arXiv subjects

Liangjian Wen

Publications and source records attributed to Liangjian Wen.

At least 37 records · Page 2Linked to original sources

arXiv2024

Machine-Learning based photon counting for PMT waveforms and its application to the improvement of the energy resolution in large liquid scintillator detectors

Photomultiplier tubes (PMTs) are widely used in particle experiments for photon detection. PMT waveform analysis is crucial for high-precision measurements of the position and energy of incident particles in liquid scintillator (LS) detectors. A key factor contributing to the energy resolution in large liquid scintillator detectors with PMTs is the charge smearing of PMTs. This paper presents a machine-learning-based photon counting method for PMT waveforms and its application to the energy reconstruction, using the JUNO experiment as an example. The results indicate that leveraging the photon counting information from the machine learning model can partially mitigate the impact of PMT charge smearing and lead to a relative 2.0% to 2.8% improvement on the energy resolution in the energy range of [1, 9] MeV.

physics.ins-det↗

arXiv2024

TimeCNN: Refining Cross-Variable Interaction on Time Point for Time Series Forecasting

Time series forecasting is extensively applied across diverse domains. Transformer-based models demonstrate significant potential in modeling cross-time and cross-variable interaction. However, we notice that the cross-variable correlation of multivariate time series demonstrates multifaceted (positive and negative correlations) and dynamic progression over time, which is not well captured by existing Transformer-based models. To address this issue, we propose a TimeCNN model to refine cross-variable interactions to enhance time series forecasting. Its key innovation is timepoint-independent, where each time point has an independent convolution kernel, allowing each time point to have its independent model to capture relationships among variables. This approach effectively handles both positive and negative correlations and adapts to the evolving nature of variable relationships over time. Extensive experiments conducted on 12 real-world datasets demonstrate that TimeCNN consistently outperforms state-of-the-art models. Notably, our model achieves significant reductions in computational requirements (approximately 60.46%) and parameter count (about 57.50%), while delivering inference speeds 3 to 4 times faster than the benchmark iTransformer model

cs.LG↗

arXiv2024

A practical approach of measuring $^{238}$U and $^{232}$Th in liquid scintillator to sub-ppq level using ICP-MS

Liquid scintillator (LS) is commonly utilized in experiments seeking rare events due to its high light yield, transparency, and radiopurity. The concentration of $^{238}$U and $^{232}$Th in LS consistently remains below 1 ppq (10$^{-15}$ g/g), and the current screening result is based on a minimum 20-ton detector. Inductively coupled plasma mass (ICP-MS) spectroscopy is well-regarded for its high sensitivity to trace $^{238}$U and $^{232}$Th. This study outlines a method for detecting $^{238}$U and $^{232}$Th in LS at the sub-ppq level using ICP-MS, involving the enrichment of $^{238}$U/$^{232}$Th from the LS through acid extraction. With meticulous cleanliness control, $^{238}$U/$^{232}$Th in approximately 2 kg of LS is concentrated by acid extraction with 0.4 (0.3) pg $^{238}$U ($^{232}$Th) contamination. Three standard adding methods are employed to assess recovery efficiency, including radon daughter, 2,5-diphenyloxazole (PPO), and natural non-existent $^{233}$U/$^{229}$Th. The method detection limit at a 99% confidence level of this approach can reach approximately 0.2-0.3 ppq for $^{238}$U/$^{232}$Th with nearly 100% recovery efficiency.

