论文标题
深度学习以改善高分辨率气体时间投影室中的KEV尺度后坐力识别
Deep learning for improved keV-scale recoil identification in high resolution gas time projection chambers
论文作者
论文摘要
具有方向敏感性的后坐力模仿气体时间投影室（TPC）对暗物质（DM）搜索具有吸引力。能够重建3D核后座方向的探测器将对DM后坐力的预测偶极角分布具有独特的敏感，这些偶极角反应分布将明确地建立声称的DM信号的银河系来源，并提供对来自太阳中微子的背景后退的强大歧视。但是，如果可以充分抑制伽玛射线的电子后坐背景，则可以利用这些优点。我们介绍了一个基于深度学习的后坐力事件分类器，该事件分类器使用3D卷积神经网络（3DCNN）根据其后坐力图像来识别事件物种。我们将3DCNN的电子背景拒绝性能与传统的轨道长度判别以及从最新的浅学习方法获得的判别物进行了比较。我们使用反冲电荷分布训练3DCNN分类器，其电离能量为0.5-10.5 $ \ rm kev_ {ee} $，在80:10:10 $ \ rm He $：$ \ rm cf_4 $：$ \ rm cf_4 $：$ \ rm rm cff_3 $中的80:10:10混合物中进行25 cm的漂移。当确定轨道长度和浅的学习判别物时，费用最初分为$（100 \ times 100 \ times 100）$ $ \rmμm^3 $ bins，但通过降低了约$（850 \ tims 850 \ times 850 \ times 850）$ \ $ $ $ \rmmμmmmmm^$^3 $^$ for 3dcnn n $（850 \ tims 850 \ times 850 \ times 850）。尽管有Courser binning，但与使用轨道长度相比，我们发现将事件与3DCNN分类可使电子背景减少1,000倍，并有效地将我们模拟TPC的能量阈值降低了30 \％的荧光内液，荧光线后退$ 50 \％\％\％\％。我们还发现，与浅机器学习方法相比，3DCNN可将电子背景降低到20倍，对应于2 $ \ rm kev_ {ee} $降低能量阈值。
Recoil-imaging gaseous time projection chambers (TPCs) with directional sensitivity are attractive for dark matter (DM) searches. Detectors capable of reconstructing 3D nuclear recoil directions would be uniquely sensitive to the predicted dipole angular distribution of DM recoils that would unambiguously establish the galactic origin of a claimed DM signal and provide powerful discrimination against background recoils from solar neutrinos. These advantages can only be exploited however, if electron recoil backgrounds from gamma rays can be sufficiently suppressed. We introduce a deep learning-based recoil event classifier that uses a 3D convolutional neural network (3DCNN) to identify event species based on their recoil images. We compare electron background rejection performance of the 3DCNN both to the traditional discriminant of track length, as well as discriminants obtained from state-of-the-art shallow learning methods. We train the 3DCNN classifier using recoil charge distributions with ionization energies ranging from 0.5-10.5 $\rm keV_{ee}$, for 25 cm of drift in an 80:10:10 mixture of $\rm He$:$\rm CF_4$:$\rm CHF_3$. The charges are initially segmented into $(100\times 100\times 100)$ $\rmμm^3$ bins when determining track length and the shallow learning discriminants, but are rebinned with a reduced segmentation of about $(850\times 850\times 850)$ $\rmμm^3$ for the 3DCNN. Despite the courser binning, compared to using track length, we find that classifying events with the 3DCNN reduces electron backgrounds by a factor of up to 1,000 and effectively reduces the energy threshold of our simulated TPC by $30\%$ for fluorine recoils and $50\%$ for helium recoils. We also find that the 3DCNN reduces electron backgrounds by up to a factor of 20 compared to the shallow machine learning approaches, corresponding to a 2 $\rm keV_{ee}$ reduction in the energy threshold.
