Search

XENONnT is a dual-phase time projection chamber with a target of 6 tonnes of ultra-pure liquid xenon which aims to search for dark matter via its scattering process. In XENONnT, incoming particles scatter and excite the target xenon atoms, resulting in an initial scintillation signal and an ionization reaction. The freed electrons from the ionization cause a second, larger ionization signal at the liquid-gas interface. Both of these signals are measured by arrays of photosensors. These photosensor measurements allow energy reconstruction of the incoming particle, which is crucial for particle identification and energy resolution in rare event searches. This poster discusses the potential use of semi-supervised autoencoders to infer one component of the total energy of the incoming interaction and to provide a method of faster data simulation.

The common form of inter-institute particle physics experiment collaborations generates unique needs for member management including paper authorship, shift assignments, subscription to mailing lists and access to 3rd party applications such as Github and Slack. For smaller collaborations, typically no facility for centralized member management is available and these needs are usually manually handled by long-term members in smaller collaborations but the management becomes tedious as collaborations grow. To automate many of these tasks for the expanding XENON collaboration, we developed the XENONnT User Management Website, a web application that stores and updates data related to the collaboration members through the use of NodeJs and MongoDB. The application allows for the scheduling of shifts for members to coordinate between institutes. User manipulation of 3rd party applications are implemented using REST API integration. The XENONnT User Management Website is open source and is a show case of quick implementation of utility application using the web framework.

The carotid web is commonly found in the carotid bulb or the beginning of the internal carotid artery. It presents as a thin layer of proliferative intimal tissue originating from the arterial wall and extending into the vessel lumen. A large body of research has proven that the carotid web is a risk factor for ischemic stroke. This review summarizes the current research status of the carotid web and focuses on its imaging presentation.

We demonstrate that Bayesian networks fill a significant methodology gap for uncertainty quantification in particle physics, providing a framework for modeling complex systems with physical constraints.To address the problem of interaction position reconstruction in dark matter direct-detection experiments, we built a Bayesian network that utilizes domain knowledge of the system in both the structure of the graph and the representation of the random variables.This method yielded highly informative per-interaction uncertainties that were previously unattainable using existing methodologies, while also demonstrating comparable precision on reconstructed positions.

We demonstrate that Bayesian networks fill a significant methodology gap for uncertainty quantification in particle physics, providing a framework for modeling complex systems with physical constraints.To address the problem of interaction position reconstruction in dark matter direct-detection experiments, we built a Bayesian network that utilizes domain knowledge of the system in both the structure of the graph and the representation of the random variables.This method yielded highly informative per-interaction uncertainties that were previously unattainable using existing methodologies, while also demonstrating comparable precision on reconstructed positions.

Image recognition technology with faster training speed and higher recognition accuracy has always been the focus and frontier of intelligent technology research. Sorting image fast recognition is of great significance to improve logistics efficiency in unmanned warehouse and other occasions. The simulation of sorting image fast recognition based on deep learning is studied. A convolution neural network is designed. For the specific environment of logistics warehouse and the specified objects to be identified, the sorting image is not very clear because of the closed environment and illumination conditions of warehouse. Firstly, the dual tree complex wavelet transform is used to denoise the sorting image. Then, on the basis of AlexNet neural network, the convolution layer of convolution neural network is dealt with. ReLU layer and pooling layer parameters are redefined to speed up the learning speed of the neural network. Then, according to the new image classification task, the last three layers of the neural network are defined, which are full connection layer, Softmax layer and classification output layer, to adapt to the new image recognition. The proposed fast sorting image recognition technology based on depth learning has higher training speed and recognition accuracy in the face of more complex sorting image recognition.

