Cover Image

Optimal operation of cryogenic calorimeters through deep reinforcement learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Angloher, G., Banik, S., 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., Fichtinger, S., Fuchs, D., Garai, A., Ghete, V. M., Gorla, P., Guillaumon, P. V., Gupta, S., Hauff, D., Ješkovský, M., Jochum, J., Kaznacheeva, M., Kinast, A., Kuckuk, S., Kluck, H., Kraus, H., Langenkämper, A., Mancuso, M., Marini, L., Mauri, B., Meyer, L., Mokina, V., Niedermayer, K., Olmi, M., Ortmann, T., Pagliarone, C., Pattavina, L., Petricca, F., Potzel, W., Povinec, P., Pröbst, F., Pucci, F., Reindl, F., Rothe, J., Schäffner, K., Schieck, J., Schönert, S., Schwertner, C., Stahlberg, M., Stodolsky, L., Strandhagen, C., Strauss, R., Usherov, I., Wagner, F., Wagner, V., Willers, M., Zema, V., Heitzinger, C., Waltenberger, W.
Format:	Preprint
Published:	2023
Subjects:	Instrumentation and Detectors
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866916663690002432
author	Angloher, G. Banik, S. 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. Fichtinger, S. Fuchs, D. Garai, A. Ghete, V. M. Gorla, P. Guillaumon, P. V. Gupta, S. Hauff, D. Ješkovský, M. Jochum, J. Kaznacheeva, M. Kinast, A. Kuckuk, S. Kluck, H. Kraus, H. Langenkämper, A. Mancuso, M. Marini, L. Mauri, B. Meyer, L. Mokina, V. Niedermayer, K. Olmi, M. Ortmann, T. Pagliarone, C. Pattavina, L. Petricca, F. Potzel, W. Povinec, P. Pröbst, F. Pucci, F. Reindl, F. Rothe, J. Schäffner, K. Schieck, J. Schönert, S. Schwertner, C. Stahlberg, M. Stodolsky, L. Strandhagen, C. Strauss, R. Usherov, I. Wagner, F. Wagner, V. Willers, M. Zema, V. Heitzinger, C. Waltenberger, W.
author_facet	Angloher, G. Banik, S. 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. Fichtinger, S. Fuchs, D. Garai, A. Ghete, V. M. Gorla, P. Guillaumon, P. V. Gupta, S. Hauff, D. Ješkovský, M. Jochum, J. Kaznacheeva, M. Kinast, A. Kuckuk, S. Kluck, H. Kraus, H. Langenkämper, A. Mancuso, M. Marini, L. Mauri, B. Meyer, L. Mokina, V. Niedermayer, K. Olmi, M. Ortmann, T. Pagliarone, C. Pattavina, L. Petricca, F. Potzel, W. Povinec, P. Pröbst, F. Pucci, F. Reindl, F. Rothe, J. Schäffner, K. Schieck, J. Schönert, S. Schwertner, C. Stahlberg, M. Stodolsky, L. Strandhagen, C. Strauss, R. Usherov, I. Wagner, F. Wagner, V. Willers, M. Zema, V. Heitzinger, C. Waltenberger, W.
contents	Cryogenic phonon detectors with transition-edge sensors achieve the best sensitivity to light dark matter-nucleus scattering in current direct detection dark matter searches. In such devices, the temperature of the thermometer and the bias current in its readout circuit need careful optimization to achieve optimal detector performance. This task is not trivial and is typically done manually by an expert. In our work, we automated the procedure with reinforcement learning in two settings. First, we trained on a simulation of the response of three CRESST detectors used as a virtual reinforcement learning environment. Second, we trained live on the same detectors operated in the CRESST underground setup. In both cases, we were able to optimize a standard detector as fast and with comparable results as human experts. Our method enables the tuning of large-scale cryogenic detector setups with minimal manual interventions.
format	Preprint
id	arxiv_https___arxiv_org_abs_2311_15147
institution	arXiv
publishDate	2023
record_format	arxiv
spellingShingle	Optimal operation of cryogenic calorimeters through deep reinforcement learning Angloher, G. Banik, S. 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. Fichtinger, S. Fuchs, D. Garai, A. Ghete, V. M. Gorla, P. Guillaumon, P. V. Gupta, S. Hauff, D. Ješkovský, M. Jochum, J. Kaznacheeva, M. Kinast, A. Kuckuk, S. Kluck, H. Kraus, H. Langenkämper, A. Mancuso, M. Marini, L. Mauri, B. Meyer, L. Mokina, V. Niedermayer, K. Olmi, M. Ortmann, T. Pagliarone, C. Pattavina, L. Petricca, F. Potzel, W. Povinec, P. Pröbst, F. Pucci, F. Reindl, F. Rothe, J. Schäffner, K. Schieck, J. Schönert, S. Schwertner, C. Stahlberg, M. Stodolsky, L. Strandhagen, C. Strauss, R. Usherov, I. Wagner, F. Wagner, V. Willers, M. Zema, V. Heitzinger, C. Waltenberger, W. Instrumentation and Detectors Cryogenic phonon detectors with transition-edge sensors achieve the best sensitivity to light dark matter-nucleus scattering in current direct detection dark matter searches. In such devices, the temperature of the thermometer and the bias current in its readout circuit need careful optimization to achieve optimal detector performance. This task is not trivial and is typically done manually by an expert. In our work, we automated the procedure with reinforcement learning in two settings. First, we trained on a simulation of the response of three CRESST detectors used as a virtual reinforcement learning environment. Second, we trained live on the same detectors operated in the CRESST underground setup. In both cases, we were able to optimize a standard detector as fast and with comparable results as human experts. Our method enables the tuning of large-scale cryogenic detector setups with minimal manual interventions.
title	Optimal operation of cryogenic calorimeters through deep reinforcement learning
topic	Instrumentation and Detectors
url	https://arxiv.org/abs/2311.15147