Confining dark sectors with pseudo-conformal dynamics can produce Soft Unclustered Energy Patterns (SUEP), at the Large Hadron Collider: the production of dark quarks in proton–proton collisions leading to a dark shower and the high-multiplicity production of dark hadrons. The final experimental signature is spherically symmetric energy deposits by an anomalously large number of soft Standard Model particles with a transverse energy of O(100)\(\,\text {MeV}\). Assuming Yukawa-like couplings of the scalar portal state, the dominant production mode is gluon fusion, and the dominant background comes from multi-jet QCD events. We have developed a deep learning-based Anomaly Detection technique to reject QCD jets and identify any anomalous signature, including SUEP, in real-time in the High-Level Trigger system of experiments like the Compact Muon Solenoid at the Large Hadron Collider. A deep convolutional neural autoencoder network has been trained using QCD events by taking transverse energy deposits in the inner tracker, electromagnetic calorimeter, and hadron calorimeter sub-detectors as 3-channel image data. Due to the sparse nature of the data, only \(\sim \)0.5% of the total \(\sim \) \({300}\,\textrm{k}\) image pixels have nonzero values. To tackle this challenge, a nonstandard loss function, the inverse of the so-called Dice Loss, is exploited. The trained autoencoder with learned spatial features of QCD jets can detect 40% of the SUEP events, with a QCD event mistagging rate as low as 2%. The model inference time has been measured using the Intel® Core\(^{\texttt {TM}}\) i5-9600KF processor and found to be \(\sim \) \({20}\textrm{ms}\), which perfectly satisfies the High-Level Trigger system’s latency of \(\mathcal {O}(10^2)~\textrm{ms}\). Given the virtue of the unsupervised learning of the autoencoders, the trained model can be applied to any new physics model that predicts an experimental signature anomalous to QCD jets.

在大型强子对撞机上，用伪共形动力学限制暗扇区可以产生软非团簇能量模式（SUEP）：质子-质子碰撞中产生暗夸克，从而导致暗簇射和暗强子的高多重性产生。最终的实验特征是由异常大量的软标准模型粒子形成的球对称能量沉积，横向能量为 O(100) \(\,\text {MeV}\)。假设标量门态的类汤川耦合，主要产生模式是胶子聚变，主要背景来自多射流QCD事件。我们开发了一种基于深度学习的异常检测技术，可以在大型强子对撞机的紧凑型介子螺线管等实验的高级触发系统中实时拒绝 QCD 射流并识别任何异常特征，包括 SUEP。通过将内部跟踪器、电磁热量计和强子热量计子探测器中的横向能量沉积作为 3 通道图像数据，使用 QCD 事件训练深度卷积神经自动编码器网络。由于数据的稀疏性，只有总\ (\sim \ ) \({300}\,\textrm{k}\)图像像素的 0.5% 具有非零值。为了应对这一挑战，我们利用了非标准损失函数，即所谓的骰子损失的逆函数。经过训练的自动编码器具有学习的 QCD 射流空间特征，可以检测 40% 的 SUEP 事件，QCD 事件误标记率低至 2%。使用Intel® Core \(^{\texttt {TM}}\)  i5-9600KF处理器测量模型推理时间，结果为\(\sim \) \({20}\textrm{ms}\)，完美满足高级触发系统的延迟\(\mathcal {O}(10^2)~\textrm{ms}\)。鉴于自动编码器的无监督学习的优点，训练后的模型可以应用于任何新的物理模型，该模型可以预测 QCD 射流异常的实验特征。