Towards an automated data cleaning with deep learning in CRESST

Angloher, G.; Banik, S.; Bartolot, D.; Benato, G.; Bento, A.; Bertolini, A.; Breier, R.; Bucci, C.; Burkhart, J.; Canonica, L.; D'Addabbo, A.; Di Lorenzo, S.; Einfalt, L.; Erb, A.; Feilitzsch, F.v.; Ferreiro Iachellini, N.; Fichtinger, S.; Fuchs, D.; Fuss, A.; Garai, A.; Ghete, V.M.; Gerster, S.; Gorla, P.; Guillaumon, P.V.; Gupta, S.; Hauff, D.; Ješkovský, M.; Jochum, J.; Kaznacheeva, M.; Kinast, A.; Kluck, H.; Kraus, H.; Lackner, M.; Langenkämper, A.; Mancuso, M.; Marini, L.; Meyer, L.; Mokina, V.; Nilima, A.; Olmi, M.; Ortmann, T.; Pagliarone, C.; Pattavina, L.; Petricca, F.; Potzel, W.; Povinec, P.; Pröbst, F.; Pucci, F.; Reindl, F.; Rizvanovic, D.; Rothe, J.; Schäffner, K.; Schieck, J.; Schmiedmayer, D.; Schönert, S.; Schwertner, C.; Stahlberg, M.; Stodolsky, L.; Strandhagen, C.; Strauss, R.; Usherov, I.; Wagner, F.; Willers, M.; Zema, V.; Waltenberger, W.

Item

ITEM ACTIONSEXPORT

Add to Basket

Local TagsRelease HistoryDetailsSummary

Released

Journal Article

Towards an automated data cleaning with deep learning in CRESST

MPS-Authors

Angloher, G.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Banik, S.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Bartolot, D.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Benato, G.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Bento, A.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Bertolini, A.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Breier, R.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Bucci, C.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Burkhart, J.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Canonica, L.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

D'Addabbo, A.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Di Lorenzo, S.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Einfalt, L.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Erb, A.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Feilitzsch, F.v.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Ferreiro Iachellini, N.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Fichtinger, S.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Fuchs, D.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Fuss, A.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Garai, A.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Ghete, V.M.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Gerster, S.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Gorla, P.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Guillaumon, P.V.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Gupta, S.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Hauff, D.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Ješkovský, M.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Jochum, J.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Kaznacheeva, M.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Kinast, A.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Kluck, H.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Kraus, H.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Lackner, M.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Langenkämper, A.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Mancuso, M.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Marini, L.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Meyer, L.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Mokina, V.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Nilima, A.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Olmi, M.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Ortmann, T.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Pagliarone, C.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Pattavina, L.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Petricca, F.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Potzel, W.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Povinec, P.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Pröbst, F.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Pucci, F.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Reindl, F.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Rizvanovic, D.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Rothe, J.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Schäffner, K.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Schieck, J.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Schmiedmayer, D.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Schönert, S.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Schwertner, C.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Stahlberg, M.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Stodolsky, L.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Strandhagen, C.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Strauss, R.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Usherov, I.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Wagner, F.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Willers, M.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Zema, V.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

Waltenberger, W.
Max Planck Institute for Physics, Max Planck Society and Cooperation Partners;

External Resource

No external resources are shared

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

Fulltext (public)

There are no public fulltexts stored in PuRe

Supplementary Material (public)

There is no public supplementary material available

Citation

Angloher, G., Banik, S., Bartolot, D., Benato, G., Bento, A., Bertolini, A., et al. (2023). Towards an automated data cleaning with deep learning in CRESST. European Physical Journal Plus, 138, 100. Retrieved from https://publications.mppmu.mpg.de/?action=search&mpi=MPP-2022-325.

Cite as: https://hdl.handle.net/21.11116/0000-000F-1192-8

Abstract

The CRESST experiment employs cryogenic calorimeters for the sensitive measurement of nuclear recoils induced by dark matter particles. The recorded signals need to undergo a careful cleaning process to avoid wrongly reconstructed recoil energies caused by pile-up and read-out artefacts. We frame this process as a time series classification task and propose to automate it with neural networks. With a data set of over one million labeled records from 68 detectors, recorded between 2013 and 2019 by CRESST, we test the capability of four commonly used neural network architectures to learn the data cleaning task. Our best performing model achieves a balanced accuracy of 0.932 on our test set. We show on an exemplary detector that about half of the wrongly predicted events are in fact wrongly labeled events, and a large share of the remaining ones have a context-dependent ground truth. We furthermore evaluate the recall and selectivity of our classifiers with simulated data. The results confirm that the trained classifiers are well suited for the data cleaning task.