一种基于梯度提升回归树的系外行星宜居性预测方法  

Habitability Prediction of Exoplanets Based on GBRT Algorithm

作　　者：朱维军[1] 王鑫 钟英辉[2] 樊永文 陈永华[1] ZHU Wei-jun;WANG Xin;ZHONG Ying-hui;FAN Yong-wen;CHEN Yong-hua(School of Information Engineering,Zhengzhou University,Zhengzhou 450001,China;School of Physical Engineering,Zhengzhou University,Zhengzhou 450001,China)

机构地区：[1]郑州大学信息工程学院,郑州450001 [2]郑州大学物理工程学院,郑州450001

出　　处：《计算机科学》2019年第B06期71-73,79,共4页Computer Science

基　　金：国家自然科学基金(U1204608)资助

摘　　要：系外行星的宜居性是近年来探索宇宙的一个热点研究课题,机器学习为系外行星宜居性分类提供了一种可行的手段。然而,现有的宜居性分类效果面临严重不足与局限。为此,给出一种基于梯度提升回归树的系外行星宜居性分类预测方法。首先,使用梯度提升回归树算法对系外潜在宜居行星与非宜居行星的相关物理学与天文学数据集进行训练;然后,利用训练好的模型对相关测试集进行预测。仿真实验结果表明,新方法在测试集上的预测准确率高达100%。The habitability of exoplanets is a hot research topic in the field of the exploration of the universe in recent years.The Machine Learning(ML)technique provides a viable means for classifying exoplanets according to their habitability.However,the existing ML-based approaches of habitability classification have some serious shortcomings and limitations.To this end,this paper provided a novel method for predicting the habitability of exoplanet based on Gradient Boosted Regression Trees(GBRT).First,the physical and astronomical data on the potentially habitable exoplanets and the inhabitable ones are employed to train by algorithm GBRT.Then,the trained model is used to predict the habitability of the exoplanets in our test set.The simulated experimental results show that the predictive accuracy of the new method is as high as 100%.

关 键 词：梯度提升回归树 系外行星 宜居性 二分类 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] P144[自动化与计算机技术—控制科学与工程]