Firstly, the spectral characteristics of the three atmospheric physical parameters are extracted by using the multi-task Sparse Group Lasso algorithm, and then the support vector machine is used to estimate the atmospheric physical parameters. The proposed scheme is evaluated on both Sloan stellar spectra and theoretical spectra computed from Kurucz's New Opacity Distribution Function (NEWODF) model. The mean absolute errors (MAEs) on the Sloan spectra are: 0.0064 for lg (Teff/K), 0.1622 for lg (g/(cm· s^-2)), and 0.1221 dex for [Fe/H]; The MAEs on synthetic spectra are 0.0006 for lg (Teff/K), 0.0098 for lg (g/(cm·s^-2)), and 0.0082 dex for [Fe/H]. Experimental results show that the proposed scheme is excellent for atmospheric parameter estimation.