This study addresses a challenge of parametrizing a resolution function of a neutron beam from the neutron time of flight facility n_TOF at CERN.A difficulty stems from a fact that a resolution function exhibits rathe...This study addresses a challenge of parametrizing a resolution function of a neutron beam from the neutron time of flight facility n_TOF at CERN.A difficulty stems from a fact that a resolution function exhibits rather strong variations in shape,over approximately ten orders of magnitude in neutron energy.To avoid a need for a manual identification of the appropri-ate analytical forms-hindering past attempts at its parametrization-we take advantage of the versatile machine learning techniques.Specifically,we parametrized it by training a multilayer feedforward neural network,relying on a key idea that such network acts as a universal approximator.The proof-of-concept is presented for a resolution function for the first experimental area of the n_TOF facility from the third phase of its operation.We propose an optimal network structure for a resolution function in question,which is also expected to be optimal or near-optimal for other experimental areas and for different phases of n_TOF operation.To reconstruct several resolution function forms in common use from a single para-metrized form,we provide a practical tool in the form of a specialized C++class encapsulating the computationally efficient procedures suited to the task.展开更多
基金supported by the Croatian Science Foundation under the project number HRZZ-IP-2022-10-3878funding from the European Union’s Horizon Europe Research and Innovation programme under Grant Agreement No 101057511Funding Open access funding provided by CERN (European Organization for Nuclear Research).
文摘This study addresses a challenge of parametrizing a resolution function of a neutron beam from the neutron time of flight facility n_TOF at CERN.A difficulty stems from a fact that a resolution function exhibits rather strong variations in shape,over approximately ten orders of magnitude in neutron energy.To avoid a need for a manual identification of the appropri-ate analytical forms-hindering past attempts at its parametrization-we take advantage of the versatile machine learning techniques.Specifically,we parametrized it by training a multilayer feedforward neural network,relying on a key idea that such network acts as a universal approximator.The proof-of-concept is presented for a resolution function for the first experimental area of the n_TOF facility from the third phase of its operation.We propose an optimal network structure for a resolution function in question,which is also expected to be optimal or near-optimal for other experimental areas and for different phases of n_TOF operation.To reconstruct several resolution function forms in common use from a single para-metrized form,we provide a practical tool in the form of a specialized C++class encapsulating the computationally efficient procedures suited to the task.