physics.ins-det↗

arXiv2024

MVEB: Self-Supervised Learning with Multi-View Entropy Bottleneck

Self-supervised learning aims to learn representation that can be effectively generalized to downstream tasks. Many self-supervised approaches regard two views of an image as both the input and the self-supervised signals, assuming that either view contains the same task-relevant information and the shared information is (approximately) sufficient for predicting downstream tasks. Recent studies show that discarding superfluous information not shared between the views can improve generalization. Hence, the ideal representation is sufficient for downstream tasks and contains minimal superfluous information, termed minimal sufficient representation. One can learn this representation by maximizing the mutual information between the representation and the supervised view while eliminating superfluous information. Nevertheless, the computation of mutual information is notoriously intractable. In this work, we propose an objective termed multi-view entropy bottleneck (MVEB) to learn minimal sufficient representation effectively. MVEB simplifies the minimal sufficient learning to maximizing both the agreement between the embeddings of two views and the differential entropy of the embedding distribution. Our experiments confirm that MVEB significantly improves performance. For example, it achieves top-1 accuracy of 76.9\% on ImageNet with a vanilla ResNet-50 backbone on linear evaluation. To the best of our knowledge, this is the new state-of-the-art result with ResNet-50.

cs.CV↗

arXiv2024

Expected geoneutrino signal at JUNO using local integrated 3-D refined crustal model

Geoneutrinos serve as a potent tool for comprehending the radiogenic power and composition of Earth. Although geoneutrinos have been observed in prior experiments, the forthcoming generation of experiments,such as JUNO, will be necessary for fully harnessing their potential. Precise prediction of the crustal contribution is vital for interpreting particlephysics measurements in the context of geo-scientific inquiries. Nonetheless, existing models such as JULOC and GIGJ have limitations in accurately forecasting the crustal contribution. This paper introduces JULOCI, the novel 3-D integrated crustal model of JUNO, which employs seismic, gravity, rock sample, and heat flow data to precisely estimate the geoneutrino signal of the lithosphere. The model indicates elevated concentrations of uranium and thorium in southern China, resulting in unexpectedly strong geoneutrino signals.The accuracy of JULOC-I, coupled with a decade of experimental data, affords JUNO the opportunity to test multiple mantle models. Once operational, JUNO can validate the model predictions and enhance the precision of mantle measurements. All in all, the improved accuracy ofJULOC-I represents a substantial stride towards comprehending the geochemical distribution of the South China crust, offering a valuable tool for investigating the composition and evolution of the Earth through geoneutrinos.

physics.geo-ph↗

arXiv2024

Enhancing Multivariate Time Series Forecasting with Mutual Information-driven Cross-Variable and Temporal Modeling

Recent advancements have underscored the impact of deep learning techniques on multivariate time series forecasting (MTSF). Generally, these techniques are bifurcated into two categories: Channel-independence and Channel-mixing approaches. Although Channel-independence methods typically yield better results, Channel-mixing could theoretically offer improvements by leveraging inter-variable correlations. Nonetheless, we argue that the integration of uncorrelated information in channel-mixing methods could curtail the potential enhancement in MTSF model performance. To substantiate this claim, we introduce the Cross-variable Decorrelation Aware feature Modeling (CDAM) for Channel-mixing approaches, aiming to refine Channel-mixing by minimizing redundant information between channels while enhancing relevant mutual information. Furthermore, we introduce the Temporal correlation Aware Modeling (TAM) to exploit temporal correlations, a step beyond conventional single-step forecasting methods. This strategy maximizes the mutual information between adjacent sub-sequences of both the forecasted and target series. Combining CDAM and TAM, our novel framework significantly surpasses existing models, including those previously considered state-of-the-art, in comprehensive tests.

cs.LG↗

arXiv2024

PDETime: Rethinking Long-Term Multivariate Time Series Forecasting from the perspective of partial differential equations