Robust position reconstruction is paramount for enabling discoveries in astroparticle physics as backgrounds are significantly reduced by only considering interactions within the fiducial volume. In this work, we present for the first time a method for position reconstruction using a Bayesian network which provides per interaction uncertainties. We demonstrate the utility of this method with simulated data based on the XENONnT detector design, a dual-phase xenon time-projection chamber, as a proof-of-concept. The network structure includes variables representing the 2D position of the interaction within the detector, the number of electrons entering the gaseous phase, and the hits measured by each sensor in the top array of the detector. The precision of the position reconstruction (difference between the true and expectation value of position) is comparable to the state-of-the-art methods -- an RMS of 0.69 cm, ~0.09 of the sensor spacing, for the inner part of the detector (60 cm). More importantly, the uncertainty of each interaction position was directly computed, which is not possible with other reconstruction methods. The method found a median 3-$σ$ confidence region of 11 cm$^2$ for the inner part of the detector and 21 cm$^2$ near the wall of the detector. We found the Bayesian network framework to be well suited to the problem of position reconstruction. The performance of this proof-of-concept, even with several simplifying assumptions, shows that this is a promising method for providing per interaction uncertainty, which can be extended to energy reconstruction and signal classification., 16 pages, 22 figures

Dark matter constitutes 85% of the matter in our Universe. However, detecting dark matter experimentally is exceedingly difficult, with the XENON1T dark matter detector being the most sensitive measurement to date. These difficulties arise from trying to measure extremely low energies and perform regressions with a poor signal-to-noise ratio. Previous attempts tried to solve this with convolution neural networks, but experienced problems due to the structure of experimental physics data (non-square lattices). We present the first application of graph convolutional neural networks (GCNN) to this regression problem in our dark-matter field. Beyond having a more natural architecture design, we attempt to include physical constraints such as: all results from the regression occurring within the bounds of the experiment and being uniform. As another goal, we place the requirement that only 1 part per 10 million of the regression results are more than 1 cm off from the target. Our prototype GCNN was built with two graph convolution layers, a final fully connected layer, and a mean squared error cost function. This prototype was able to produce below 3 mm root mean squared error in both the x and y dimensions, where the spacing between light sensors is 7 cm. XENONnT will provide the perfect test case for these methods as it is already collecting data, with the promise of extending this test case to other areas of particle physics.

Dark Matter comprises 85% of the Universe, yet there is no experimental knowledge of its properties. Direct detection experiments generate Petabytes of extremely noisy spatiotemporal data, in which scientists search for the signatures of exceptionally rare particles at the noise level of the sensors. Currently used techniques do not readily allow for domain knowledge to be incorporated into the models that are being built and learned for supporting this search. As a way of embedding domain knowledge into the solution, we propose using the framework of probabilistic graphical models, which can readily incorporate physical constraints and prior knowledge. The learned Probabilistic Graphical Model can be used to infer interaction positions of experimentally measured events, and thus uncover the meaningful signals in noisy detector data.

DIDACTS (Data-Intensive Discovery Accelerated by Computational Techniques for Science) is a collaboration of physicists and machine learning experts with an overall goal of incorporate scientific knowledge into machine learning and data science methods in the context of scientific disciplines. As part of DIDACTS’ research program, we are looking into the challenging problem of Dark Matter direct detection using XENON1T as test bed. The core principle of DIDACTS is that many particle physics experiments lend themselves to 'graphical' data analysis as the data is often hierarchical and irregular. In this talk we will highlight some of DIDACTS’ projects such as; graphical convolutional neural networks, quasi-supervised learning via inverse problem regularization, graph learning, and having per-event reconstruction uncertainties using graphical models., Recording: https://stanford.zoom.us/rec/play/v5Msceqo-2g3T4ad5ASDBvN4W466K6qs03If_KYPn0_hWiYBOwD0M7sUM-fggeHxsjGn7SxcBkJ0SGlN?startTime=1595343774000&_x_zm_rtaid=X6OHFxLzRhuEc896Y2IjAA.1596989159546.a224172c13fe60435b63210084206fc2&_x_zm_rhtaid=193 This work is supported by the National Science Foundation through awards 1940074, 1940209, and 1940080.