Exoplanet characterization using conditional invertible neural networks

The characterization of an exoplanet's interior is an inverse problem, which requires statistical methods such as Bayesian inference in order to be solved. Current methods employ Markov Chain Monte Carlo (MCMC) sampling to infer the posterior probability of planetary structure parameters for a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Haldemann, Jonas (VerfasserIn) , Ksoll, Victor F. (VerfasserIn) , Walter, Daniel (VerfasserIn) , Alibert, Yann (VerfasserIn) , Klessen, Ralf S. (VerfasserIn) , Benz, Willy (VerfasserIn) , Köthe, Ullrich (VerfasserIn) , Ardizzone, Lynton (VerfasserIn) , Rother, Carsten (VerfasserIn)
Dokumenttyp: Article (Journal) Kapitel/Artikel
Sprache:Englisch
Veröffentlicht: 31 Jan 2022
In: Arxiv
Year: 2022, Pages: 1-15
Online-Zugang:Verlag, lizenzpflichtig, Volltext: http://arxiv.org/abs/2202.00027
Volltext
Verfasserangaben:Jonas Haldemann, Victor Ksoll, Daniel Walter, Yann Alibert, Ralf S. Klessen, Willy Benz, Ullrich Koethe, Lynton Ardizzone, and Carsten Rother