Recent advancements in deep learning have led to the development of various models for long-term multivariate time-series forecasting (LMTF), many of which have shown promising results. Generally, the focus has been on historical-value-based models, which rely on past observations to predict future series. Notably, a new trend has emerged with time-index-based models, offering a more nuanced understanding of the continuous dynamics underlying time series. Unlike these two types of models that aggregate the information of spatial domains or temporal domains, in this paper, we consider multivariate time series as spatiotemporal data regularly sampled from a continuous dynamical system, which can be represented by partial differential equations (PDEs), with the spatial domain being fixed. Building on this perspective, we present PDETime, a novel LMTF model inspired by the principles of Neural PDE solvers, following the encoding-integration-decoding operations. Our extensive experimentation across seven diverse real-world LMTF datasets reveals that PDETime not only adapts effectively to the intrinsic spatiotemporal nature of the data but also sets new benchmarks, achieving state-of-the-art results

cs.LG↗

arXiv2023

Environmental radon control in the 700-m underground laboratory at JUNO

The Jiangmen Underground Neutrino Observatory is building the world's largest liquid scintillator detector with a 20 kt target mass and about 700 m overburden. The total underground space of civil construction is about 300,000 m$^3$ with the main hall volume of about 120,000 m$^3$, which is the biggest laboratory in the world. Radon concentration in the underground air is quite important for not only human beings' health but also the background of experiments with rare decay detection, such as neutrino and dark matter experiments. The radon concentration is the main hall is required to be around 100 Bq/m$^3$. Optimization of the ventilation with fresh air is effective to control the radon underground. To find the radon sources in the underground laboratory, we made a benchmark experiment in the refuge room near the main hall. The result shows that the radon emanating from underground water is one of the main radon sources in the underground air. The total underground ventilation rate is about 160,000 m$^3$/h fresh air with about 30 Bq/m$^3$ $^{222}$Rn from the bottom of the vertical tunnel after optimization, and 55,000 m$^3$/h is used for the ventilation in the main hall. Finally, the radon concentration inside the main hall decreased from 1600 Bq/m$^3$ to around 100 Bq/m$^3$. The suggested strategies for controlling radon concentration in the underground air are described in this paper.

physics.ins-det↗

arXiv2023

Simulation Software of the JUNO Experiment

The Jiangmen Underground Neutrino Observatory (JUNO) is a multi-purpose experiment, under construction in southeast China, that is designed to determine the neutrino mass ordering and precisely measure neutrino oscillation parameters. Monte Carlo simulation plays an important role for JUNO detector design, detector commissioning, offline data processing, and physics processing. The JUNO experiment has the world's largest liquid scintillator detector instrumented with many thousands of PMTs. The broad energy range of interest, long lifetime, and the large scale present data processing challenges across all areas. This paper describes the JUNO simulation software, highlighting the challenges of JUNO simulation and solutions to meet these challenges, including such issues as support for time-correlated analysis, event mixing, event correlation and handling the simulation of many millions of optical photons.

hep-ex↗

arXiv2023

Generative Oversampling for Imbalanced Data via Majority-Guided VAE

Learning with imbalanced data is a challenging problem in deep learning. Over-sampling is a widely used technique to re-balance the sampling distribution of training data. However, most existing over-sampling methods only use intra-class information of minority classes to augment the data but ignore the inter-class relationships with the majority ones, which is prone to overfitting, especially when the imbalance ratio is large. To address this issue, we propose a novel over-sampling model, called Majority-Guided VAE~(MGVAE), which generates new minority samples under the guidance of a majority-based prior. In this way, the newly generated minority samples can inherit the diversity and richness of the majority ones, thus mitigating overfitting in downstream tasks. Furthermore, to prevent model collapse under limited data, we first pre-train MGVAE on sufficient majority samples and then fine-tune based on minority samples with Elastic Weight Consolidation(EWC) regularization. Experimental results on benchmark image datasets and real-world tabular data show that MGVAE achieves competitive improvements over other over-sampling methods in downstream classification tasks, demonstrating the effectiveness of our method.

