Interpretability of deep-learning methods applied to large-scale structure surveys
Lade...
Dateien
Autor:innen
Autor:in (Körperschaft)
Publikationsdatum
2026
Typ der Arbeit
Studiengang
Sammlung
Typ
01A - Beitrag in wissenschaftlicher Zeitschrift
Herausgeber:innen
Herausgeber:in (Körperschaft)
Betreuer:in
Übergeordnetes Werk
Astronomy & Astrophysics
Themenheft
DOI der Originalpublikation
Link
Zugehörige Forschungsdaten
Reihe / Serie
Reihennummer
Jahrgang / Band
709
Ausgabe / Nummer
Seiten / Dauer
A78
Patentnummer
Verlag / Herausgebende Institution
EDP Sciences
Verlagsort / Veranstaltungsort
Auflage
Version
Programmiersprache
Abtretungsempfänger:in
Praxispartner:in/Auftraggeber:in
Zusammenfassung
Deep learning and convolutional neural networks in particular are powerful and promising tools for cosmological analysis of large-scale structure surveys. They already provide similar performance levels to classical analysis methods using fixed summary statistics and show potential to break key degeneracies through better probe combinations. They will also likely improve rapidly in the coming years as progress is made in terms of physical modelling through both software and hardware improvement. One key issue remains: unlike classical analysis, a convolutional neural network’s inference process is hidden from the user as the network optimises millions of parameters with no interpretable physical meaning. This prevents a clear understanding of the potential limitations and biases of the analysis, making it hard to rely on as a main analysis method. In this work, we explored the behaviour of such a convolutional neural network through a novel method. Instead of trying to analyse a network a posteriori, i.e. after training has been completed, we studied the impact on the constraining power of training the network and predicting parameters with degraded data, where we removed part of the information. This allowed us to gain an understanding of which parts and features of tomographic, weak gravitational lensing maps are most important in the network’s inference process. For Stage-III-like noise levels, we find that the network’s inference process relies on a mix of both Gaussian and non-Gaussian information, and it seems to put an emphasis on structures whose scales are at the limit between linear and non-linear regimes. When studying a noiseless survey, we find that the relative importance of small scales increases, indicating that they hold relevant cosmological information that is inaccessible when including realistic levels of shape noise.
Schlagwörter
Fachgebiet (DDC)
Veranstaltung
Startdatum der Ausstellung
Enddatum der Ausstellung
Startdatum der Konferenz
Enddatum der Konferenz
Datum der letzten Prüfung
ISBN
ISSN
1432-0746
0004-6361
0004-6361
Sprache
Englisch
Während FHNW Zugehörigkeit erstellt
Ja
Zukunftsfelder FHNW
Publikationsstatus
Veröffentlicht
Begutachtung
peer-reviewed
Open Access-Status
Gold
Lizenz
Zitation
Aymerich, G., Kacprzak, T., Refregier, A., & Thomsen, A. (2026). Interpretability of deep-learning methods applied to large-scale structure surveys. Astronomy & Astrophysics, 709, A78. https://doi.org/10.1051/0004-6361/202553963