MARC

LEADER 00000caa a2200000 c 4500
001 1818769484
003 DE-627
005 20230118142735.0
007 cr uuu---uuuuu
008 221012s2022 xx |||||o 00| ||eng c
035 |a (DE-627)1818769484 
035 |a (DE-599)KXP1818769484 
035 |a (OCoLC)1361695772 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 29  |2 sdnb 
100 1 |a Haldemann, Jonas  |e VerfasserIn  |0 (DE-588)1270157841  |0 (DE-627)181885483X  |4 aut 
245 1 0 |a Exoplanet characterization using conditional invertible neural networks  |c Jonas Haldemann, Victor Ksoll, Daniel Walter, Yann Alibert, Ralf S. Klessen, Willy Benz, Ullrich Koethe, Lynton Ardizzone, and Carsten Rother 
264 1 |c 31 Jan 2022 
300 |a 15 
336 |a Text  |b txt  |2 rdacontent 
337 |a Computermedien  |b c  |2 rdamedia 
338 |a Online-Ressource  |b cr  |2 rdacarrier 
500 |a Gesehen am 12.10.2022 
520 |a The characterization of an exoplanet's interior is an inverse problem, which requires statistical methods such as Bayesian inference in order to be solved. Current methods employ Markov Chain Monte Carlo (MCMC) sampling to infer the posterior probability of planetary structure parameters for a given exoplanet. These methods are time consuming since they require the calculation of a large number of planetary structure models. To speed up the inference process when characterizing an exoplanet, we propose to use conditional invertible neural networks (cINNs) to calculate the posterior probability of the internal structure parameters. cINNs are a special type of neural network which excel in solving inverse problems. We constructed a cINN using FrEIA, which was then trained on a database of $5.6\cdot 10^6$ internal structure models to recover the inverse mapping between internal structure parameters and observable features (i.e., planetary mass, planetary radius and composition of the host star). The cINN method was compared to a Metropolis-Hastings MCMC. For that we repeated the characterization of the exoplanet K2-111 b, using both the MCMC method and the trained cINN. We show that the inferred posterior probability of the internal structure parameters from both methods are very similar, with the biggest differences seen in the exoplanet's water content. Thus cINNs are a possible alternative to the standard time-consuming sampling methods. Indeed, using cINNs allows for orders of magnitude faster inference of an exoplanet's composition than what is possible using an MCMC method, however, it still requires the computation of a large database of internal structures to train the cINN. Since this database is only computed once, we found that using a cINN is more efficient than an MCMC, when more than 10 exoplanets are characterized using the same cINN. 
650 4 |a Astrophysics - Earth and Planetary Astrophysics 
650 4 |a Astrophysics - Instrumentation and Methods for Astrophysics 
650 4 |a Computer Science - Machine Learning 
700 1 |a Ksoll, Victor F.  |d 1992-  |e VerfasserIn  |0 (DE-588)1176827448  |0 (DE-627)1048198030  |0 (DE-576)51686372X  |4 aut 
700 1 |a Walter, Daniel  |e VerfasserIn  |0 (DE-588)1270157574  |0 (DE-627)1818854759  |4 aut 
700 1 |a Alibert, Yann  |e VerfasserIn  |4 aut 
700 1 |a Klessen, Ralf S.  |d 1968-  |e VerfasserIn  |0 (DE-588)120533820  |0 (DE-627)392381532  |0 (DE-576)178685399  |4 aut 
700 1 |a Benz, Willy  |e VerfasserIn  |4 aut 
700 1 |a Köthe, Ullrich  |e VerfasserIn  |0 (DE-588)123963435  |0 (DE-627)594480884  |0 (DE-576)304484520  |4 aut 
700 1 |a Ardizzone, Lynton  |d 1994-  |e VerfasserIn  |0 (DE-588)1194988512  |0 (DE-627)1677182296  |4 aut 
700 1 |a Rother, Carsten  |e VerfasserIn  |0 (DE-588)1181464692  |0 (DE-627)1662676883  |4 aut 
773 0 8 |i Enthalten in  |t Arxiv  |d Ithaca, NY : Cornell University, 1991  |g (2022), Artikel-ID 2202.00027, Seite 1-15  |h Online-Ressource  |w (DE-627)509006531  |w (DE-600)2225896-6  |w (DE-576)28130436X  |7 nnas  |a Exoplanet characterization using conditional invertible neural networks 
773 1 8 |g year:2022  |g elocationid:2202.00027  |g pages:1-15  |g extent:15  |a Exoplanet characterization using conditional invertible neural networks 
856 4 0 |u http://arxiv.org/abs/2202.00027  |x Verlag  |z lizenzpflichtig  |3 Volltext 
951 |a AR 
992 |a 20221012 
993 |a Article 
994 |a 2022 
998 |g 1181464692  |a Rother, Carsten  |m 1181464692:Rother, Carsten  |d 700000  |d 708070  |d 700000  |d 728500  |e 700000PR1181464692  |e 708070PR1181464692  |e 700000PR1181464692  |e 728500PR1181464692  |k 0/700000/  |k 1/700000/708070/  |k 0/700000/  |k 1/700000/728500/  |p 9  |y j 
998 |g 1194988512  |a Ardizzone, Lynton  |m 1194988512:Ardizzone, Lynton  |d 110000  |d 700000  |d 728500  |e 110000PA1194988512  |e 700000PA1194988512  |e 728500PA1194988512  |k 0/110000/  |k 0/700000/  |k 1/700000/728500/  |p 8 
998 |g 123963435  |a Köthe, Ullrich  |m 123963435:Köthe, Ullrich  |d 700000  |d 708070  |d 700000  |d 728500  |e 700000PK123963435  |e 708070PK123963435  |e 700000PK123963435  |e 728500PK123963435  |k 0/700000/  |k 1/700000/708070/  |k 0/700000/  |k 1/700000/728500/  |p 7 
998 |g 120533820  |a Klessen, Ralf S.  |m 120533820:Klessen, Ralf S.  |d 700000  |d 714000  |d 714200  |d 700000  |d 728500  |e 700000PK120533820  |e 714000PK120533820  |e 714200PK120533820  |e 700000PK120533820  |e 728500PK120533820  |k 0/700000/  |k 1/700000/714000/  |k 2/700000/714000/714200/  |k 0/700000/  |k 1/700000/728500/  |p 5 
998 |g 1270157574  |a Walter, Daniel  |m 1270157574:Walter, Daniel  |p 3 
998 |g 1176827448  |a Ksoll, Victor F.  |m 1176827448:Ksoll, Victor F.  |d 700000  |d 714000  |d 714200  |d 700000  |d 728500  |e 700000PK1176827448  |e 714000PK1176827448  |e 714200PK1176827448  |e 700000PK1176827448  |e 728500PK1176827448  |k 0/700000/  |k 1/700000/714000/  |k 2/700000/714000/714200/  |k 0/700000/  |k 1/700000/728500/  |p 2 
999 |a KXP-PPN1818769484  |e 4196402186 
BIB |a Y 
JSO |a {"name":{"displayForm":["Jonas Haldemann, Victor Ksoll, Daniel Walter, Yann Alibert, Ralf S. Klessen, Willy Benz, Ullrich Koethe, Lynton Ardizzone, and Carsten Rother"]},"language":["eng"],"person":[{"family":"Haldemann","role":"aut","given":"Jonas","display":"Haldemann, Jonas"},{"family":"Ksoll","role":"aut","display":"Ksoll, Victor F.","given":"Victor F."},{"given":"Daniel","display":"Walter, Daniel","family":"Walter","role":"aut"},{"display":"Alibert, Yann","given":"Yann","role":"aut","family":"Alibert"},{"given":"Ralf S.","display":"Klessen, Ralf S.","family":"Klessen","role":"aut"},{"family":"Benz","role":"aut","given":"Willy","display":"Benz, Willy"},{"role":"aut","family":"Köthe","display":"Köthe, Ullrich","given":"Ullrich"},{"family":"Ardizzone","role":"aut","given":"Lynton","display":"Ardizzone, Lynton"},{"role":"aut","family":"Rother","given":"Carsten","display":"Rother, Carsten"}],"recId":"1818769484","note":["Gesehen am 12.10.2022"],"title":[{"title_sort":"Exoplanet characterization using conditional invertible neural networks","title":"Exoplanet characterization using conditional invertible neural networks"}],"type":{"bibl":"chapter","media":"Online-Ressource"},"physDesc":[{"extent":"15 S."}],"id":{"eki":["1818769484"]},"relHost":[{"recId":"509006531","origin":[{"dateIssuedKey":"1991","publisherPlace":"Ithaca, NY ; [Erscheinungsort nicht ermittelbar]","publisher":"Cornell University ; Arxiv.org","dateIssuedDisp":"1991-"}],"physDesc":[{"extent":"Online-Ressource"}],"id":{"eki":["509006531"],"zdb":["2225896-6"]},"title":[{"title":"Arxiv","title_sort":"Arxiv"}],"note":["Gesehen am 28.05.2024"],"pubHistory":["1991 -"],"part":{"pages":"1-15","extent":"15","text":"(2022), Artikel-ID 2202.00027, Seite 1-15","year":"2022"},"language":["eng"],"titleAlt":[{"title":"Arxiv.org"},{"title":"Arxiv.org e-print archive"},{"title":"Arxiv e-print archive"},{"title":"De.arxiv.org"}],"disp":"Exoplanet characterization using conditional invertible neural networksArxiv","type":{"bibl":"edited-book","media":"Online-Ressource"}}],"origin":[{"dateIssuedDisp":"31 Jan 2022","dateIssuedKey":"2022"}]} 
SRT |a HALDEMANNJEXOPLANETC3120