cs.LG↗

arXiv2023

Study on U/Th residual radioactivity in acrylic from surface treatment

Acrylic is widely used as material for the target container in low background experiments due to its high light transparency and low intrinsic radioactivity. However, its surface can be easily contaminated during production, so careful treatment of the surface is essential to avoid direct contamination of the target. The Jiangmen Underground Neutrino Observatory will use about 600~t of acrylic to build the spherical vessel of 35.4~m in diameter for a 20~kt liquid scintillator (LS). Since acrylic will contact the LS directly, the cleanliness of the its surface is quite important for the radiopurity of the LS. A new method for measuring the radioactivity of $^{238}$U and $^{232}$Th in acrylic to sub-ppt ($<10^{-12}$~g/g) was developed, and it is crucial for the acrylic radioactivity screening in this study. We performed many background tests on different surface treatments, and the recommended procedure for the treatment of acrylic to achieve low radioactivity and high light transparency could be applicable to other low background experiments.

physics.ins-det↗

arXiv2022

Structure-Preserving Graph Representation Learning

Though graph representation learning (GRL) has made significant progress, it is still a challenge to extract and embed the rich topological structure and feature information in an adequate way. Most existing methods focus on local structure and fail to fully incorporate the global topological structure. To this end, we propose a novel Structure-Preserving Graph Representation Learning (SPGRL) method, to fully capture the structure information of graphs. Specifically, to reduce the uncertainty and misinformation of the original graph, we construct a feature graph as a complementary view via k-Nearest Neighbor method. The feature graph can be used to contrast at node-level to capture the local relation. Besides, we retain the global topological structure information by maximizing the mutual information (MI) of the whole graph and feature embeddings, which is theoretically reduced to exchanging the feature embeddings of the feature and the original graphs to reconstruct themselves. Extensive experiments show that our method has quite superior performance on semi-supervised node classification task and excellent robustness under noise perturbation on graph structure or node features.

cs.LG↗

arXiv2022

Determine Energy Nonlinearity and Resolution of $e^{\pm}$ and $γ$ in Liquid Scintillator Detectors by A Universal Energy Response Model

Energy nonlinearity and resolution in liquid scintillator (LS) detectors are correlated and particle-dependent. A unified energy response model for liquid scintillator detectors has been presented in details. This model has advanced a data-driven approach to calibrate the particle-dependent energy response, using both the monoenergetic $γ$-ray sources and the continuous $β$ spectra of $^\mathrm{12}\mathrm{B}$ and Michel $e^-$ induced by cosmic muons. Monte Carlo studies have demonstrated the effectiveness and robustness of the proposed model, in particular, the positron energy resolution can be extracted in the absence of positron sources. This work will provide a feasible approach of simultaneous calibration of energy nonlinearity and resolution for the running and future LS detectors.

hep-ex↗

arXiv2022

Self-Supervision Can Be a Good Few-Shot Learner

Existing few-shot learning (FSL) methods rely on training with a large labeled dataset, which prevents them from leveraging abundant unlabeled data. From an information-theoretic perspective, we propose an effective unsupervised FSL method, learning representations with self-supervision. Following the InfoMax principle, our method learns comprehensive representations by capturing the intrinsic structure of the data. Specifically, we maximize the mutual information (MI) of instances and their representations with a low-bias MI estimator to perform self-supervised pre-training. Rather than supervised pre-training focusing on the discriminable features of the seen classes, our self-supervised model has less bias toward the seen classes, resulting in better generalization for unseen classes. We explain that supervised pre-training and self-supervised pre-training are actually maximizing different MI objectives. Extensive experiments are further conducted to analyze their FSL performance with various training settings. Surprisingly, the results show that self-supervised pre-training can outperform supervised pre-training under the appropriate conditions. Compared with state-of-the-art FSL methods, our approach achieves comparable performance on widely used FSL benchmarks without any labels of the base classes.

cs.CV↗

arXiv2022

Development of silicon interposer: towards an ultralow radioactivity background photodetector system

