一种基于梯度提升回归树的系外行星宜居性预测方法

计算机科学 ›› 2019, Vol. 46 ›› Issue (6A): 71-73.

一种基于梯度提升回归树的系外行星宜居性预测方法

朱维军¹, 王鑫¹, 钟英辉², 樊永文¹, 陈永华¹

郑州大学信息工程学院郑州450001¹;
郑州大学物理工程学院郑州450001²

出版日期:2019-06-14 发布日期:2019-07-02
通讯作者: 陈永华(1962-),男,博士,副教授,主要研究方向为DNA计算,E-mail:ieyhchen@zzu.edu.cn(通信作者)。
作者简介:朱维军(1976-),男,博士后,副教授,CCF高级会员,主要研究方向为人工智能及其多学科应用,E-mail:zhuweijun@zzu.edu.cn;王鑫(1997-),男,主要研究方向为人工智能;钟英辉(1987-),女,博士,副教授,主要研究方向为宇宙辐射、毫米波、天体物理;樊永文(1993-),男,硕士生,主要研究方向为人工智能;
基金资助:
本文受国家自然科学基金(U1204608)资助。

Habitability Prediction of Exoplanets Based on GBRT Algorithm

ZHU Wei-jun¹, WANG Xin¹, ZHONG Ying-hui², FAN Yong-wen¹, CHEN Yong-hua¹

School of Information Engineering,Zhengzhou University,Zhengzhou 450001,China¹;
School of Physical Engineering,Zhengzhou University,Zhengzhou 450001,China²

Online:2019-06-14 Published:2019-07-02

摘要/Abstract

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%。

关键词: 二分类, 梯度提升回归树, 系外行星, 宜居性

Abstract: 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 habita-bility.However,the existing ML-based approaches of habitability classification have some serious shortcomings and li-mitations.To this end,this paper provided a novel method for predicting the habitability of exopla-net based on Gra-dient Boosted Regression Trees(GBRT).First,the physical and astronomical data on the potentially habitable exopla-nets 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%.

Key words: Binary classification, Exoplanet, Gradient boosted regression trees, Habitability

中图分类号:

TP181

朱维军, 王鑫, 钟英辉, 樊永文, 陈永华. 一种基于梯度提升回归树的系外行星宜居性预测方法[J]. 计算机科学, 2019, 46(6A): 71-73. https://doi.org/

ZHU Wei-jun, WANG Xin, ZHONG Ying-hui, FAN Yong-wen, CHEN Yong-hua. Habitability Prediction of Exoplanets Based on GBRT Algorithm[J]. Computer Science, 2019, 46(6A): 71-73. https://doi.org/

参考文献

[1]BORA K,SAHA S,AGRAWAL S,et al.CD-HPF:New habitability score via data analytic modeling[J].Astronomy & Computing,2016,17:129-143.
[2]SAHA S,BASAK S,SAFONOVA M,et al.Theoretical validation of potential habitability via analytical and boosted tree methods:An optimistic study on recently discovered exoplanets[J].Astronomy & Computing,2018,23:141-150.
[3]HORA K.Classifying Exoplanets as Potentially Habitable Using Machine Learning[M]∥ICT Based Innovations,2018:203-212.
[4]田丰,胡雄,吴季.系外行星大气与宜居系外行星研究进展及发展趋势[J].空间科学学报,2016,36(6):815-827.
[5]FRIEDMAN J H.Greedy function approximation:a gradient-boosting machine [J].Annal of Statistics,2001(29):1189-1232.
[6]PENG X,SETLUR S,GOVINDARAJU V,et al.Using a boosted tree classifier for text segmentation in hand-annotated documents[J].Pattern Recognition Letters,2008,29(1):943-950.
[7]DEMIRKIR,C,SANKUR B.Face detection using boosted tree classifier stages[C]∥Signal Processing and Communications Applications Conference.IEEE,2004:575-578.
[8]PARAG T,ELGAMMAL A M.Unsupervised Learning of Boosted Tree Classifier Using Graph Cuts for Hand Pose Recognition[C]∥British Machine Vision Conference 2006.Edinburgh,UK,DBLP,2013:1259-1268.
[9]WU B,NEVATIA R.Cluster Boosted Tree Classifier for Multi-View,Multi-Pose Object Detection[C]∥IEEE 11th Internatio-nal Conference on Computer Vision.IEEE,2007:1-8.
[10]DAY M.Emotion recognition with boosted tree classifiers[C]∥ACM on International Conference on Multimodal Interaction.ACM,2013:531-534.
[11]1.11.Ensemble methods —scikit-learn 0.19.1 documentation[EB/OL].http://scikit-learn.org/stable/modules/ensemble.html#gradient-boosting.
[12]Graphlabcreate^TM.Fast,Scalable Machine Learning Modeling in Python [EB/OL].https://turi.com/.
[13]The Habitable Exoplanets Catalog-Planetary Habitability Laboratory @ UPR Arecibo[EB/OL].http://phl.upr.edu/projects/habitable-exoplanets-catalog.
[14]Extrasolar Planet’s Catalogue produced by Kyoto University [EB/OL].www.exoplanetkyoto.org.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed