发表机构
University of Oxford; Nikhef; CERN（牛津大学; 荷兰国家亚原子物理研究所; 欧洲核子研究中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出基于紧凑前馈神经网络的Timepix4时间游走校正方法，无需显式函数假设或分箱，仅用20%校准数据即达到与拟合基线相当的渐近时间分辨率（180ps和300ps）。
AI 中文摘要
混合像素探测器的时间游走校正通常采用启发式拟合，这些拟合在相关输入变量的分箱中独立进行。这既需要显式的函数假设和分箱方案，也需要密集的校准数据，而随着输入变量的增加，所需数据量会迅速增长。本文提出了一种基于紧凑前馈神经网络（NN）的Timepix4读出芯片时间游走校正方法，该方法直接从输入变量学习依赖关系，无需显式函数假设或分箱。利用2025年在CERN SPS的Timepix4束流望远镜上获取的数据，将神经网络与基于拟合的基线方法进行了比较，这些数据来自厚度为$100\\,\mathrm{\mu m}$和$300\\,\mathrm{\mu m}$的平面传感器。两种方法都将时间游走校正参数化为测量电荷和重建的像素内撞击位置的函数。仅使用20%的校准数据，神经网络就已达到与基于拟合的基线相同的渐近时间分辨率：对于两种厚度分别为$180\\,\mathrm{ps}$和$300\\,\mathrm{ps}$。
英文摘要
Timewalk corrections of hybrid pixel detectors conventionally employ heuristic fits performed independently in bins of the relevant input variables. This requires both an explicit functional ansatz and binning scheme, as well as densely populated calibration data whose required size grows rapidly as further input variables are added. This paper presents a timewalk correction for the Timepix4 readout chip based on a compact feed-forward neural network (NN), which learns the dependence directly from the input variables without requiring an explicit functional ansatz or binning. The NN is compared against the fit-based baseline using data from the Timepix4 beam telescope at the CERN SPS in 2025, with $100\,\mathrm{μm}$ and $300\,\mathrm{μm}$ thick planar sensors. Both methods parameterise the timewalk correction as a function of the measured charge and reconstructed intrapixel impact position. With only 20 % of the calibration data, the NN already achieves the same asymptotic time resolutions as the fit-based baseline: $180\,\mathrm{ps}$ and $300\,\mathrm{ps}$ for the two thicknesses, respectively.