It is of great importance to develop a photodetector system with an ultralow radioactivity background in rare event searches. Silicon photomultipliers (SiPMs) and application-specific integrated circuits (ASICs) are two ideal candidates for low background photosensors and readout electronics, respectively, because they are mainly composed of silicon, which can achieve good radio-purity without considerable extra effort. However, interposers, used to provide mechanical support and signal routes between the photosensor and the electronics, are a bottleneck in building ultralow background photodetectors. Silicon and quartz are two candidates to construct the low background interposer because of their good radio-purity; nevertheless, it is non-trivial to produce through silicon vias (TSV) or through quartz vias (TQV) on the large area silicon or quartz wafer. In this work, based on double-sided TSV interconnect technology, we developed the first prototype of a silicon interposer with a size of 10~cm$\times$10~cm and a thickness of 320~$μ$m. The electrical properties of the interposer are carefully evaluated at room temperature, and its performance is also examined at -110~$^\circ$C with an integrated SiPM on the interposer. The testing results reveal quite promising performance of the prototype, and the single photoelectron signals can be clearly observed from the SiPM. The features of the observed signals are comparable with those from the SiPM mounted on a normal FR4-based PCB. Based on the success of the silicon interposer prototype, we started the follow-up studies that aimed to further improve the performance and yield of the silicon interposer, and eventually to provide a solution for building an ultralow background photodetector system.

physics.ins-det↗

arXiv2022

A New Optical Model for Photomultiplier Tubes

It is critical to construct an accurate optical model of photomultiplier tubes (PMTs) in many applications to describe the angular and spectral responses of the photon detection efficiency (PDE) of the PMTs in their working media. In this study, we propose a new PMT optical model to describe both light interactions with the PMT window and optical processes inside PMTs with reasonable accuracy based on the optics theory and a GEANT4-based simulation toolkit. The proposed model builds a relationship between the PDE and the underlying processes that the PDE relies on. This model also provides a tool to transform the PDE measured in one working medium (like air) to the PDE in other media (like water, liquid scintillator, etc). Using two 20" MCP-PMTs and one 20" dynode PMT, we demonstrate a complete procedure to obtain the key parameters used in the model from experimental data, such as the optical properties of the antireflective coating and photocathode of the three PMTs. The proposed model can effectively reproduce the angular responses of the quantum efficiency of PMTs, even though an ideally uniform photocathode is assumed in the model. Interestingly, the proposed model predicts a similar level ($20\%\sim30\%$) of light yield excess observed in the experimental data of many liquid scintillator-based neutrino detectors, compared with that predicted at the stage of detector design. However, this excess has never been explained, and the proposed PMT model provides a good explanation for it, which highlights the imperfections of PMT models used in their detector simulations.

physics.ins-det↗

arXiv2022

Rectifying the Shortcut Learning of Background for Few-Shot Learning

The category gap between training and evaluation has been characterised as one of the main obstacles to the success of Few-Shot Learning (FSL). In this paper, we for the first time empirically identify image background, common in realistic images, as a shortcut knowledge helpful for in-class classification but ungeneralizable beyond training categories in FSL. A novel framework, COSOC, is designed to tackle this problem by extracting foreground objects in images at both training and evaluation without any extra supervision. Extensive experiments carried on inductive FSL tasks demonstrate the effectiveness of our approaches.

cs.CV↗

arXiv2021

Self-supervised Consensus Representation Learning for Attributed Graph

Attempting to fully exploit the rich information of topological structure and node features for attributed graph, we introduce self-supervised learning mechanism to graph representation learning and propose a novel Self-supervised Consensus Representation Learning (SCRL) framework. In contrast to most existing works that only explore one graph, our proposed SCRL method treats graph from two perspectives: topology graph and feature graph. We argue that their embeddings should share some common information, which could serve as a supervisory signal. Specifically, we construct the feature graph of node features via k-nearest neighbor algorithm. Then graph convolutional network (GCN) encoders extract features from two graphs respectively. Self-supervised loss is designed to maximize the agreement of the embeddings of the same node in the topology graph and the feature graph. Extensive experiments on real citation networks and social networks demonstrate the superiority of our proposed SCRL over the state-of-the-art methods on semi-supervised node classification task. Meanwhile, compared with its main competitors, SCRL is rather efficient.

cs.SI↗